struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
unsigned long offset;
struct ext3_group_desc * desc;
struct ext3_sb_info *sbi = EXT3_SB(sb);
if (block_group >= sbi->s_groups_count) {
ext3_error (sb, "ext3_get_group_desc",
"block_group >= groups_count - "
"block_group = %d, groups_count = %lu",
block_group, sbi->s_groups_count);
return NULL;
}
smp_rmb();
group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT3_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
ext3_error (sb, "ext3_get_group_desc",
"Group descriptor not loaded - "
"block_group = %d, group_desc = %lu, desc = %lu",
block_group, group_desc, offset);
return NULL;
}
desc = (struct ext3_group_desc *) sbi->s_group_desc[group_desc]->b_data;
if (bh)
*bh = sbi->s_group_desc[group_desc];
return desc + offset;
}
struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
unsigned long desc;
struct ext3_group_desc * gdp;
if (block_group >= EXT3_SB(sb)->s_groups_count) {
ext3_error (sb, "ext3_get_group_desc",
"block_group >= groups_count - "
"block_group = %d, groups_count = %lu",
block_group, EXT3_SB(sb)->s_groups_count);
return NULL;
}
smp_rmb();
group_desc = block_group / EXT3_DESC_PER_BLOCK(sb);
desc = block_group % EXT3_DESC_PER_BLOCK(sb);
if (!EXT3_SB(sb)->s_group_desc[group_desc]) {
ext3_error (sb, "ext3_get_group_desc",
"Group descriptor not loaded - "
"block_group = %d, group_desc = %lu, desc = %lu",
block_group, group_desc, desc);
return NULL;
}
gdp = (struct ext3_group_desc *)
EXT3_SB(sb)->s_group_desc[group_desc]->b_data;
if (bh)
*bh = EXT3_SB(sb)->s_group_desc[group_desc];
return gdp + desc;
}
/*
* Read the inode allocation bitmap for a given block_group, reading
* into the specified slot in the superblock's bitmap cache.
*
* Return >=0 on success or a -ve error code.
*/
static int read_inode_bitmap (struct super_block * sb,
unsigned long block_group,
unsigned int bitmap_nr)
{
struct ext3_group_desc * gdp;
struct buffer_head * bh = NULL;
int retval = 0;
gdp = ext3_get_group_desc (sb, block_group, NULL);
if (!gdp) {
retval = -EIO;
goto error_out;
}
bh = sb_bread(sb, le32_to_cpu(gdp->bg_inode_bitmap));
if (!bh) {
ext3_error (sb, "read_inode_bitmap",
"Cannot read inode bitmap - "
"block_group = %lu, inode_bitmap = %lu",
block_group, (unsigned long) gdp->bg_inode_bitmap);
retval = -EIO;
}
/*
* On IO error, just leave a zero in the superblock's block pointer for
* this group. The IO will be retried next time.
*/
error_out:
sb->u.ext3_sb.s_inode_bitmap_number[bitmap_nr] = block_group;
sb->u.ext3_sb.s_inode_bitmap[bitmap_nr] = bh;
return retval;
}
int ext3_check_dir_entry (const char * function, struct inode * dir,
struct ext3_dir_entry_2 * de,
struct buffer_head * bh,
unsigned long offset)
{
const char * error_msg = NULL;
const int rlen = le16_to_cpu(de->rec_len);
if (rlen < EXT3_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
else if (rlen % 4 != 0)
error_msg = "rec_len % 4 != 0";
else if (rlen < EXT3_DIR_REC_LEN(de->name_len))
error_msg = "rec_len is too small for name_len";
else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
error_msg = "directory entry across blocks";
else if (le32_to_cpu(de->inode) >
le32_to_cpu(dir->i_sb->u.ext3_sb.s_es->s_inodes_count))
error_msg = "inode out of bounds";
if (error_msg != NULL)
ext3_error (dir->i_sb, function,
"bad entry in directory #%lu: %s - "
"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
dir->i_ino, error_msg, offset,
(unsigned long) le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
}
/* Called at mount-time, super-block is locked */
void ext3_check_inodes_bitmap (struct super_block * sb)
{
struct ext3_super_block * es;
unsigned long desc_count, bitmap_count, x;
struct buffer_head *bitmap_bh = NULL;
struct ext3_group_desc * gdp;
int i;
es = EXT3_SB(sb)->s_es;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;
for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++) {
gdp = ext3_get_group_desc (sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, i);
if (!bitmap_bh)
continue;
x = ext3_count_free(bitmap_bh, EXT3_INODES_PER_GROUP(sb) / 8);
if (le16_to_cpu(gdp->bg_free_inodes_count) != x)
ext3_error (sb, "ext3_check_inodes_bitmap",
"Wrong free inodes count in group %d, "
"stored = %d, counted = %lu", i,
le16_to_cpu(gdp->bg_free_inodes_count), x);
bitmap_count += x;
}
brelse(bitmap_bh);
