void jfs_delete_inode(struct inode *inode)
{
jfs_info("In jfs_delete_inode, inode = 0x%p", inode);
if (!is_bad_inode(inode))
dquot_initialize(inode);
if (!is_bad_inode(inode) &&
(JFS_IP(inode)->fileset == FILESYSTEM_I)) {
truncate_inode_pages(&inode->i_data, 0);
if (test_cflag(COMMIT_Freewmap, inode))
jfs_free_zero_link(inode);
diFree(inode);
/*
* Free the inode from the quota allocation.
*/
dquot_initialize(inode);
dquot_free_inode(inode);
dquot_drop(inode);
}
clear_inode(inode);
}
void jfs_evict_inode(struct inode *inode)
{
jfs_info("In jfs_evict_inode, inode = 0x%p", inode);
if (!inode->i_nlink && !is_bad_inode(inode)) {
dquot_initialize(inode);
if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
truncate_inode_pages(&inode->i_data, 0);
if (test_cflag(COMMIT_Freewmap, inode))
jfs_free_zero_link(inode);
diFree(inode);
/*
* Free the inode from the quota allocation.
*/
dquot_initialize(inode);
dquot_free_inode(inode);
}
} else {
truncate_inode_pages(&inode->i_data, 0);
}
end_writeback(inode);
dquot_drop(inode);
}
/* quota utility function, call if you've had to abort after calling
** new_inode_init, and have not called reiserfs_new_inode yet.
** This should only be called on inodes that do not have stat data
** inserted into the tree yet.
*/
static int drop_new_inode(struct inode *inode)
{
dquot_drop(inode);
make_bad_inode(inode);
inode->i_flags |= S_NOQUOTA;
iput(inode);
return 0;
}
static void ext2_clear_inode(struct inode *inode)
{
struct ext2_block_alloc_info *rsv = EXT2_I(inode)->i_block_alloc_info;
dquot_drop(inode);
ext2_discard_reservation(inode);
EXT2_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext2_evict_inode(struct inode * inode)
{
struct ext2_block_alloc_info *rsv;
int want_delete = 0;
if (!inode->i_nlink && !is_bad_inode(inode)) {
want_delete = 1;
dquot_initialize(inode);
} else {
dquot_drop(inode);
}
truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
sb_start_intwrite(inode->i_sb);
/* set dtime */
EXT2_I(inode)->i_dtime = get_seconds();
mark_inode_dirty(inode);
__ext2_write_inode(inode, inode_needs_sync(inode));
/* truncate to 0 */
inode->i_size = 0;
if (inode->i_blocks)
ext2_truncate_blocks(inode, 0);
ext2_xattr_delete_inode(inode);
}
invalidate_inode_buffers(inode);
clear_inode(inode);
ext2_discard_reservation(inode);
rsv = EXT2_I(inode)->i_block_alloc_info;
EXT2_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
if (want_delete) {
ext2_free_inode(inode);
sb_end_intwrite(inode->i_sb);
}
}
/*
* 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, 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;
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)) {
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);
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) {
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_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;
inode->i_nlink = 0;
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
static void ocfs2_clear_inode(struct inode *inode)
{
int status;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
clear_inode(inode);
trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
inode->i_nlink);
mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL,
"Inode=%lu\n", inode->i_ino);
dquot_drop(inode);
/* To preven remote deletes we hold open lock before, now it
* is time to unlock PR and EX open locks. */
ocfs2_open_unlock(inode);
/* Do these before all the other work so that we don't bounce
* the downconvert thread while waiting to destroy the locks. */
ocfs2_mark_lockres_freeing(&oi->ip_rw_lockres);
ocfs2_mark_lockres_freeing(&oi->ip_inode_lockres);
ocfs2_mark_lockres_freeing(&oi->ip_open_lockres);
ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
&oi->ip_la_data_resv);
ocfs2_resv_init_once(&oi->ip_la_data_resv);
/* We very well may get a clear_inode before all an inodes
