/* We need to start a transaction to maintain lock ordering */
int reiserfs_xattr_set(struct inode *inode, const char *name,
const void *buffer, size_t buffer_size, int flags)
{
struct reiserfs_transaction_handle th;
int error, error2;
size_t jbegin_count = reiserfs_xattr_nblocks(inode, buffer_size);
if (!(flags & XATTR_REPLACE))
jbegin_count += reiserfs_xattr_jcreate_nblocks(inode);
reiserfs_write_lock(inode->i_sb);
error = journal_begin(&th, inode->i_sb, jbegin_count);
reiserfs_write_unlock(inode->i_sb);
if (error) {
return error;
}
error = reiserfs_xattr_set_handle(&th, inode, name,
buffer, buffer_size, flags);
reiserfs_write_lock(inode->i_sb);
error2 = journal_end(&th, inode->i_sb, jbegin_count);
reiserfs_write_unlock(inode->i_sb);
if (error == 0)
error = error2;
return error;
}
static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
int retval;
struct inode *inode = d_inode(old_dentry);
struct reiserfs_transaction_handle th;
/*
* We need blocks for transaction + update of quotas for
* the owners of the directory
*/
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 +
2 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
retval = dquot_initialize(dir);
if (retval)
return retval;
reiserfs_write_lock(dir->i_sb);
if (inode->i_nlink >= REISERFS_LINK_MAX) {
/* FIXME: sd_nlink is 32 bit for new files */
reiserfs_write_unlock(dir->i_sb);
return -EMLINK;
}
/* inc before scheduling so reiserfs_unlink knows we are here */
inc_nlink(inode);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
drop_nlink(inode);
reiserfs_write_unlock(dir->i_sb);
return retval;
}
/* create new entry */
retval =
reiserfs_add_entry(&th, dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
if (retval) {
int err;
drop_nlink(inode);
err = journal_end(&th);
reiserfs_write_unlock(dir->i_sb);
return err ? err : retval;
}
inode->i_ctime = current_time(inode);
reiserfs_update_sd(&th, inode);
ihold(inode);
d_instantiate(dentry, inode);
retval = journal_end(&th);
reiserfs_write_unlock(dir->i_sb);
return retval;
}
int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, int datasync) {
struct inode *inode = dentry->d_inode;
reiserfs_write_lock(inode->i_sb);
reiserfs_commit_for_inode(inode) ;
reiserfs_write_unlock(inode->i_sb) ;
return 0 ;
}
static int lookup_and_delete_xattr(struct inode *inode, const char *name)
{
int err = 0;
struct dentry *dentry, *xadir;
xadir = open_xa_dir(inode, XATTR_REPLACE);
if (IS_ERR(xadir))
return PTR_ERR(xadir);
mutex_lock_nested(&xadir->d_inode->i_mutex, I_MUTEX_XATTR);
dentry = lookup_one_len(name, xadir, strlen(name));
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out_dput;
}
if (dentry->d_inode) {
reiserfs_write_lock(inode->i_sb);
err = xattr_unlink(xadir->d_inode, dentry);
reiserfs_write_unlock(inode->i_sb);
update_ctime(inode);
}
dput(dentry);
out_dput:
mutex_unlock(&xadir->d_inode->i_mutex);
dput(xadir);
return err;
}
/*
** looks up the dentry of the parent directory for child.
** taken from ext2_get_parent
*/
struct dentry *reiserfs_get_parent(struct dentry *child)
{
int retval;
struct inode * inode = NULL;
struct reiserfs_dir_entry de;
INITIALIZE_PATH (path_to_entry);
struct dentry *parent;
struct inode *dir = child->d_inode ;
if (dir->i_nlink == 0) {
return ERR_PTR(-ENOENT);
}
de.de_gen_number_bit_string = NULL;
reiserfs_write_lock(dir->i_sb);
retval = reiserfs_find_entry (dir, "..", 2, &path_to_entry, &de);
pathrelse (&path_to_entry);
if (retval != NAME_FOUND) {
reiserfs_write_unlock(dir->i_sb);
return ERR_PTR(-ENOENT);
}
inode = reiserfs_iget (dir->i_sb, (struct cpu_key *)&(de.de_dir_id));
reiserfs_write_unlock(dir->i_sb);
if (!inode || IS_ERR(inode)) {
return ERR_PTR(-EACCES);
}
parent = d_alloc_anon(inode);
if (!parent) {
iput(inode);
parent = ERR_PTR(-ENOMEM);
}
return parent;
}
/*
** looks up the dentry of the parent directory for child.
** taken from ext2_get_parent
*/
struct dentry *reiserfs_get_parent(struct dentry *child)
{
int retval;
struct inode *inode = NULL;
struct reiserfs_dir_entry de;
INITIALIZE_PATH(path_to_entry);
struct inode *dir = child->d_inode;
if (dir->i_nlink == 0) {
return ERR_PTR(-ENOENT);
}
de.de_gen_number_bit_string = NULL;
reiserfs_write_lock(dir->i_sb);
retval = reiserfs_find_entry(dir, "..", 2, &path_to_entry, &de);
pathrelse(&path_to_entry);
if (retval != NAME_FOUND) {
reiserfs_write_unlock(dir->i_sb);
return ERR_PTR(-ENOENT);
}
inode = reiserfs_iget(dir->i_sb, (struct cpu_key *)&(de.de_dir_id));
reiserfs_write_unlock(dir->i_sb);
return d_obtain_alias(inode);
}
int reiserfs_unpack(struct inode *inode, struct file *filp)
{
int retval = 0;
int index;
struct page *page;
struct address_space *mapping;
unsigned long write_from;
unsigned long blocksize = inode->i_sb->s_blocksize;
if (inode->i_size == 0) {
REISERFS_I(inode)->i_flags |= i_nopack_mask;
return 0;
}
/* ioctl already done */
if (REISERFS_I(inode)->i_flags & i_nopack_mask) {
return 0;
}
/* we need to make sure nobody is changing the file size beneath
** us
*/
mutex_lock(&inode->i_mutex);
reiserfs_write_lock(inode->i_sb);
write_from = inode->i_size & (blocksize - 1);
/* if we are on a block boundary, we are already unpacked. */
if (write_from == 0) {
REISERFS_I(inode)->i_flags |= i_nopack_mask;
goto out;