if (le32_to_cpu(es->s_free_inodes_count) != bitmap_count)
ext3_error (sb, "ext3_check_inodes_bitmap",
"Wrong free inodes count in super block, "
"stored = %lu, counted = %lu",
(unsigned long)le32_to_cpu(es->s_free_inodes_count),
bitmap_count);
}
/* Called at mount-time, super-block is locked */
void ext3_check_inodes_bitmap (struct super_block * sb)
{
struct ext3_super_block * es;
unsigned long desc_count, bitmap_count, x;
int bitmap_nr;
struct ext3_group_desc * gdp;
int i;
es = sb->u.ext3_sb.s_es;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;
for (i = 0; i < sb->u.ext3_sb.s_groups_count; i++) {
gdp = ext3_get_group_desc (sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
bitmap_nr = load_inode_bitmap (sb, i);
if (bitmap_nr < 0)
continue;
x = ext3_count_free (sb->u.ext3_sb.s_inode_bitmap[bitmap_nr],
EXT3_INODES_PER_GROUP(sb) / 8);
if (le16_to_cpu(gdp->bg_free_inodes_count) != x)
ext3_error (sb, "ext3_check_inodes_bitmap",
"Wrong free inodes count in group %d, "
"stored = %d, counted = %lu", i,
le16_to_cpu(gdp->bg_free_inodes_count), x);
bitmap_count += x;
}
if (le32_to_cpu(es->s_free_inodes_count) != bitmap_count)
ext3_error (sb, "ext3_check_inodes_bitmap",
"Wrong free inodes count in super block, "
"stored = %lu, counted = %lu",
(unsigned long)le32_to_cpu(es->s_free_inodes_count),
bitmap_count);
}
static struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
struct ext3_group_desc * desc;
struct buffer_head * bh = NULL;
ext3_fsblk_t bitmap_blk;
desc = ext3_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext3_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
if (likely(bh_uptodate_or_lock(bh)))
return bh;
if (bh_submit_read(bh) < 0) {
brelse(bh);
ext3_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
ext3_valid_block_bitmap(sb, desc, block_group, bh);
/*
* file system mounted not to panic on error, continue with corrupt
* bitmap
*/
return bh;
}
/*
* Read the bitmap for a given block_group, reading into the specified
* slot in the superblock's bitmap cache.
*
* Return buffer_head on success or NULL in case of failure.
*/
static struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
struct ext3_group_desc * desc;
struct buffer_head * bh = NULL;
desc = ext3_get_group_desc (sb, block_group, NULL);
if (!desc)
goto error_out;
bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap));
if (!bh)
ext3_error (sb, "read_block_bitmap",
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
error_out:
return bh;
}
static int ext3_valid_block_bitmap(struct super_block *sb,
struct ext3_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh)
{
ext3_grpblk_t offset;
ext3_grpblk_t next_zero_bit;
ext3_fsblk_t bitmap_blk;
ext3_fsblk_t group_first_block;
group_first_block = ext3_group_first_block_no(sb, block_group);
/* check whether block bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
offset = bitmap_blk - group_first_block;
if (!ext3_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
offset = bitmap_blk - group_first_block;
if (!ext3_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode table block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_table);
offset = bitmap_blk - group_first_block;
next_zero_bit = ext3_find_next_zero_bit(bh->b_data,
offset + EXT3_SB(sb)->s_itb_per_group,
offset);
if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group)
/* good bitmap for inode tables */
return 1;
err_out:
ext3_error(sb, __func__,
"Invalid block bitmap - "
"block_group = %d, block = %lu",
block_group, bitmap_blk);
return 0;
}
/*
* NOTE! When we get the inode, we're the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call "clear_inode()"
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext3_free_inode (handle_t *handle, struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
unsigned long block_group;
unsigned long bit;
struct ext3_group_desc * gdp;
struct ext3_super_block * es;
struct ext3_sb_info *sbi;
int fatal = 0, err;
if (atomic_read(&inode->i_count) > 1) {
printk ("ext3_free_inode: inode has count=%d\n",
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
printk ("ext3_free_inode: inode has nlink=%d\n",
inode->i_nlink);
return;
}
if (!sb) {
printk("ext3_free_inode: inode on nonexistent device\n");
return;
}
sbi = EXT3_SB(sb);
ino = inode->i_ino;
ext3_debug ("freeing inode %lu\n", ino);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