* metadata has hit disk. Of course, we can't drop any cluster
* locks until the journal has finished with it. The only
* exception here are successfully wiped inodes - their
* metadata can now be considered to be part of the system
* inodes from which it came. */
if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED))
ocfs2_checkpoint_inode(inode);
mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
"Clear inode of %llu, inode has io markers\n",
(unsigned long long)oi->ip_blkno);
ocfs2_extent_map_trunc(inode, 0);
status = ocfs2_drop_inode_locks(inode);
if (status < 0)
mlog_errno(status);
ocfs2_lock_res_free(&oi->ip_rw_lockres);
ocfs2_lock_res_free(&oi->ip_inode_lockres);
ocfs2_lock_res_free(&oi->ip_open_lockres);
ocfs2_metadata_cache_exit(INODE_CACHE(inode));
mlog_bug_on_msg(INODE_CACHE(inode)->ci_num_cached,
"Clear inode of %llu, inode has %u cache items\n",
(unsigned long long)oi->ip_blkno,
INODE_CACHE(inode)->ci_num_cached);
mlog_bug_on_msg(!(INODE_CACHE(inode)->ci_flags & OCFS2_CACHE_FL_INLINE),
"Clear inode of %llu, inode has a bad flag\n",
(unsigned long long)oi->ip_blkno);
mlog_bug_on_msg(spin_is_locked(&oi->ip_lock),
"Clear inode of %llu, inode is locked\n",
(unsigned long long)oi->ip_blkno);
mlog_bug_on_msg(!mutex_trylock(&oi->ip_io_mutex),
"Clear inode of %llu, io_mutex is locked\n",
(unsigned long long)oi->ip_blkno);
mutex_unlock(&oi->ip_io_mutex);
/*
* down_trylock() returns 0, down_write_trylock() returns 1
* kernel 1, world 0
*/
mlog_bug_on_msg(!down_write_trylock(&oi->ip_alloc_sem),
"Clear inode of %llu, alloc_sem is locked\n",
(unsigned long long)oi->ip_blkno);
up_write(&oi->ip_alloc_sem);
mlog_bug_on_msg(oi->ip_open_count,
"Clear inode of %llu has open count %d\n",
(unsigned long long)oi->ip_blkno, oi->ip_open_count);
/* Clear all other flags. */
oi->ip_flags = 0;
oi->ip_dir_start_lookup = 0;
oi->ip_blkno = 0ULL;
/*
* ip_jinode is used to track txns against this inode. We ensure that
* the journal is flushed before journal shutdown. Thus it is safe to
* have inodes get cleaned up after journal shutdown.
*/
jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
&oi->ip_jinode);
}
/*
* 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_init_owner(inode, parent, mode);
/*
* 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.
*/
dquot_initialize(inode);
rc = dquot_alloc_inode(inode);
if (rc)
goto fail_drop;
/* 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 |= inode->i_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:
dquot_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);
}
/*
* Called at inode eviction from icache
*/
void ext3_evict_inode (struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
struct ext3_block_alloc_info *rsv;
handle_t *handle;
int want_delete = 0;
trace_ext3_evict_inode(inode);
if (!inode->i_nlink && !is_bad_inode(inode)) {
dquot_initialize(inode);
want_delete = 1;
}
/*
* When journalling data dirty buffers are tracked only in the journal.
* So although mm thinks everything is clean and ready for reaping the
* inode might still have some pages to write in the running
* transaction or waiting to be checkpointed. Thus calling
* journal_invalidatepage() (via truncate_inode_pages()) to discard
* these buffers can cause data loss. Also even if we did not discard
* these buffers, we would have no way to find them after the inode
* is reaped and thus user could see stale data if he tries to read
* them before the transaction is checkpointed. So be careful and
* force everything to disk here... We use ei->i_datasync_tid to
* store the newest transaction containing inode's data.
*
* Note that directories do not have this problem because they don't
* use page cache.
*
* The s_journal check handles the case when ext3_get_journal() fails
* and puts the journal inode.