}
/* we unpack by finding the page with the tail, and calling
** reiserfs_prepare_write on that page. This will force a
** reiserfs_get_block to unpack the tail for us.
*/
index = inode->i_size >> PAGE_CACHE_SHIFT;
mapping = inode->i_mapping;
page = grab_cache_page(mapping, index);
retval = -ENOMEM;
if (!page) {
goto out;
}
retval = reiserfs_prepare_write(NULL, page, write_from, write_from);
if (retval)
goto out_unlock;
/* conversion can change page contents, must flush */
flush_dcache_page(page);
retval = reiserfs_commit_write(NULL, page, write_from, write_from);
REISERFS_I(inode)->i_flags |= i_nopack_mask;
out_unlock:
unlock_page(page);
page_cache_release(page);
out:
mutex_unlock(&inode->i_mutex);
reiserfs_write_unlock(inode->i_sb);
return retval;
}
static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
int retval;
struct inode *inode = old_dentry->d_inode;
struct reiserfs_transaction_handle th;
/* We need blocks for transaction + update of quotas for the owners of the directory */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 +
2 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
reiserfs_write_lock(dir->i_sb);
if (inode->i_nlink >= REISERFS_LINK_MAX) {
//FIXME: sd_nlink is 32 bit for new files
reiserfs_write_unlock(dir->i_sb);
return -EMLINK;
}
if (inode->i_nlink == 0) {
reiserfs_write_unlock(dir->i_sb);
return -ENOENT;
}
/* inc before scheduling so reiserfs_unlink knows we are here */
inode->i_nlink++;
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
inode->i_nlink--;
reiserfs_write_unlock(dir->i_sb);
return retval;
}
/* create new entry */
retval =
reiserfs_add_entry(&th, dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
if (retval) {
int err;
inode->i_nlink--;
err = journal_end(&th, dir->i_sb, jbegin_count);
reiserfs_write_unlock(dir->i_sb);
return err ? err : retval;
}
inode->i_ctime = CURRENT_TIME_SEC;
reiserfs_update_sd(&th, inode);
atomic_inc(&inode->i_count);
d_instantiate(dentry, inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
reiserfs_write_unlock(dir->i_sb);
return retval;
}
static int reiserfs_create (struct inode * dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
int retval;
struct inode * inode;
int jbegin_count = JOURNAL_PER_BALANCE_CNT * 2 ;
struct reiserfs_transaction_handle th ;
int locked;
if (!(inode = new_inode(dir->i_sb))) {
return -ENOMEM ;
}
retval = new_inode_init(inode, dir, mode);
if (retval)
return retval;
locked = reiserfs_cache_default_acl (dir);
reiserfs_write_lock(dir->i_sb);
if (locked)
reiserfs_write_lock_xattrs (dir->i_sb);
journal_begin(&th, dir->i_sb, jbegin_count) ;
retval = reiserfs_new_inode (&th, dir, mode, 0, 0/*i_size*/, dentry, inode);
if (locked)
reiserfs_write_unlock_xattrs (dir->i_sb);
if (retval) {
goto out_failed;
}
inode->i_op = &reiserfs_file_inode_operations;
inode->i_fop = &reiserfs_file_operations;
inode->i_mapping->a_ops = &reiserfs_address_space_operations ;
retval = reiserfs_add_entry (&th, dir, dentry->d_name.name, dentry->d_name.len,
inode, 1/*visible*/);
if (retval) {
inode->i_nlink--;
reiserfs_update_sd (&th, inode);
journal_end(&th, dir->i_sb, jbegin_count) ;
iput (inode);
goto out_failed;
}
reiserfs_update_inode_transaction(inode) ;
reiserfs_update_inode_transaction(dir) ;
d_instantiate(dentry, inode);
journal_end(&th, dir->i_sb, jbegin_count) ;
out_failed:
reiserfs_write_unlock(dir->i_sb);
return retval;
}
int
reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int error, error2;
struct reiserfs_transaction_handle th;
size_t jcreate_blocks;
int size = acl ? posix_acl_xattr_size(acl->a_count) : 0;
int update_mode = 0;
umode_t mode = inode->i_mode;
/*
* Pessimism: We can't assume that anything from the xattr root up
* has been created.
*/
jcreate_blocks = reiserfs_xattr_jcreate_nblocks(inode) +
reiserfs_xattr_nblocks(inode, size) * 2;
reiserfs_write_lock(inode->i_sb);
error = journal_begin(&th, inode->i_sb, jcreate_blocks);
reiserfs_write_unlock(inode->i_sb);
if (error == 0) {
if (type == ACL_TYPE_ACCESS && acl) {
error = posix_acl_update_mode(inode, &mode, &acl);
if (error)
goto unlock;
update_mode = 1;
}
error = __reiserfs_set_acl(&th, inode, type, acl);
if (!error && update_mode)
inode->i_mode = mode;
unlock:
reiserfs_write_lock(inode->i_sb);
error2 = journal_end(&th);
reiserfs_write_unlock(inode->i_sb);
if (error2)
error = error2;
}
return error;
}
static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
int retval;
struct inode *inode = NULL;
struct reiserfs_dir_entry de;
INITIALIZE_PATH(path_to_entry);
if (REISERFS_MAX_NAME(dir->i_sb->s_blocksize) < dentry->d_name.len)
return ERR_PTR(-ENAMETOOLONG);
reiserfs_write_lock(dir->i_sb);
de.de_gen_number_bit_string = NULL;
retval =
reiserfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len,
&path_to_entry, &de);
pathrelse(&path_to_entry);
if (retval == NAME_FOUND) {
/* Hide the .reiserfs_priv directory */
if (reiserfs_xattrs(dir->i_sb) &&
!old_format_only(dir->i_sb) &&
REISERFS_SB(dir->i_sb)->priv_root &&
REISERFS_SB(dir->i_sb)->priv_root->d_inode &&
de.de_objectid ==
le32_to_cpu(INODE_PKEY
(REISERFS_SB(dir->i_sb)->priv_root->d_inode)->
k_objectid)) {
reiserfs_write_unlock(dir->i_sb);
return ERR_PTR(-EACCES);
}
inode =
reiserfs_iget(dir->i_sb, (struct cpu_key *)&(de.de_dir_id));
if (!inode || IS_ERR(inode)) {
reiserfs_write_unlock(dir->i_sb);
return ERR_PTR(-EACCES);
}
/* Propogate the priv_object flag so we know we're in the priv tree */
if (is_reiserfs_priv_object(dir))
reiserfs_mark_inode_private(inode);
}
reiserfs_write_unlock(dir->i_sb);
if (retval == IO_ERROR) {
return ERR_PTR(-EIO);
}
return d_splice_alias(inode, dentry);
}
static int
posix_acl_set(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags, int type)
{
struct inode *inode = dentry->d_inode;
struct posix_acl *acl;
int error, error2;
struct reiserfs_transaction_handle th;
size_t jcreate_blocks;
if (!reiserfs_posixacl(inode->i_sb))
return -EOPNOTSUPP;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl)) {
return PTR_ERR(acl);
} else if (acl) {
error = posix_acl_valid(acl);
if (error)
goto release_and_out;
}
} else
acl = NULL;
/* Pessimism: We can't assume that anything from the xattr root up
* has been created. */
jcreate_blocks = reiserfs_xattr_jcreate_nblocks(inode) +
reiserfs_xattr_nblocks(inode, size) * 2;
reiserfs_write_lock(inode->i_sb);
error = journal_begin(&th, inode->i_sb, jcreate_blocks);
if (error == 0) {
error = reiserfs_set_acl(&th, inode, type, acl);
error2 = journal_end(&th, inode->i_sb, jcreate_blocks);
if (error2)
error = error2;
}
reiserfs_write_unlock(inode->i_sb);
release_and_out:
posix_acl_release(acl);
return error;
}
int reiserfs_acl_chmod(struct inode *inode)
{
struct posix_acl *acl, *clone;
int error;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (get_inode_sd_version(inode) == STAT_DATA_V1 ||
!reiserfs_posixacl(inode->i_sb)) {
return 0;
}
reiserfs_write_unlock(inode->i_sb);
acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
reiserfs_write_lock(inode->i_sb);
if (!acl)
return 0;
if (IS_ERR(acl))
return PTR_ERR(acl);
clone = posix_acl_clone(acl, GFP_NOFS);
posix_acl_release(acl);
if (!clone)
return -ENOMEM;
error = posix_acl_chmod_masq(clone, inode->i_mode);
if (!error) {
struct reiserfs_transaction_handle th;
size_t size = reiserfs_xattr_nblocks(inode,
reiserfs_acl_size(clone->a_count));
int depth;
depth = reiserfs_write_lock_once(inode->i_sb);
error = journal_begin(&th, inode->i_sb, size * 2);
if (!error) {
int error2;
error = reiserfs_set_acl(&th, inode, ACL_TYPE_ACCESS,
clone);
error2 = journal_end(&th, inode->i_sb, size * 2);
if (error2)
error = error2;
}
reiserfs_write_unlock_once(inode->i_sb, depth);
}
posix_acl_release(clone);
return error;
}
static int reiserfs_sync_file(
struct file * p_s_filp,
struct dentry * p_s_dentry,
int datasync
) {
struct inode * p_s_inode = p_s_dentry->d_inode;
int n_err;
reiserfs_write_lock(p_s_inode->i_sb);
if (!S_ISREG(p_s_inode->i_mode))
BUG ();
n_err = sync_mapping_buffers(p_s_inode->i_mapping) ;
reiserfs_commit_for_inode(p_s_inode) ;
reiserfs_write_unlock(p_s_inode->i_sb);
return ( n_err < 0 ) ? -EIO : 0;
}
static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct inode *inode = filp->f_mapping->host;
int err;
err = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (err)
return err;
mutex_lock(&inode->i_mutex);
reiserfs_write_lock(inode->i_sb);
err = reiserfs_commit_for_inode(inode);
reiserfs_write_unlock(inode->i_sb);
mutex_unlock(&inode->i_mutex);
if (err < 0)
return err;
return 0;
}
static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
int retval;
struct inode *inode = NULL;
struct reiserfs_dir_entry de;
INITIALIZE_PATH(path_to_entry);
if (REISERFS_MAX_NAME(dir->i_sb->s_blocksize) < dentry->d_name.len)
return ERR_PTR(-ENAMETOOLONG);
reiserfs_write_lock(dir->i_sb);
de.de_gen_number_bit_string = NULL;
retval =
reiserfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len,
&path_to_entry, &de);
pathrelse(&path_to_entry);
if (retval == NAME_FOUND) {
inode = reiserfs_iget(dir->i_sb,
(struct cpu_key *)&de.de_dir_id);
if (!inode || IS_ERR(inode)) {
reiserfs_write_unlock(dir->i_sb);
return ERR_PTR(-EACCES);
}
/*
* Propagate the private flag so we know we're
* in the priv tree
*/
if (IS_PRIVATE(dir))
inode->i_flags |= S_PRIVATE;
}
reiserfs_write_unlock(dir->i_sb);
if (retval == IO_ERROR) {
return ERR_PTR(-EIO);
}
return d_splice_alias(inode, dentry);