DQUOT_INIT(inode);
ext3_xattr_delete_inode(handle, inode);
DQUOT_FREE_INODE(inode);
DQUOT_DROP(inode);
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
clear_inode (inode);
es = EXT3_SB(sb)->s_es;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_free_inode",
"reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit, bitmap_bh->b_data))
ext3_error (sb, "ext3_free_inode",
"bit already cleared for inode %lu", ino);
else {
gdp = ext3_get_group_desc (sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bh2);
if (fatal) goto error_return;
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
gdp->bg_free_inodes_count = cpu_to_le16(
le16_to_cpu(gdp->bg_free_inodes_count) + 1);
if (is_directory)
gdp->bg_used_dirs_count = cpu_to_le16(
le16_to_cpu(gdp->bg_used_dirs_count) - 1);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
}
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (!fatal) fatal = err;
}
BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
error_return:
brelse(bitmap_bh);
ext3_std_error(sb, fatal);
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
{
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
unsigned long ino = 0;
struct inode * inode;
struct ext3_group_desc * gdp = NULL;
struct ext3_super_block * es;
struct ext3_inode_info *ei;
struct ext3_sb_info *sbi;
int err = 0;
struct inode *ret;
int i;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT3_I(inode);
sbi = EXT3_SB(sb);
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
group = find_group_dir(sb, dir);
else
group = find_group_orlov(sb, dir);
} else
group = find_group_other(sb, dir);
err = -ENOSPC;
if (group == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
gdp = ext3_get_group_desc(sb, group, &bh2);
if (!gdp)
goto fail;
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext3_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
if (ino < EXT3_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext3_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT3_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
}
/*
* This case is possible in concurrent environment. It is very
* rare. We cannot repeat the find_group_xxx() call because
* that will simply return the same blockgroup, because the
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
if (++group == sbi->s_groups_count)
group = 0;
}
err = -ENOSPC;
goto out;
got:
ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group, ino);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
gdp->bg_free_inodes_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
if (S_ISDIR(mode)) {
gdp->bg_used_dirs_count =
cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
sb->s_dirt = 1;
inode->i_uid = current->fsuid;
if (test_opt (sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current->fsgid;
inode->i_mode = mode;
inode->i_ino = ino;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blksize = PAGE_SIZE;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags = EXT3_I(dir)->i_flags & ~EXT3_INDEX_FL;
if (S_ISLNK(mode))
ei->i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
/* dirsync only applies to directories */
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT3_DIRSYNC_FL;
#ifdef EXT3_FRAGMENTS
ei->i_faddr = 0;
ei->i_frag_no = 0;
ei->i_frag_size = 0;
#endif
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
insert_inode_hash(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state = EXT3_STATE_NEW;
ei->i_extra_isize =
(EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ?
sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0;
ret = inode;
if(DQUOT_ALLOC_INODE(inode)) {
err = -EDQUOT;
goto fail_drop;
}
err = ext3_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext3_init_security(handle,inode, dir);
if (err)
goto fail_free_drop;
err = ext3_mark_inode_dirty(handle, inode);
if (err) {
ext3_std_error(sb, err);
goto fail_free_drop;
}
ext3_debug("allocating inode %lu\n", inode->i_ino);
goto really_out;
fail:
ext3_std_error(sb, err);
out:
iput(inode);
ret = ERR_PTR(err);
really_out:
brelse(bitmap_bh);
return ret;
fail_free_drop:
DQUOT_FREE_INODE(inode);
fail_drop:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
/*
* NOTE! When we get the inode, we're the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call "clear_inode()"
