static int nilfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
if (err)
return err;
err = -ENOTEMPTY;
if (nilfs_empty_dir(inode)) {
err = nilfs_do_unlink(dir, dentry);
if (!err) {
inode->i_size = 0;
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
drop_nlink(dir);
nilfs_mark_inode_dirty(dir);
}
}
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
}
static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
struct inode *inode;
struct nilfs_transaction_info ti;
int err;
if (dir->i_nlink >= NILFS_LINK_MAX)
return -EMLINK;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inc_nlink(dir);
inode = nilfs_new_inode(dir, S_IFDIR | mode);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_dir;
inode->i_op = &nilfs_dir_inode_operations;
inode->i_fop = &nilfs_dir_operations;
inode->i_mapping->a_ops = &nilfs_aops;
inc_nlink(inode);
err = nilfs_make_empty(inode, dir);
if (err)
goto out_fail;
err = nilfs_add_link(dentry, inode);
if (err)
goto out_fail;
nilfs_mark_inode_dirty(inode);
d_instantiate(dentry, inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
out_fail:
drop_nlink(inode);
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
iput(inode);
out_dir:
drop_nlink(dir);
nilfs_mark_inode_dirty(dir);
goto out;
}
/*
* By the time this is called, we already have created
* the directory cache entry for the new file, but it
* is so far negative - it has no inode.
*
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
static int nilfs_create(struct inode *dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
struct inode *inode;
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inode = nilfs_new_inode(dir, mode);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &nilfs_file_inode_operations;
inode->i_fop = &nilfs_file_operations;
inode->i_mapping->a_ops = &nilfs_aops;
nilfs_mark_inode_dirty(inode);
err = nilfs_add_nondir(dentry, inode);
}
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
}
static int
nilfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
{
struct inode *inode;
struct nilfs_transaction_info ti;
int err;
if (!new_valid_dev(rdev))
return -EINVAL;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inode = nilfs_new_inode(dir, mode);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
nilfs_mark_inode_dirty(inode);
err = nilfs_add_nondir(dentry, inode);
}
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
}
void nilfs_evict_inode(struct inode *inode)
{
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
int ret;
if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
nilfs_clear_inode(inode);
return;
}
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
truncate_inode_pages_final(&inode->i_data);
/* TODO: some of the following operations may fail. */
nilfs_truncate_bmap(ii, 0);
nilfs_mark_inode_dirty(inode);
clear_inode(inode);
ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
if (!ret)
atomic64_dec(&ii->i_root->inodes_count);
nilfs_clear_inode(inode);
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But delete_inode has no return value. */
}
void nilfs_evict_inode(struct inode *inode)
{
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
int ret;
if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
end_writeback(inode);
nilfs_clear_inode(inode);
return;
}
nilfs_transaction_begin(sb, &ti, 0);
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
nilfs_truncate_bmap(ii, 0);
nilfs_mark_inode_dirty(inode);
end_writeback(inode);
ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
if (!ret)
atomic_dec(&ii->i_root->inodes_count);
nilfs_clear_inode(inode);
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_transaction_commit(sb);
}
int nilfs_get_block(struct inode *inode, sector_t blkoff,
struct buffer_head *bh_result, int create)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
__u64 blknum = 0;
int err = 0, ret;
unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;
down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
if (ret >= 0) {
map_bh(bh_result, inode->i_sb, blknum);
if (ret > 0)
bh_result->b_size = (ret << inode->i_blkbits);
goto out;
}
if (ret == -ENOENT && create) {
struct nilfs_transaction_info ti;
bh_result->b_blocknr = 0;
err = nilfs_transaction_begin(inode->i_sb, &ti, 1);
if (unlikely(err))
goto out;
err = nilfs_bmap_insert(ii->i_bmap, (unsigned long)blkoff,
(unsigned long)bh_result);
if (unlikely(err != 0)) {
if (err == -EEXIST) {
printk(KERN_WARNING
"nilfs_get_block: a race condition "
"while inserting a data block. "
"(inode number=%lu, file block "
"offset=%llu)\n",
inode->i_ino,
(unsigned long long)blkoff);
err = 0;
}
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_mark_inode_dirty(inode);
nilfs_transaction_commit(inode->i_sb);
set_buffer_new(bh_result);
set_buffer_delay(bh_result);
map_bh(bh_result, inode->i_sb, 0);
} else if (ret == -ENOENT) {
;
} else {
err = ret;
}
out:
return err;
}
static int nilfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
if (err)
return err;
err = nilfs_do_unlink(dir, dentry);
if (!err) {
nilfs_mark_inode_dirty(dir);
nilfs_mark_inode_dirty(dentry->d_inode);
err = nilfs_transaction_commit(dir->i_sb);
} else
nilfs_transaction_abort(dir->i_sb);
return err;
}
/**
* nilfs_dirty_inode - reflect changes on given inode to an inode block.