}
/*
** We pack the tails of files on file close, not at the time they are written.
** This implies an unnecessary copy of the tail and an unnecessary indirect item
** insertion/balancing, for files that are written in one write.
** It avoids unnecessary tail packings (balances) for files that are written in
** multiple writes and are small enough to have tails.
**
** file_release is called by the VFS layer when the file is closed. If
** this is the last open file descriptor, and the file
** small enough to have a tail, and the tail is currently in an
** unformatted node, the tail is converted back into a direct item.
**
** We use reiserfs_truncate_file to pack the tail, since it already has
** all the conditions coded.
*/
static int reiserfs_file_release (struct inode * inode, struct file * filp)
{
struct reiserfs_transaction_handle th ;
if (!S_ISREG (inode->i_mode))
BUG ();
/* fast out for when nothing needs to be done */
if ((atomic_read(&inode->i_count) > 1 ||
!(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) ||
!tail_has_to_be_packed(inode)) &&
REISERFS_I(inode)->i_prealloc_count <= 0) {
return 0;
}
reiserfs_write_lock(inode->i_sb);
down (&inode->i_sem);
journal_begin(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 3) ;
reiserfs_update_inode_transaction(inode) ;
#ifdef REISERFS_PREALLOCATE
reiserfs_discard_prealloc (&th, inode);
#endif
journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 3) ;
if (atomic_read(&inode->i_count) <= 1 &&
(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) &&
tail_has_to_be_packed (inode)) {
/* if regular file is released by last holder and it has been
appended (we append by unformatted node only) or its direct
item(s) had to be converted, then it may have to be
indirect2direct converted */
reiserfs_truncate_file(inode, 0) ;
}
up (&inode->i_sem);
reiserfs_write_unlock(inode->i_sb);
return 0;
}
int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
filldir_t filldir, loff_t *pos)
{
struct inode *inode = dentry->d_inode;
struct cpu_key pos_key; /* key of current position in the directory (key of directory entry) */
INITIALIZE_PATH(path_to_entry);
struct buffer_head *bh;
int item_num, entry_num;
const struct reiserfs_key *rkey;
struct item_head *ih, tmp_ih;
int search_res;
char *local_buf;
loff_t next_pos;
char small_buf[32]; /* avoid kmalloc if we can */
struct reiserfs_dir_entry de;
int ret = 0;
reiserfs_write_lock(inode->i_sb);
reiserfs_check_lock_depth(inode->i_sb, "readdir");
/* form key for search the next directory entry using f_pos field of
file structure */
make_cpu_key(&pos_key, inode, *pos ?: DOT_OFFSET, TYPE_DIRENTRY, 3);
next_pos = cpu_key_k_offset(&pos_key);
path_to_entry.reada = PATH_READA;
while (1) {
research:
/* search the directory item, containing entry with specified key */
search_res =
search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
&de);
if (search_res == IO_ERROR) {
// FIXME: we could just skip part of directory which could
// not be read
ret = -EIO;
goto out;
}
entry_num = de.de_entry_num;
bh = de.de_bh;
item_num = de.de_item_num;
ih = de.de_ih;
store_ih(&tmp_ih, ih);
/* we must have found item, that is item of this directory, */
RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
"vs-9000: found item %h does not match to dir we readdir %K",
ih, &pos_key);
RFALSE(item_num > B_NR_ITEMS(bh) - 1,
"vs-9005 item_num == %d, item amount == %d",
item_num, B_NR_ITEMS(bh));
/* and entry must be not more than number of entries in the item */
RFALSE(I_ENTRY_COUNT(ih) < entry_num,
"vs-9010: entry number is too big %d (%d)",
entry_num, I_ENTRY_COUNT(ih));
if (search_res == POSITION_FOUND
|| entry_num < I_ENTRY_COUNT(ih)) {
/* go through all entries in the directory item beginning from the entry, that has been found */
struct reiserfs_de_head *deh =
B_I_DEH(bh, ih) + entry_num;
for (; entry_num < I_ENTRY_COUNT(ih);
entry_num++, deh++) {
int d_reclen;
char *d_name;
off_t d_off;
ino_t d_ino;
loff_t cur_pos = deh_offset(deh);
if (!de_visible(deh))
/* it is hidden entry */
continue;
d_reclen = entry_length(bh, ih, entry_num);
d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
if (d_reclen <= 0 ||
d_name + d_reclen > bh->b_data + bh->b_size) {
/* There is corrupted data in entry,
* We'd better stop here */
pathrelse(&path_to_entry);
ret = -EIO;
goto out;
}
if (!d_name[d_reclen - 1])
d_reclen = strlen(d_name);
if (d_reclen >
REISERFS_MAX_NAME(inode->i_sb->
s_blocksize)) {
/* too big to send back to VFS */
continue;
}
/* Ignore the .reiserfs_priv entry */
if (is_privroot_deh(dentry, deh))
continue;
d_off = deh_offset(deh);
*pos = d_off;
d_ino = deh_objectid(deh);
if (d_reclen <= 32) {
local_buf = small_buf;
} else {
local_buf = kmalloc(d_reclen,
GFP_NOFS);
if (!local_buf) {
pathrelse(&path_to_entry);
ret = -ENOMEM;
goto out;
}
if (item_moved(&tmp_ih, &path_to_entry)) {
kfree(local_buf);
goto research;
}
}
// Note, that we copy name to user space via temporary
// buffer (local_buf) because filldir will block if
// user space buffer is swapped out. At that time
// entry can move to somewhere else
memcpy(local_buf, d_name, d_reclen);
/*
* Since filldir might sleep, we can release
* the write lock here for other waiters
*/
reiserfs_write_unlock(inode->i_sb);
if (filldir
(dirent, local_buf, d_reclen, d_off, d_ino,
DT_UNKNOWN) < 0) {
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
goto end;
}
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
/* deh_offset(deh) may be invalid now. */
next_pos = cur_pos + 1;
if (item_moved(&tmp_ih, &path_to_entry)) {
goto research;
}
} /* for */
}
if (item_num != B_NR_ITEMS(bh) - 1)
// end of directory has been reached
goto end;
/* item we went through is last item of node. Using right
delimiting key check is it directory end */
rkey = get_rkey(&path_to_entry, inode->i_sb);
if (!comp_le_keys(rkey, &MIN_KEY)) {
/* set pos_key to key, that is the smallest and greater
that key of the last entry in the item */
set_cpu_key_k_offset(&pos_key, next_pos);
continue;
}
if (COMP_SHORT_KEYS(rkey, &pos_key)) {
// end of directory has been reached
goto end;
}
/* directory continues in the right neighboring block */
set_cpu_key_k_offset(&pos_key,
le_key_k_offset(KEY_FORMAT_3_5, rkey));
} /* while */
end:
*pos = next_pos;
pathrelse(&path_to_entry);
reiserfs_check_path(&path_to_entry);
out:
reiserfs_write_unlock(inode->i_sb);
return ret;
}
int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
filldir_t filldir, loff_t *pos)
{
struct inode *inode = dentry->d_inode;
struct cpu_key pos_key;
INITIALIZE_PATH(path_to_entry);
struct buffer_head *bh;
int item_num, entry_num;
const struct reiserfs_key *rkey;
struct item_head *ih, tmp_ih;
int search_res;
char *local_buf;
loff_t next_pos;
char small_buf[32];
struct reiserfs_dir_entry de;
int ret = 0;
reiserfs_write_lock(inode->i_sb);
reiserfs_check_lock_depth(inode->i_sb, "readdir");
make_cpu_key(&pos_key, inode, *pos ?: DOT_OFFSET, TYPE_DIRENTRY, 3);
next_pos = cpu_key_k_offset(&pos_key);
path_to_entry.reada = PATH_READA;
while (1) {
research:
search_res =
search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
&de);
if (search_res == IO_ERROR) {
ret = -EIO;
goto out;
}
entry_num = de.de_entry_num;
bh = de.de_bh;
item_num = de.de_item_num;
ih = de.de_ih;
store_ih(&tmp_ih, ih);
RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