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext3_free_inode (handle_t *handle, struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
unsigned long block_group;
unsigned long bit;
struct ext3_group_desc * gdp;
struct ext3_super_block * es;
struct ext3_sb_info *sbi;
int fatal = 0, err;
if (atomic_read(&inode->i_count) > 1) {
printk ("ext3_free_inode: inode has count=%d\n",
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
printk ("ext3_free_inode: inode has nlink=%d\n",
inode->i_nlink);
return;
}
if (!sb) {
printk("ext3_free_inode: inode on nonexistent device\n");
return;
}
sbi = EXT3_SB(sb);
ino = inode->i_ino;
ext3_debug ("freeing inode %lu\n", ino);
trace_ext3_free_inode(inode);
is_directory = S_ISDIR(inode->i_mode);
es = EXT3_SB(sb)->s_es;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_free_inode",
"reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit, bitmap_bh->b_data))
ext3_error (sb, "ext3_free_inode",
"bit already cleared for inode %lu", ino);
else {
gdp = ext3_get_group_desc (sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bh2);
if (fatal) goto error_return;
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
le16_add_cpu(&gdp->bg_free_inodes_count, 1);
if (is_directory)
le16_add_cpu(&gdp->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
}
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (!fatal) fatal = err;
}
BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bitmap_bh);
if (!fatal)
fatal = err;
error_return:
brelse(bitmap_bh);
ext3_std_error(sb, fatal);
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
struct inode * ext3_new_inode (handle_t *handle,
const struct inode * dir, int mode)
{
struct super_block * sb;
struct buffer_head * bh;
struct buffer_head * bh2;
int i, j, avefreei;
struct inode * inode;
int bitmap_nr;
struct ext3_group_desc * gdp;
struct ext3_group_desc * tmp;
struct ext3_super_block * es;
int err = 0;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
init_rwsem(&inode->u.ext3_i.truncate_sem);
lock_super (sb);
es = sb->u.ext3_sb.s_es;
repeat:
gdp = NULL;
i = 0;
if (S_ISDIR(mode)) {
avefreei = le32_to_cpu(es->s_free_inodes_count) /
sb->u.ext3_sb.s_groups_count;
if (!gdp) {
for (j = 0; j < sb->u.ext3_sb.s_groups_count; j++) {
struct buffer_head *temp_buffer;
tmp = ext3_get_group_desc (sb, j, &temp_buffer);
if (tmp &&
le16_to_cpu(tmp->bg_free_inodes_count) &&
le16_to_cpu(tmp->bg_free_inodes_count) >=
avefreei) {
if (!gdp || (le16_to_cpu(tmp->bg_free_blocks_count) >
le16_to_cpu(gdp->bg_free_blocks_count))) {
i = j;
gdp = tmp;
bh2 = temp_buffer;
}
}
}
}
} else {
/*
* Try to place the inode in its parent directory
*/
i = dir->u.ext3_i.i_block_group;
tmp = ext3_get_group_desc (sb, i, &bh2);
if (tmp && le16_to_cpu(tmp->bg_free_inodes_count))
gdp = tmp;
else
{
/*
* Use a quadratic hash to find a group with a
* free inode
*/
for (j = 1; j < sb->u.ext3_sb.s_groups_count; j <<= 1) {
i += j;
if (i >= sb->u.ext3_sb.s_groups_count)
i -= sb->u.ext3_sb.s_groups_count;
tmp = ext3_get_group_desc (sb, i, &bh2);
if (tmp &&
le16_to_cpu(tmp->bg_free_inodes_count)) {
gdp = tmp;
break;
}
}
}
if (!gdp) {
/*
* That failed: try linear search for a free inode
*/
i = dir->u.ext3_i.i_block_group + 1;
for (j = 2; j < sb->u.ext3_sb.s_groups_count; j++) {
if (++i >= sb->u.ext3_sb.s_groups_count)
i = 0;
tmp = ext3_get_group_desc (sb, i, &bh2);
if (tmp &&
le16_to_cpu(tmp->bg_free_inodes_count)) {
gdp = tmp;
break;
}
}
}
}
err = -ENOSPC;
if (!gdp)
goto fail;
err = -EIO;
bitmap_nr = load_inode_bitmap (sb, i);
if (bitmap_nr < 0)
goto fail;
bh = sb->u.ext3_sb.s_inode_bitmap[bitmap_nr];
if ((j = ext3_find_first_zero_bit ((unsigned long *) bh->b_data,
EXT3_INODES_PER_GROUP(sb))) <
EXT3_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bh, "get_write_access");
err = ext3_journal_get_write_access(handle, bh);
if (err) goto fail;
if (ext3_set_bit (j, bh->b_data)) {
ext3_error (sb, "ext3_new_inode",
"bit already set for inode %d", j);
goto repeat;
}
BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh);
if (err) goto fail;
} else {
if (le16_to_cpu(gdp->bg_free_inodes_count) != 0) {
ext3_error (sb, "ext3_new_inode",
"Free inodes count corrupted in group %d",
i);
/* Is it really ENOSPC? */
err = -ENOSPC;
if (sb->s_flags & MS_RDONLY)
goto fail;
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
gdp->bg_free_inodes_count = 0;