*/
if (inode->i_nlink && ext3_should_journal_data(inode) &&
EXT3_SB(inode->i_sb)->s_journal &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
inode->i_ino != EXT3_JOURNAL_INO) {
tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
log_start_commit(journal, commit_tid);
log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
ext3_discard_reservation(inode);
rsv = ei->i_block_alloc_info;
ei->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
if (!want_delete)
goto no_delete;
handle = start_transaction(inode);
if (IS_ERR(handle)) {
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext3_orphan_del(NULL, inode);
goto no_delete;
}
if (IS_SYNC(inode))
handle->h_sync = 1;
inode->i_size = 0;
if (inode->i_blocks)
ext3_truncate(inode);
/*
* Kill off the orphan record created when the inode lost the last
* link. Note that ext3_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - ext3_truncate() could
* have removed the record.
*/
ext3_orphan_del(handle, inode);
ei->i_dtime = get_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext3_mark_inode_dirty(handle, inode)) {
/* If that failed, just dquot_drop() and be done with that */
dquot_drop(inode);
clear_inode(inode);
} else {
ext3_xattr_delete_inode(handle, inode);
dquot_free_inode(inode);
dquot_drop(inode);
clear_inode(inode);
ext3_free_inode(handle, inode);
}
ext3_journal_stop(handle);
return;
no_delete:
clear_inode(inode);
dquot_drop(inode);
}
/*
* 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 ufs_free_inode (struct inode * inode)
{
struct super_block * sb;
struct ufs_sb_private_info * uspi;
struct ufs_super_block_first * usb1;
struct ufs_cg_private_info * ucpi;
struct ufs_cylinder_group * ucg;
int is_directory;
unsigned ino, cg, bit;
UFSD("ENTER, ino %lu\n", inode->i_ino);
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
usb1 = ubh_get_usb_first(uspi);
ino = inode->i_ino;
lock_super (sb);
if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
unlock_super (sb);
return;
}
cg = ufs_inotocg (ino);
bit = ufs_inotocgoff (ino);
ucpi = ufs_load_cylinder (sb, cg);
if (!ucpi) {
unlock_super (sb);
return;
}
ucg = ubh_get_ucg(UCPI_UBH(ucpi));
if (!ufs_cg_chkmagic(sb, ucg))
ufs_panic (sb, "ufs_free_fragments", "internal error, bad cg magic number");
ucg->cg_time = cpu_to_fs32(sb, get_seconds());
is_directory = S_ISDIR(inode->i_mode);
dquot_free_inode(inode);
dquot_drop(inode);
clear_inode (inode);
if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_iusedoff, bit))
ufs_error(sb, "ufs_free_inode", "bit already cleared for inode %u", ino);
else {
ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_iusedoff, bit);
if (ino < ucpi->c_irotor)
ucpi->c_irotor = ino;
fs32_add(sb, &ucg->cg_cs.cs_nifree, 1);
uspi->cs_total.cs_nifree++;
fs32_add(sb, &UFS_SB(sb)->fs_cs(cg).cs_nifree, 1);
if (is_directory) {
fs32_sub(sb, &ucg->cg_cs.cs_ndir, 1);
uspi->cs_total.cs_ndir--;
fs32_sub(sb, &UFS_SB(sb)->fs_cs(cg).cs_ndir, 1);
}
}
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS) {
ubh_ll_rw_block(SWRITE, UCPI_UBH(ucpi));
ubh_wait_on_buffer (UCPI_UBH(ucpi));
}
sb->s_dirt = 1;
unlock_super (sb);
UFSD("EXIT\n");
}
/*
* 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 * ufs_new_inode(struct inode * dir, int mode)
{
struct super_block * sb;
struct ufs_sb_info * sbi;
struct ufs_sb_private_info * uspi;
struct ufs_super_block_first * usb1;
struct ufs_cg_private_info * ucpi;
struct ufs_cylinder_group * ucg;