"vs-9000: found item %h does not match to dir we readdir %K",
ih, &pos_key);
RFALSE(item_num > B_NR_ITEMS(bh) - 1,
"vs-9005 item_num == %d, item amount == %d",
item_num, B_NR_ITEMS(bh));
RFALSE(I_ENTRY_COUNT(ih) < entry_num,
"vs-9010: entry number is too big %d (%d)",
entry_num, I_ENTRY_COUNT(ih));
if (search_res == POSITION_FOUND
|| entry_num < I_ENTRY_COUNT(ih)) {
struct reiserfs_de_head *deh =
B_I_DEH(bh, ih) + entry_num;
for (; entry_num < I_ENTRY_COUNT(ih);
entry_num++, deh++) {
int d_reclen;
char *d_name;
off_t d_off;
ino_t d_ino;
if (!de_visible(deh))
continue;
d_reclen = entry_length(bh, ih, entry_num);
d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
if (d_reclen <= 0 ||
d_name + d_reclen > bh->b_data + bh->b_size) {
pathrelse(&path_to_entry);
ret = -EIO;
goto out;
}
if (!d_name[d_reclen - 1])
d_reclen = strlen(d_name);
if (d_reclen >
REISERFS_MAX_NAME(inode->i_sb->
s_blocksize)) {
continue;
}
if (is_privroot_deh(dentry, deh))
continue;
d_off = deh_offset(deh);
*pos = d_off;
d_ino = deh_objectid(deh);
if (d_reclen <= 32) {
local_buf = small_buf;
} else {
local_buf = kmalloc(d_reclen,
GFP_NOFS);
if (!local_buf) {
pathrelse(&path_to_entry);
ret = -ENOMEM;
goto out;
}
if (item_moved(&tmp_ih, &path_to_entry)) {
kfree(local_buf);
goto research;
}
}
memcpy(local_buf, d_name, d_reclen);
reiserfs_write_unlock(inode->i_sb);
if (filldir
(dirent, local_buf, d_reclen, d_off, d_ino,
DT_UNKNOWN) < 0) {
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
goto end;
}
reiserfs_write_lock(inode->i_sb);
if (local_buf != small_buf) {
kfree(local_buf);
}
next_pos = deh_offset(deh) + 1;
if (item_moved(&tmp_ih, &path_to_entry)) {
goto research;
}
}
}
if (item_num != B_NR_ITEMS(bh) - 1)
goto end;
rkey = get_rkey(&path_to_entry, inode->i_sb);
if (!comp_le_keys(rkey, &MIN_KEY)) {
set_cpu_key_k_offset(&pos_key, next_pos);
continue;
}
if (COMP_SHORT_KEYS(rkey, &pos_key)) {
goto end;
}
set_cpu_key_k_offset(&pos_key,
le_key_k_offset(KEY_FORMAT_3_5, rkey));
}
end:
*pos = next_pos;
pathrelse(&path_to_entry);
reiserfs_check_path(&path_to_entry);
out:
reiserfs_write_unlock(inode->i_sb);
return ret;
}
static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
{
int retval, err;
struct inode *inode;
struct reiserfs_transaction_handle th;
int jbegin_count;
INITIALIZE_PATH(path);
struct reiserfs_dir_entry de;
/* we will be doing 2 balancings and update 2 stat data, we change quotas
* of the owner of the directory and of the owner of the parent directory.
* The quota structure is possibly deleted only on last iput => outside
* of this transaction */
jbegin_count =
JOURNAL_PER_BALANCE_CNT * 2 + 2 +
4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
dquot_initialize(dir);
reiserfs_write_lock(dir->i_sb);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval)
goto out_rmdir;
de.de_gen_number_bit_string = NULL;
if ((retval =
reiserfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len,
&path, &de)) == NAME_NOT_FOUND) {
retval = -ENOENT;
goto end_rmdir;
} else if (retval == IO_ERROR) {
retval = -EIO;
goto end_rmdir;
}
inode = dentry->d_inode;
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
if (de.de_objectid != inode->i_ino) {
// FIXME: compare key of an object and a key found in the
// entry
retval = -EIO;
goto end_rmdir;
}
if (!reiserfs_empty_dir(inode)) {
retval = -ENOTEMPTY;
goto end_rmdir;
}
/* cut entry from dir directory */
retval = reiserfs_cut_from_item(&th, &path, &(de.de_entry_key), dir, NULL, /* page */
0 /*new file size - not used here */ );
if (retval < 0)
goto end_rmdir;
if (inode->i_nlink != 2 && inode->i_nlink != 1)
reiserfs_error(inode->i_sb, "reiserfs-7040",
"empty directory has nlink != 2 (%d)",
inode->i_nlink);
clear_nlink(inode);
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
reiserfs_update_sd(&th, inode);
DEC_DIR_INODE_NLINK(dir)
dir->i_size -= (DEH_SIZE + de.de_entrylen);
reiserfs_update_sd(&th, dir);
/* prevent empty directory from getting lost */
add_save_link(&th, inode, 0 /* not truncate */ );
retval = journal_end(&th, dir->i_sb, jbegin_count);
reiserfs_check_path(&path);
out_rmdir:
reiserfs_write_unlock(dir->i_sb);
return retval;
end_rmdir:
/* we must release path, because we did not call
reiserfs_cut_from_item, or reiserfs_cut_from_item does not
release path if operation was not complete */
pathrelse(&path);
err = journal_end(&th, dir->i_sb, jbegin_count);
reiserfs_write_unlock(dir->i_sb);
return err ? err : retval;
}
static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
dev_t rdev)
{
int retval;
struct inode *inode;
struct reiserfs_transaction_handle th;
struct reiserfs_security_handle security;
/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 +
2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb));
if (!new_valid_dev(rdev))
return -EINVAL;
dquot_initialize(dir);
if (!(inode = new_inode(dir->i_sb))) {
return -ENOMEM;
}
new_inode_init(inode, dir, mode);
jbegin_count += reiserfs_cache_default_acl(dir);
retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
if (retval < 0) {
drop_new_inode(inode);
return retval;
}
jbegin_count += retval;
reiserfs_write_lock(dir->i_sb);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
drop_new_inode(inode);
goto out_failed;
}
retval =
reiserfs_new_inode(&th, dir, mode, NULL, 0 /*i_size */ , dentry,
inode, &security);
if (retval) {
goto out_failed;
}
inode->i_op = &reiserfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
//FIXME: needed for block and char devices only
reiserfs_update_sd(&th, inode);
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
retval =
reiserfs_add_entry(&th, dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
retval = err;
unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
unlock_new_inode(inode);
d_instantiate(dentry, inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
out_failed:
reiserfs_write_unlock(dir->i_sb);
return retval;
}
static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
struct nameidata *nd)
{
int retval;
struct inode *inode;
/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 2 +
2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb));
struct reiserfs_transaction_handle th;
struct reiserfs_security_handle security;
dquot_initialize(dir);
if (!(inode = new_inode(dir->i_sb))) {
return -ENOMEM;
}
new_inode_init(inode, dir, mode);
jbegin_count += reiserfs_cache_default_acl(dir);
retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
if (retval < 0) {
drop_new_inode(inode);
return retval;
}
jbegin_count += retval;
reiserfs_write_lock(dir->i_sb);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
drop_new_inode(inode);
goto out_failed;
}
retval =
reiserfs_new_inode(&th, dir, mode, NULL, 0 /*i_size */ , dentry,
inode, &security);
if (retval)
goto out_failed;
inode->i_op = &reiserfs_file_inode_operations;
inode->i_fop = &reiserfs_file_operations;
inode->i_mapping->a_ops = &reiserfs_address_space_operations;
retval =
reiserfs_add_entry(&th, dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
retval = err;
unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
unlock_new_inode(inode);
d_instantiate(dentry, inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
out_failed:
reiserfs_write_unlock(dir->i_sb);
return retval;
}
/* Allocates blocks for a file to fulfil write request.