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
}
goto repeat;
}
j += i * EXT3_INODES_PER_GROUP(sb) + 1;
if (j < EXT3_FIRST_INO(sb) || j > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d,inode=%d", i, j);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
gdp->bg_free_inodes_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
if (S_ISDIR(mode))
gdp->bg_used_dirs_count =
cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
BUFFER_TRACE(sb->u.ext3_sb.s_sbh, "get_write_access");
err = ext3_journal_get_write_access(handle, sb->u.ext3_sb.s_sbh);
if (err) goto fail;
es->s_free_inodes_count =
cpu_to_le32(le32_to_cpu(es->s_free_inodes_count) - 1);
BUFFER_TRACE(sb->u.ext3_sb.s_sbh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, sb->u.ext3_sb.s_sbh);
sb->s_dirt = 1;
if (err) goto fail;
inode->i_uid = current->fsuid;
if (test_opt (sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current->fsgid;
inode->i_mode = mode;
inode->i_ino = j;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blksize = PAGE_SIZE;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->u.ext3_i.i_flags = dir->u.ext3_i.i_flags & ~EXT3_INDEX_FL;
if (S_ISLNK(mode))
inode->u.ext3_i.i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
#ifdef EXT3_FRAGMENTS
inode->u.ext3_i.i_faddr = 0;
inode->u.ext3_i.i_frag_no = 0;
inode->u.ext3_i.i_frag_size = 0;
#endif
inode->u.ext3_i.i_file_acl = 0;
inode->u.ext3_i.i_dir_acl = 0;
inode->u.ext3_i.i_dtime = 0;
INIT_LIST_HEAD(&inode->u.ext3_i.i_orphan);
#ifdef EXT3_PREALLOCATE
inode->u.ext3_i.i_prealloc_count = 0;
#endif
inode->u.ext3_i.i_block_group = i;
if (inode->u.ext3_i.i_flags & EXT3_SYNC_FL)
inode->i_flags |= S_SYNC;
if (IS_SYNC(inode))
handle->h_sync = 1;
insert_inode_hash(inode);
inode->i_generation = sb->u.ext3_sb.s_next_generation++;
inode->u.ext3_i.i_state = EXT3_STATE_NEW;
err = ext3_mark_inode_dirty(handle, inode);
if (err) goto fail;
unlock_super (sb);
if(DQUOT_ALLOC_INODE(inode)) {
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
iput(inode);
return ERR_PTR(-EDQUOT);
}
ext3_debug ("allocating inode %lu\n", inode->i_ino);
return inode;
fail:
unlock_super(sb);
iput(inode);
ext3_std_error(sb, err);
return ERR_PTR(err);
}
static int ext3_readdir(struct file * filp,
void * dirent, filldir_t filldir)
{
int error = 0;
unsigned long offset, blk;
int i, num, stored;
struct buffer_head * bh, * tmp, * bha[16];
struct ext3_dir_entry_2 * de;
struct super_block * sb;
int err;
struct inode *inode = filp->f_dentry->d_inode;
int dir_has_error = 0;
sb = inode->i_sb;
stored = 0;
bh = NULL;
offset = filp->f_pos & (sb->s_blocksize - 1);
while (!error && !stored && filp->f_pos < inode->i_size) {
blk = (filp->f_pos) >> EXT3_BLOCK_SIZE_BITS(sb);
bh = ext3_bread (0, inode, blk, 0, &err);
if (!bh) {
if (!dir_has_error) {
ext3_error (sb, __func__, "directory #%lu "
"contains a hole at offset %lld",
inode->i_ino, filp->f_pos);
dir_has_error = 1;
}
filp->f_pos += sb->s_blocksize - offset;
continue;
}
/*
* Do the readahead
*/
if (!offset) {
for (i = 16 >> (EXT3_BLOCK_SIZE_BITS(sb) - 9), num = 0;
i > 0; i--) {
tmp = ext3_getblk (NULL, inode, ++blk, 0, &err);
if (tmp && !buffer_uptodate(tmp) &&
!buffer_locked(tmp))
bha[num++] = tmp;
else
brelse (tmp);
}
if (num) {
ll_rw_block (READA, num, bha);
for (i = 0; i < num; i++)
brelse (bha[i]);
}
}
revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
if (filp->f_version != inode->i_version) {
for (i = 0; i < sb->s_blocksize && i < offset; ) {
de = (struct ext3_dir_entry_2 *)
(bh->b_data + i);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (le16_to_cpu(de->rec_len) <
EXT3_DIR_REC_LEN(1))
break;
i += le16_to_cpu(de->rec_len);
}
offset = i;
filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
| offset;
filp->f_version = inode->i_version;
}
while (!error && filp->f_pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext3_dir_entry_2 *) (bh->b_data + offset);
if (!ext3_check_dir_entry ("ext3_readdir", inode, de,
bh, offset)) {
/* On error, skip the f_pos to the
next block. */
filp->f_pos = (filp->f_pos |
(sb->s_blocksize - 1)) + 1;
brelse (bh);
return stored;
}
offset += le16_to_cpu(de->rec_len);
if (le32_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
* currently swapped out. So, use a
* version stamp to detect whether or
* not the directory has been modified
* during the copy operation.