* @inode: inode of the file to be registered.
*
* nilfs_dirty_inode() loads a inode block containing the specified
* @inode and copies data from a nilfs_inode to a corresponding inode
* entry in the inode block. This operation is excluded from the segment
* construction. This function can be called both as a single operation
* and as a part of indivisible file operations.
*/
void nilfs_dirty_inode(struct inode *inode)
{
struct nilfs_transaction_info ti;
if (is_bad_inode(inode)) {
nilfs_warning(inode->i_sb, __func__,
"tried to mark bad_inode dirty. ignored.\n");
dump_stack();
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
nilfs_mark_inode_dirty(inode);
nilfs_transaction_commit(inode->i_sb); /* never fails */
}
static int nilfs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct nilfs_transaction_info ti;
struct super_block *sb = dir->i_sb;
unsigned int l = strlen(symname) + 1;
struct inode *inode;
int err;
if (l > sb->s_blocksize)
return -ENAMETOOLONG;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inode = nilfs_new_inode(dir, S_IFLNK | S_IRWXUGO);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out;
/* slow symlink */
inode->i_op = &nilfs_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &nilfs_aops;
err = page_symlink(inode, symname, l);
if (err)
goto out_fail;
/* mark_inode_dirty(inode); */
/* page_symlink() do this */
err = nilfs_add_nondir(dentry, inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
out_fail:
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
unlock_new_inode(inode);
iput(inode);
goto out;
}
void nilfs_dirty_inode(struct inode *inode, int flags)
{
struct nilfs_transaction_info ti;
struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
if (is_bad_inode(inode)) {
nilfs_warning(inode->i_sb, __func__,
"tried to mark bad_inode dirty. ignored.\n");
dump_stack();
return;
}
if (mdi) {
nilfs_mdt_mark_dirty(inode);
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
nilfs_mark_inode_dirty(inode);
nilfs_transaction_commit(inode->i_sb);
}
/**
* nilfs_get_block() - get a file block on the filesystem (callback function)
* @inode - inode struct of the target file
* @blkoff - file block number
* @bh_result - buffer head to be mapped on
* @create - indicate whether allocating the block or not when it has not
* been allocated yet.
*
* This function does not issue actual read request of the specified data
* block. It is done by VFS.
*/
int nilfs_get_block(struct inode *inode, sector_t blkoff,
struct buffer_head *bh_result, int create)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
__u64 blknum = 0;
int err = 0, ret;
unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;
down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
if (ret >= 0) { /* found */
map_bh(bh_result, inode->i_sb, blknum);
if (ret > 0)
bh_result->b_size = (ret << inode->i_blkbits);
goto out;
}
/* data block was not found */
if (ret == -ENOENT && create) {
struct nilfs_transaction_info ti;
bh_result->b_blocknr = 0;
err = nilfs_transaction_begin(inode->i_sb, &ti, 1);
if (unlikely(err))
goto out;
err = nilfs_bmap_insert(ii->i_bmap, (unsigned long)blkoff,
(unsigned long)bh_result);
if (unlikely(err != 0)) {
if (err == -EEXIST) {
/*
* The get_block() function could be called
* from multiple callers for an inode.
* However, the page having this block must
* be locked in this case.