Maps all unmapped but prepared pages from the list.
Updates metadata with newly allocated blocknumbers as needed */
int reiserfs_allocate_blocks_for_region(
struct reiserfs_transaction_handle *th,
struct inode *inode, /* Inode we work with */
loff_t pos, /* Writing position */
int num_pages, /* number of pages write going
to touch */
int write_bytes, /* amount of bytes to write */
struct page **prepared_pages, /* array of
prepared pages
*/
int blocks_to_allocate /* Amount of blocks we
need to allocate to
fit the data into file
*/
)
{
struct cpu_key key; // cpu key of item that we are going to deal with
struct item_head *ih; // pointer to item head that we are going to deal with
struct buffer_head *bh; // Buffer head that contains items that we are going to deal with
__u32 * item; // pointer to item we are going to deal with
INITIALIZE_PATH(path); // path to item, that we are going to deal with.
b_blocknr_t *allocated_blocks; // Pointer to a place where allocated blocknumbers would be stored.
reiserfs_blocknr_hint_t hint; // hint structure for block allocator.
size_t res; // return value of various functions that we call.
int curr_block; // current block used to keep track of unmapped blocks.
int i; // loop counter
int itempos; // position in item
unsigned int from = (pos & (PAGE_CACHE_SIZE - 1)); // writing position in
// first page
unsigned int to = ((pos + write_bytes - 1) & (PAGE_CACHE_SIZE - 1)) + 1; /* last modified byte offset in last page */
__u64 hole_size ; // amount of blocks for a file hole, if it needed to be created.
int modifying_this_item = 0; // Flag for items traversal code to keep track
// of the fact that we already prepared
// current block for journal
int will_prealloc = 0;
RFALSE(!blocks_to_allocate, "green-9004: tried to allocate zero blocks?");
/* only preallocate if this is a small write */
if (REISERFS_I(inode)->i_prealloc_count ||
(!(write_bytes & (inode->i_sb->s_blocksize -1)) &&
blocks_to_allocate <
REISERFS_SB(inode->i_sb)->s_alloc_options.preallocsize))
will_prealloc = REISERFS_SB(inode->i_sb)->s_alloc_options.preallocsize;
allocated_blocks = kmalloc((blocks_to_allocate + will_prealloc) *
sizeof(b_blocknr_t), GFP_NOFS);
/* First we compose a key to point at the writing position, we want to do
that outside of any locking region. */
make_cpu_key (&key, inode, pos+1, TYPE_ANY, 3/*key length*/);
/* If we came here, it means we absolutely need to open a transaction,
since we need to allocate some blocks */
reiserfs_write_lock(inode->i_sb); // Journaling stuff and we need that.
journal_begin(th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 3 + 1); // Wish I know if this number enough
reiserfs_update_inode_transaction(inode) ;
/* Look for the in-tree position of our write, need path for block allocator */
res = search_for_position_by_key(inode->i_sb, &key, &path);
if ( res == IO_ERROR ) {
res = -EIO;
goto error_exit;
}
/* Allocate blocks */
/* First fill in "hint" structure for block allocator */
hint.th = th; // transaction handle.
hint.path = &path; // Path, so that block allocator can determine packing locality or whatever it needs to determine.
hint.inode = inode; // Inode is needed by block allocator too.
hint.search_start = 0; // We have no hint on where to search free blocks for block allocator.
hint.key = key.on_disk_key; // on disk key of file.
hint.block = inode->i_blocks>>(inode->i_sb->s_blocksize_bits-9); // Number of disk blocks this file occupies already.
hint.formatted_node = 0; // We are allocating blocks for unformatted node.
hint.preallocate = will_prealloc;
/* Call block allocator to allocate blocks */
res = reiserfs_allocate_blocknrs(&hint, allocated_blocks, blocks_to_allocate, blocks_to_allocate);
if ( res != CARRY_ON ) {
if ( res == NO_DISK_SPACE ) {
/* We flush the transaction in case of no space. This way some
blocks might become free */
SB_JOURNAL(inode->i_sb)->j_must_wait = 1;
restart_transaction(th, inode, &path);
/* We might have scheduled, so search again */
res = search_for_position_by_key(inode->i_sb, &key, &path);
if ( res == IO_ERROR ) {
res = -EIO;
goto error_exit;
}
/* update changed info for hint structure. */
res = reiserfs_allocate_blocknrs(&hint, allocated_blocks, blocks_to_allocate, blocks_to_allocate);
if ( res != CARRY_ON ) {
res = -ENOSPC;
pathrelse(&path);
goto error_exit;
}
} else {
res = -ENOSPC;
pathrelse(&path);
goto error_exit;
}
}
#ifdef __BIG_ENDIAN
// Too bad, I have not found any way to convert a given region from
// cpu format to little endian format
{
int i;
for ( i = 0; i < blocks_to_allocate ; i++)
allocated_blocks[i]=cpu_to_le32(allocated_blocks[i]);
}
#endif
/* Blocks allocating well might have scheduled and tree might have changed,
let's search the tree again */
/* find where in the tree our write should go */
res = search_for_position_by_key(inode->i_sb, &key, &path);
if ( res == IO_ERROR ) {
res = -EIO;
goto error_exit_free_blocks;
}
bh = get_last_bh( &path ); // Get a bufferhead for last element in path.