*/
unsigned long version = filp->f_version;
unsigned char d_type = DT_UNKNOWN;
if (EXT3_HAS_INCOMPAT_FEATURE(sb,
EXT3_FEATURE_INCOMPAT_FILETYPE)
&& de->file_type < EXT3_FT_MAX)
d_type =
ext3_filetype_table[de->file_type];
error = filldir(dirent, de->name,
de->name_len,
filp->f_pos,
le32_to_cpu(de->inode),
d_type);
if (error)
break;
if (version != filp->f_version)
goto revalidate;
stored ++;
}
filp->f_pos += le16_to_cpu(de->rec_len);
}
offset = 0;
brelse (bh);
}
UPDATE_ATIME(inode);
return 0;
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
struct inode *ext3_new_inode(handle_t *handle, struct inode * dir,
const struct qstr *qstr, umode_t mode)
{
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
unsigned long ino = 0;
struct inode * inode;
struct ext3_group_desc * gdp = NULL;
struct ext3_super_block * es;
struct ext3_inode_info *ei;
struct ext3_sb_info *sbi;
int err = 0;
struct inode *ret;
int i;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
trace_ext3_request_inode(dir, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT3_I(inode);
sbi = EXT3_SB(sb);
es = sbi->s_es;
if (S_ISDIR(mode))
group = find_group_orlov(sb, dir);
else
group = find_group_other(sb, dir);
err = -ENOSPC;
if (group == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
gdp = ext3_get_group_desc(sb, group, &bh2);
if (!gdp)
goto fail;
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext3_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
if (ino < EXT3_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext3_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT3_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
}
/*
* This case is possible in concurrent environment. It is very
* rare. We cannot repeat the find_group_xxx() call because
* that will simply return the same blockgroup, because the
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
if (++group == sbi->s_groups_count)
group = 0;
}
err = -ENOSPC;
goto out;
got:
ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group, ino);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
le16_add_cpu(&gdp->bg_free_inodes_count, -1);
if (S_ISDIR(mode)) {
le16_add_cpu(&gdp->bg_used_dirs_count, 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
} else
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags =
ext3_mask_flags(mode, EXT3_I(dir)->i_flags & EXT3_FL_INHERITED);
#ifdef EXT3_FRAGMENTS
ei->i_faddr = 0;
ei->i_frag_no = 0;
ei->i_frag_size = 0;
#endif
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
if (insert_inode_locked(inode) < 0) {
/*
* Likely a bitmap corruption causing inode to be allocated
* twice.
*/
err = -EIO;
goto fail;
}
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state_flags = 0;
ext3_set_inode_state(inode, EXT3_STATE_NEW);
/* See comment in ext3_iget for explanation */
if (ino >= EXT3_FIRST_INO(sb) + 1 &&
EXT3_INODE_SIZE(sb) > EXT3_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize =
sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE;
} else {
ei->i_extra_isize = 0;
}
ret = inode;
dquot_initialize(inode);
err = dquot_alloc_inode(inode);
if (err)
goto fail_drop;
err = ext3_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext3_init_security(handle, inode, dir, qstr);
if (err)
goto fail_free_drop;
err = ext3_mark_inode_dirty(handle, inode);
if (err) {
ext3_std_error(sb, err);
goto fail_free_drop;
}
ext3_debug("allocating inode %lu\n", inode->i_ino);
trace_ext3_allocate_inode(inode, dir, mode);
goto really_out;
fail:
ext3_std_error(sb, err);
out:
iput(inode);
ret = ERR_PTR(err);
really_out:
brelse(bitmap_bh);
return ret;
fail_free_drop:
dquot_free_inode(inode);
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