*/
printk(KERN_WARNING
"nilfs_get_block: a race condition "
"while inserting a data block. "
"(inode number=%lu, file block "
"offset=%llu)\n",
inode->i_ino,
(unsigned long long)blkoff);
err = 0;
}
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_mark_inode_dirty(inode);
nilfs_transaction_commit(inode->i_sb); /* never fails */
/* Error handling should be detailed */
set_buffer_new(bh_result);
set_buffer_delay(bh_result);
map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed
to proper value */
} else if (ret == -ENOENT) {
/* not found is not error (e.g. hole); must return without
the mapped state flag. */
;
} else {
err = ret;
}
out:
return err;
}
struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return ilookup5(sb, ino, nilfs_iget_test, &args);
}
struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
}
struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct inode *inode;
int err;
inode = nilfs_iget_locked(sb, root, ino);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = __nilfs_read_inode(sb, root, ino, inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
__u64 cno)
{
struct nilfs_iget_args args = {
.ino = ino, .root = NULL, .cno = cno, .for_gc = 1
};
struct inode *inode;
int err;
inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = nilfs_init_gcinode(inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
void nilfs_write_inode_common(struct inode *inode,
struct nilfs_inode *raw_inode, int has_bmap)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
raw_inode->i_uid = cpu_to_le32(inode->i_uid);
raw_inode->i_gid = cpu_to_le32(inode->i_gid);
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le64(inode->i_size);
raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);
raw_inode->i_flags = cpu_to_le32(ii->i_flags);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
/* zero-fill unused portion in the case of super root block */
raw_inode->i_xattr = 0;
raw_inode->i_pad = 0;
memset((void *)raw_inode + sizeof(*raw_inode), 0,
nilfs->ns_inode_size - sizeof(*raw_inode));
}
if (has_bmap)
nilfs_bmap_write(ii->i_bmap, raw_inode);
else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_device_code =
cpu_to_le64(huge_encode_dev(inode->i_rdev));
/* When extending inode, nilfs->ns_inode_size should be checked
for substitutions of appended fields */
}
void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
{
ino_t ino = inode->i_ino;
struct nilfs_inode_info *ii = NILFS_I(inode);
struct inode *ifile = ii->i_root->ifile;
struct nilfs_inode *raw_inode;
raw_inode = nilfs_ifile_map_inode(ifile, ino, ibh);
if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
nilfs_write_inode_common(inode, raw_inode, 0);
/* XXX: call with has_bmap = 0 is a workaround to avoid
deadlock of bmap. This delays update of i_bmap to just
before writing */
nilfs_ifile_unmap_inode(ifile, ino, ibh);
}
#define NILFS_MAX_TRUNCATE_BLOCKS 16384 /* 64MB for 4KB block */
static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
unsigned long from)
{
unsigned long b;
int ret;
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
repeat:
ret = nilfs_bmap_last_key(ii->i_bmap, &b);
if (ret == -ENOENT)
return;
else if (ret < 0)
goto failed;
if (b < from)
return;
b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
ret = nilfs_bmap_truncate(ii->i_bmap, b);
nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
if (!ret || (ret == -ENOMEM &&
nilfs_bmap_truncate(ii->i_bmap, b) == 0))
goto repeat;
failed:
nilfs_warning(ii->vfs_inode.i_sb, __func__,
"failed to truncate bmap (ino=%lu, err=%d)",
ii->vfs_inode.i_ino, ret);
}
void nilfs_truncate(struct inode *inode)
{
unsigned long blkoff;
unsigned int blocksize;
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;
blocksize = sb->s_blocksize;
blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);
nilfs_truncate_bmap(ii, blkoff);
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_mark_inode_dirty(inode);
nilfs_set_file_dirty(inode, 0);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But truncate has no return value. */
}
static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *dir_page = NULL;
struct nilfs_dir_entry *dir_de = NULL;
struct page *old_page;
struct nilfs_dir_entry *old_de;
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(old_dir->i_sb, &ti, 1);
if (unlikely(err))
return err;
err = -ENOENT;
old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_de)
goto out;
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
dir_de = nilfs_dotdot(old_inode, &dir_page);
if (!dir_de)
goto out_old;
}
if (new_inode) {
struct page *new_page;
struct nilfs_dir_entry *new_de;
err = -ENOTEMPTY;
if (dir_de && !nilfs_empty_dir(new_inode))
goto out_dir;
err = -ENOENT;
new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
nilfs_set_link(new_dir, new_de, new_page, old_inode);
nilfs_mark_inode_dirty(new_dir);
new_inode->i_ctime = CURRENT_TIME;
if (dir_de)
drop_nlink(new_inode);
drop_nlink(new_inode);
nilfs_mark_inode_dirty(new_inode);
} else {
err = nilfs_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
if (dir_de) {
inc_nlink(new_dir);
nilfs_mark_inode_dirty(new_dir);
}
}
/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
old_inode->i_ctime = CURRENT_TIME;
nilfs_delete_entry(old_de, old_page);
if (dir_de) {
nilfs_set_link(old_inode, dir_de, dir_page, new_dir);
drop_nlink(old_dir);
}
nilfs_mark_inode_dirty(old_dir);
nilfs_mark_inode_dirty(old_inode);
err = nilfs_transaction_commit(old_dir->i_sb);
return err;
out_dir:
if (dir_de) {
kunmap(dir_page);
page_cache_release(dir_page);
}
out_old:
kunmap(old_page);
page_cache_release(old_page);
out:
nilfs_transaction_abort(old_dir->i_sb);
return err;
}