ih = get_ih( &path ); // Get a pointer to last item head in path.
item = get_item( &path ); // Get a pointer to last item in path
/* Let's see what we have found */
if ( res != POSITION_FOUND ) { /* position not found, this means that we
might need to append file with holes
first */
// Since we are writing past the file's end, we need to find out if
// there is a hole that needs to be inserted before our writing
// position, and how many blocks it is going to cover (we need to
// populate pointers to file blocks representing the hole with zeros)
{
int item_offset = 1;
/*
* if ih is stat data, its offset is 0 and we don't want to
* add 1 to pos in the hole_size calculation
*/
if (is_statdata_le_ih(ih))
item_offset = 0;
hole_size = (pos + item_offset -
(le_key_k_offset( get_inode_item_key_version(inode),
&(ih->ih_key)) +
op_bytes_number(ih, inode->i_sb->s_blocksize))) >>
inode->i_sb->s_blocksize_bits;
}
/*
* process, that is going to call fix_nodes/do_balance must hold only
* one path. If it holds 2 or more, it can get into endless waiting in
* get_empty_nodes or its clones
*/
static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
int retval;
INITIALIZE_PATH(old_entry_path);
INITIALIZE_PATH(new_entry_path);
INITIALIZE_PATH(dot_dot_entry_path);
struct item_head new_entry_ih, old_entry_ih, dot_dot_ih;
struct reiserfs_dir_entry old_de, new_de, dot_dot_de;
struct inode *old_inode, *new_dentry_inode;
struct reiserfs_transaction_handle th;
int jbegin_count;
umode_t old_inode_mode;
unsigned long savelink = 1;
struct timespec ctime;
/* three balancings: (1) old name removal, (2) new name insertion
and (3) maybe "save" link insertion
stat data updates: (1) old directory,
(2) new directory and (3) maybe old object stat data (when it is
directory) and (4) maybe stat data of object to which new entry
pointed initially and (5) maybe block containing ".." of
renamed directory
quota updates: two parent directories */
jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 + 5 +
4 * REISERFS_QUOTA_TRANS_BLOCKS(old_dir->i_sb);
dquot_initialize(old_dir);
dquot_initialize(new_dir);
old_inode = old_dentry->d_inode;
new_dentry_inode = new_dentry->d_inode;
// make sure, that oldname still exists and points to an object we
// are going to rename
old_de.de_gen_number_bit_string = NULL;
reiserfs_write_lock(old_dir->i_sb);
retval =
reiserfs_find_entry(old_dir, old_dentry->d_name.name,
old_dentry->d_name.len, &old_entry_path,
&old_de);
pathrelse(&old_entry_path);
if (retval == IO_ERROR) {
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
if (retval != NAME_FOUND || old_de.de_objectid != old_inode->i_ino) {
reiserfs_write_unlock(old_dir->i_sb);
return -ENOENT;
}
old_inode_mode = old_inode->i_mode;
if (S_ISDIR(old_inode_mode)) {
// make sure, that directory being renamed has correct ".."
// and that its new parent directory has not too many links
// already
if (new_dentry_inode) {
if (!reiserfs_empty_dir(new_dentry_inode)) {
reiserfs_write_unlock(old_dir->i_sb);
return -ENOTEMPTY;
}
}
/* directory is renamed, its parent directory will be changed,
** so find ".." entry
*/
dot_dot_de.de_gen_number_bit_string = NULL;
retval =
reiserfs_find_entry(old_inode, "..", 2, &dot_dot_entry_path,
&dot_dot_de);
pathrelse(&dot_dot_entry_path);
if (retval != NAME_FOUND) {
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
/* inode number of .. must equal old_dir->i_ino */
if (dot_dot_de.de_objectid != old_dir->i_ino) {
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
}
retval = journal_begin(&th, old_dir->i_sb, jbegin_count);
if (retval) {
reiserfs_write_unlock(old_dir->i_sb);
return retval;
}
/* add new entry (or find the existing one) */
retval =
reiserfs_add_entry(&th, new_dir, new_dentry->d_name.name,
new_dentry->d_name.len, old_inode, 0);
if (retval == -EEXIST) {
if (!new_dentry_inode) {
reiserfs_panic(old_dir->i_sb, "vs-7050",
"new entry is found, new inode == 0");
}
} else if (retval) {
int err = journal_end(&th, old_dir->i_sb, jbegin_count);
reiserfs_write_unlock(old_dir->i_sb);
return err ? err : retval;
}
reiserfs_update_inode_transaction(old_dir);
reiserfs_update_inode_transaction(new_dir);
/* this makes it so an fsync on an open fd for the old name will
** commit the rename operation
*/
reiserfs_update_inode_transaction(old_inode);
if (new_dentry_inode)
reiserfs_update_inode_transaction(new_dentry_inode);
while (1) {
// look for old name using corresponding entry key (found by reiserfs_find_entry)
if ((retval =
search_by_entry_key(new_dir->i_sb, &old_de.de_entry_key,
&old_entry_path,
&old_de)) != NAME_FOUND) {
pathrelse(&old_entry_path);
journal_end(&th, old_dir->i_sb, jbegin_count);
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
copy_item_head(&old_entry_ih, get_ih(&old_entry_path));
reiserfs_prepare_for_journal(old_inode->i_sb, old_de.de_bh, 1);
// look for new name by reiserfs_find_entry
new_de.de_gen_number_bit_string = NULL;
retval =
reiserfs_find_entry(new_dir, new_dentry->d_name.name,
new_dentry->d_name.len, &new_entry_path,
&new_de);
// reiserfs_add_entry should not return IO_ERROR, because it is called with essentially same parameters from
// reiserfs_add_entry above, and we'll catch any i/o errors before we get here.
