/*
* 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));
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);
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_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) {
err = -EINVAL;
goto fail_drop;
}
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 (vfs_dq_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:
vfs_dq_free_inode(inode);
fail_drop:
vfs_dq_drop(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
nid_t ino;
struct inode *inode;
bool nid_free = false;
int err;
inode = new_inode(dir->i_sb);
if (!inode)
return ERR_PTR(-ENOMEM);
f2fs_lock_op(sbi);
if (!alloc_nid(sbi, &ino)) {
f2fs_unlock_op(sbi);
err = -ENOSPC;
goto fail;
}
f2fs_unlock_op(sbi);
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = sbi->s_next_generation++;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
nid_free = true;
goto fail;
}
/* If the directory encrypted, then we should encrypt the inode. */
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
f2fs_set_encrypted_inode(inode);
if (f2fs_may_inline_data(inode))
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
if (f2fs_may_inline_dentry(inode))
set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
f2fs_init_extent_tree(inode, NULL);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
trace_f2fs_new_inode(inode, 0);
mark_inode_dirty(inode);
return inode;
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
if (nid_free)
set_inode_flag(F2FS_I(inode), FI_FREE_NID);
iput(inode);
return ERR_PTR(err);
}
/*
* NAME: ialloc()
*
* FUNCTION: Allocate a new inode
*
*/
struct inode *ialloc(struct inode *parent, umode_t mode)
{
struct super_block *sb = parent->i_sb;
struct inode *inode;
struct jfs_inode_info *jfs_inode;
int rc;
inode = new_inode(sb);
if (!inode) {
jfs_warn("ialloc: new_inode returned NULL!");
rc = -ENOMEM;
goto fail;
}
jfs_inode = JFS_IP(inode);
rc = diAlloc(parent, S_ISDIR(mode), inode);
if (rc) {
jfs_warn("ialloc: diAlloc returned %d!", rc);
if (rc == -EIO)
make_bad_inode(inode);
goto fail_put;
}
if (insert_inode_locked(inode) < 0) {
rc = -EINVAL;
goto fail_unlock;
}
inode->i_uid = current_fsuid();
if (parent->i_mode & S_ISGID) {
inode->i_gid = parent->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current_fsgid();
/*
* New inodes need to save sane values on disk when
* uid & gid mount options are used
*/
jfs_inode->saved_uid = inode->i_uid;
jfs_inode->saved_gid = inode->i_gid;
/*
* Allocate inode to quota.
*/
if (vfs_dq_alloc_inode(inode)) {
rc = -EDQUOT;
goto fail_drop;
}
inode->i_mode = mode;
/* inherit flags from parent */
jfs_inode->mode2 = JFS_IP(parent)->mode2 & JFS_FL_INHERIT;
if (S_ISDIR(mode)) {
jfs_inode->mode2 |= IDIRECTORY;
jfs_inode->mode2 &= ~JFS_DIRSYNC_FL;
}
else {
jfs_inode->mode2 |= INLINEEA | ISPARSE;
if (S_ISLNK(mode))
jfs_inode->mode2 &= ~(JFS_IMMUTABLE_FL|JFS_APPEND_FL);
}
jfs_inode->mode2 |= mode;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
jfs_inode->otime = inode->i_ctime.tv_sec;
inode->i_generation = JFS_SBI(sb)->gengen++;
jfs_inode->cflag = 0;
/* Zero remaining fields */
memset(&jfs_inode->acl, 0, sizeof(dxd_t));
memset(&jfs_inode->ea, 0, sizeof(dxd_t));
jfs_inode->next_index = 0;
jfs_inode->acltype = 0;
jfs_inode->btorder = 0;
jfs_inode->btindex = 0;
jfs_inode->bxflag = 0;
jfs_inode->blid = 0;
jfs_inode->atlhead = 0;
jfs_inode->atltail = 0;
jfs_inode->xtlid = 0;
jfs_set_inode_flags(inode);
jfs_info("ialloc returns inode = 0x%p\n", inode);
return inode;
fail_drop:
vfs_dq_drop(inode);
inode->i_flags |= S_NOQUOTA;
fail_unlock:
inode->i_nlink = 0;
unlock_new_inode(inode);
fail_put:
iput(inode);
fail:
return ERR_PTR(rc);
}
/*
* Allocate a new inode with the passed id and ops.
*/
static struct inode *
zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
const struct file_operations *fops, const struct inode_operations *ops)
{
struct timespec now = current_fs_time(zsb->z_sb);
struct inode *ip;
znode_t *zp;
ip = new_inode(zsb->z_sb);
if (ip == NULL)
return (NULL);
zp = ITOZ(ip);
ASSERT3P(zp->z_dirlocks, ==, NULL);
ASSERT3P(zp->z_acl_cached, ==, NULL);
ASSERT3P(zp->z_xattr_cached, ==, NULL);
zp->z_id = id;
zp->z_unlinked = 0;
zp->z_atime_dirty = 0;
zp->z_zn_prefetch = 0;
zp->z_moved = 0;
zp->z_sa_hdl = NULL;
zp->z_blksz = 0;
zp->z_seq = 0;
zp->z_mapcnt = 0;
zp->z_gen = 0;
zp->z_size = 0;
zp->z_atime[0] = 0;
zp->z_atime[1] = 0;
zp->z_links = 0;
zp->z_pflags = 0;
zp->z_uid = 0;
zp->z_gid = 0;
zp->z_mode = 0;
zp->z_sync_cnt = 0;
zp->z_is_zvol = B_FALSE;
zp->z_is_mapped = B_FALSE;
zp->z_is_ctldir = B_TRUE;
zp->z_is_sa = B_FALSE;
ip->i_ino = id;
ip->i_mode = (S_IFDIR | S_IRUGO | S_IXUGO);
ip->i_uid = 0;
ip->i_gid = 0;
ip->i_blkbits = SPA_MINBLOCKSHIFT;
ip->i_atime = now;
ip->i_mtime = now;
ip->i_ctime = now;
ip->i_fop = fops;
ip->i_op = ops;
if (insert_inode_locked(ip)) {
unlock_new_inode(ip);
iput(ip);
return (NULL);
}
mutex_enter(&zsb->z_znodes_lock);
list_insert_tail(&zsb->z_all_znodes, zp);
zsb->z_nr_znodes++;
membar_producer();
mutex_exit(&zsb->z_znodes_lock);
unlock_new_inode(ip);
return (ip);
}
static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
nid_t ino;
struct inode *inode;
bool nid_free = false;
int err;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
f2fs_lock_op(sbi);
if (!alloc_nid(sbi, &ino)) {
f2fs_unlock_op(sbi);
err = -ENOSPC;
goto fail;
}
f2fs_unlock_op(sbi);
inode->i_uid = current_fsuid();
if (IS_ANDROID_EMU(sbi, F2FS_I(dir), F2FS_I(dir))) {
f2fs_android_emu(sbi, inode, &inode->i_uid,
&inode->i_gid, &mode);
} else {
inode->i_uid = current_fsuid();
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_ino = ino;
inode->i_mode = mode;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = sbi->s_next_generation++;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
nid_free = true;
goto out;
}
trace_f2fs_new_inode(inode, 0);
mark_inode_dirty(inode);
return inode;
out:
clear_nlink(inode);
unlock_new_inode(inode);
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
iput(inode);
if (nid_free)
alloc_nid_failed(sbi, ino);
return ERR_PTR(err);
}