struct inode * inode;
unsigned cg, bit, i, j, start;
struct ufs_inode_info *ufsi;
int err = -ENOSPC;
UFSD("ENTER\n");
/* 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);
ufsi = UFS_I(inode);
sbi = UFS_SB(sb);
uspi = sbi->s_uspi;
usb1 = ubh_get_usb_first(uspi);
lock_super (sb);
/*
* Try to place the inode in its parent directory
*/
i = ufs_inotocg(dir->i_ino);
if (sbi->fs_cs(i).cs_nifree) {
cg = i;
goto cg_found;
}
/*
* Use a quadratic hash to find a group with a free inode
*/
for ( j = 1; j < uspi->s_ncg; j <<= 1 ) {
i += j;
if (i >= uspi->s_ncg)
i -= uspi->s_ncg;
if (sbi->fs_cs(i).cs_nifree) {
cg = i;
goto cg_found;
}
}
/*
* That failed: try linear search for a free inode
*/
i = ufs_inotocg(dir->i_ino) + 1;
for (j = 2; j < uspi->s_ncg; j++) {
i++;
if (i >= uspi->s_ncg)
i = 0;
if (sbi->fs_cs(i).cs_nifree) {
cg = i;
goto cg_found;
}
}
goto failed;
cg_found:
ucpi = ufs_load_cylinder (sb, cg);
if (!ucpi) {
err = -EIO;
goto failed;
}
ucg = ubh_get_ucg(UCPI_UBH(ucpi));
if (!ufs_cg_chkmagic(sb, ucg))
ufs_panic (sb, "ufs_new_inode", "internal error, bad cg magic number");
start = ucpi->c_irotor;
bit = ubh_find_next_zero_bit (UCPI_UBH(ucpi), ucpi->c_iusedoff, uspi->s_ipg, start);
if (!(bit < uspi->s_ipg)) {
bit = ubh_find_first_zero_bit (UCPI_UBH(ucpi), ucpi->c_iusedoff, start);
if (!(bit < start)) {
ufs_error (sb, "ufs_new_inode",
"cylinder group %u corrupted - error in inode bitmap\n", cg);
err = -EIO;
goto failed;
}
}
UFSD("start = %u, bit = %u, ipg = %u\n", start, bit, uspi->s_ipg);
if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_iusedoff, bit))
ubh_setbit (UCPI_UBH(ucpi), ucpi->c_iusedoff, bit);
else {
ufs_panic (sb, "ufs_new_inode", "internal error");
err = -EIO;
goto failed;
}
if (uspi->fs_magic == UFS2_MAGIC) {
u32 initediblk = fs32_to_cpu(sb, ucg->cg_u.cg_u2.cg_initediblk);
if (bit + uspi->s_inopb > initediblk &&
initediblk < fs32_to_cpu(sb, ucg->cg_u.cg_u2.cg_niblk))
ufs2_init_inodes_chunk(sb, ucpi, ucg);
}
fs32_sub(sb, &ucg->cg_cs.cs_nifree, 1);
uspi->cs_total.cs_nifree--;
fs32_sub(sb, &sbi->fs_cs(cg).cs_nifree, 1);
if (S_ISDIR(mode)) {
fs32_add(sb, &ucg->cg_cs.cs_ndir, 1);
uspi->cs_total.cs_ndir++;
fs32_add(sb, &sbi->fs_cs(cg).cs_ndir, 1);
}
ubh_mark_buffer_dirty (USPI_UBH(uspi));
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS) {
ubh_ll_rw_block(SWRITE, UCPI_UBH(ucpi));
ubh_wait_on_buffer (UCPI_UBH(ucpi));
}
sb->s_dirt = 1;
inode->i_ino = cg * uspi->s_ipg + bit;
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
inode->i_generation = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
ufsi->i_flags = UFS_I(dir)->i_flags;
ufsi->i_lastfrag = 0;
ufsi->i_shadow = 0;
ufsi->i_osync = 0;
ufsi->i_oeftflag = 0;
ufsi->i_dir_start_lookup = 0;
memset(&ufsi->i_u1, 0, sizeof(ufsi->i_u1));
insert_inode_hash(inode);
mark_inode_dirty(inode);
if (uspi->fs_magic == UFS2_MAGIC) {
struct buffer_head *bh;
struct ufs2_inode *ufs2_inode;
/*
* setup birth date, we do it here because of there is no sense
* to hold it in struct ufs_inode_info, and lose 64 bit
*/
bh = sb_bread(sb, uspi->s_sbbase + ufs_inotofsba(inode->i_ino));
if (!bh) {
ufs_warning(sb, "ufs_read_inode",
"unable to read inode %lu\n",
inode->i_ino);
err = -EIO;
goto fail_remove_inode;
}
lock_buffer(bh);
ufs2_inode = (struct ufs2_inode *)bh->b_data;
ufs2_inode += ufs_inotofsbo(inode->i_ino);
ufs2_inode->ui_birthtime = cpu_to_fs64(sb, CURRENT_TIME.tv_sec);
ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, CURRENT_TIME.tv_nsec);
mark_buffer_dirty(bh);
unlock_buffer(bh);
if (sb->s_flags & MS_SYNCHRONOUS)
sync_dirty_buffer(bh);
brelse(bh);
}
unlock_super (sb);
dquot_initialize(inode);
err = dquot_alloc_inode(inode);
if (err) {
dquot_drop(inode);
goto fail_without_unlock;
}
UFSD("allocating inode %lu\n", inode->i_ino);
UFSD("EXIT\n");
return inode;
fail_remove_inode:
unlock_super(sb);
fail_without_unlock:
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
iput(inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
failed:
unlock_super (sb);
make_bad_inode(inode);
iput (inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
}
/*
* Called at the last iput() if i_nlink is zero
*/
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
f2fs_drop_inmem_pages(inode);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
f2fs_remove_dirty_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
i_size_write(inode, 0);
retry:
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
f2fs_show_injection_info(FAULT_EVICT_INODE);
err = -EIO;
}
if (!err) {
f2fs_lock_op(sbi);
err = f2fs_remove_inode_page(inode);
f2fs_unlock_op(sbi);
if (err == -ENOENT)
err = 0;
}
/* give more chances, if ENOMEM case */
if (err == -ENOMEM) {
err = 0;
goto retry;
}
if (err)
f2fs_update_inode_page(inode);
dquot_free_inode(inode);
sb_end_intwrite(inode->i_sb);
no_delete:
dquot_drop(inode);
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)))
f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
else
f2fs_inode_synced(inode);
/* ino == 0, if f2fs_new_inode() was failed t*/
if (inode->i_ino)
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
if (inode->i_nlink) {
if (is_inode_flag_set(inode, FI_APPEND_WRITE))
f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
}
if (is_inode_flag_set(inode, FI_FREE_NID)) {
f2fs_alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(inode, FI_FREE_NID);
} else {
/*
* If xattr nid is corrupted, we can reach out error condition,
* err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
* In that case, f2fs_check_nid_range() is enough to give a clue.
*/
}
out_clear:
fscrypt_put_encryption_info(inode);
clear_inode(inode);
}
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);
nid_free = true;
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);
inode->i_generation = sbi->s_next_generation++;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
goto fail;
}
err = dquot_initialize(inode);
if (err)
goto fail_drop;
err = dquot_alloc_inode(inode);
if (err)
goto fail_drop;
/* If the directory encrypted, then we should encrypt the inode. */
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
f2fs_set_encrypted_inode(inode);
set_inode_flag(inode, FI_NEW_INODE);
if (test_opt(sbi, INLINE_XATTR))
set_inode_flag(inode, FI_INLINE_XATTR);
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
set_inode_flag(inode, FI_INLINE_DATA);
if (f2fs_may_inline_dentry(inode))
set_inode_flag(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);
return inode;
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
if (nid_free)
set_inode_flag(inode, FI_FREE_NID);
iput(inode);
return ERR_PTR(err);
fail_drop:
trace_f2fs_new_inode(inode, err);
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
if (nid_free)
set_inode_flag(inode, FI_FREE_NID);
clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
return ERR_PTR(err);
}