if (retval != NAME_FOUND_INVISIBLE && retval != NAME_FOUND) {
pathrelse(&new_entry_path);
pathrelse(&old_entry_path);
journal_end(&th, old_dir->i_sb, jbegin_count);
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
copy_item_head(&new_entry_ih, get_ih(&new_entry_path));
reiserfs_prepare_for_journal(old_inode->i_sb, new_de.de_bh, 1);
if (S_ISDIR(old_inode->i_mode)) {
if ((retval =
search_by_entry_key(new_dir->i_sb,
&dot_dot_de.de_entry_key,
&dot_dot_entry_path,
&dot_dot_de)) != NAME_FOUND) {
pathrelse(&dot_dot_entry_path);
pathrelse(&new_entry_path);
pathrelse(&old_entry_path);
journal_end(&th, old_dir->i_sb, jbegin_count);
reiserfs_write_unlock(old_dir->i_sb);
return -EIO;
}
copy_item_head(&dot_dot_ih,
get_ih(&dot_dot_entry_path));
// node containing ".." gets into transaction
reiserfs_prepare_for_journal(old_inode->i_sb,
dot_dot_de.de_bh, 1);
}
/* we should check seals here, not do
this stuff, yes? Then, having
gathered everything into RAM we
should lock the buffers, yes? -Hans */
/* probably. our rename needs to hold more
** than one path at once. The seals would
** have to be written to deal with multi-path
** issues -chris
*/
/* sanity checking before doing the rename - avoid races many
** of the above checks could have scheduled. We have to be
** sure our items haven't been shifted by another process.
*/
if (item_moved(&new_entry_ih, &new_entry_path) ||
!entry_points_to_object(new_dentry->d_name.name,
new_dentry->d_name.len,
&new_de, new_dentry_inode) ||
item_moved(&old_entry_ih, &old_entry_path) ||
!entry_points_to_object(old_dentry->d_name.name,
old_dentry->d_name.len,
&old_de, old_inode)) {
reiserfs_restore_prepared_buffer(old_inode->i_sb,
new_de.de_bh);
reiserfs_restore_prepared_buffer(old_inode->i_sb,
old_de.de_bh);
if (S_ISDIR(old_inode_mode))
reiserfs_restore_prepared_buffer(old_inode->
i_sb,
dot_dot_de.
de_bh);
continue;
}
if (S_ISDIR(old_inode_mode)) {
if (item_moved(&dot_dot_ih, &dot_dot_entry_path) ||
!entry_points_to_object("..", 2, &dot_dot_de,
old_dir)) {
reiserfs_restore_prepared_buffer(old_inode->
i_sb,
old_de.de_bh);
reiserfs_restore_prepared_buffer(old_inode->
i_sb,
new_de.de_bh);
reiserfs_restore_prepared_buffer(old_inode->
i_sb,
dot_dot_de.
de_bh);
continue;
}
}
RFALSE(S_ISDIR(old_inode_mode) &&
!buffer_journal_prepared(dot_dot_de.de_bh), "");
break;
}
/* ok, all the changes can be done in one fell swoop when we
have claimed all the buffers needed. */
mark_de_visible(new_de.de_deh + new_de.de_entry_num);
set_ino_in_dir_entry(&new_de, INODE_PKEY(old_inode));
journal_mark_dirty(&th, old_dir->i_sb, new_de.de_bh);
mark_de_hidden(old_de.de_deh + old_de.de_entry_num);
journal_mark_dirty(&th, old_dir->i_sb, old_de.de_bh);
ctime = CURRENT_TIME_SEC;
old_dir->i_ctime = old_dir->i_mtime = ctime;
new_dir->i_ctime = new_dir->i_mtime = ctime;
/* thanks to Alex Adriaanse <*****@*****.**> for patch which adds ctime update of
renamed object */
old_inode->i_ctime = ctime;
if (new_dentry_inode) {
// adjust link number of the victim
if (S_ISDIR(new_dentry_inode->i_mode)) {
clear_nlink(new_dentry_inode);
} else {
drop_nlink(new_dentry_inode);
}
new_dentry_inode->i_ctime = ctime;
savelink = new_dentry_inode->i_nlink;
}
if (S_ISDIR(old_inode_mode)) {
/* adjust ".." of renamed directory */
set_ino_in_dir_entry(&dot_dot_de, INODE_PKEY(new_dir));
journal_mark_dirty(&th, new_dir->i_sb, dot_dot_de.de_bh);
if (!new_dentry_inode)
/* there (in new_dir) was no directory, so it got new link
(".." of renamed directory) */
INC_DIR_INODE_NLINK(new_dir);
/* old directory lost one link - ".. " of renamed directory */
DEC_DIR_INODE_NLINK(old_dir);
}
// looks like in 2.3.99pre3 brelse is atomic. so we can use pathrelse
pathrelse(&new_entry_path);
pathrelse(&dot_dot_entry_path);
// FIXME: this reiserfs_cut_from_item's return value may screw up
// anybody, but it will panic if will not be able to find the
// entry. This needs one more clean up
if (reiserfs_cut_from_item
(&th, &old_entry_path, &(old_de.de_entry_key), old_dir, NULL,
0) < 0)
reiserfs_error(old_dir->i_sb, "vs-7060",
"couldn't not cut old name. Fsck later?");
old_dir->i_size -= DEH_SIZE + old_de.de_entrylen;
reiserfs_update_sd(&th, old_dir);
reiserfs_update_sd(&th, new_dir);
reiserfs_update_sd(&th, old_inode);
if (new_dentry_inode) {
if (savelink == 0)
add_save_link(&th, new_dentry_inode,
0 /* not truncate */ );
reiserfs_update_sd(&th, new_dentry_inode);
}
retval = journal_end(&th, old_dir->i_sb, jbegin_count);
reiserfs_write_unlock(old_dir->i_sb);
return retval;
}
static int reiserfs_symlink(struct inode *parent_dir,
struct dentry *dentry, const char *symname)
{
int retval;
struct inode *inode;
char *name;
int item_len;
struct reiserfs_transaction_handle th;
struct reiserfs_security_handle security;
int mode = S_IFLNK | S_IRWXUGO;
/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 +
2 * (REISERFS_QUOTA_INIT_BLOCKS(parent_dir->i_sb) +
REISERFS_QUOTA_TRANS_BLOCKS(parent_dir->i_sb));
dquot_initialize(parent_dir);
if (!(inode = new_inode(parent_dir->i_sb))) {
return -ENOMEM;
}
new_inode_init(inode, parent_dir, mode);
retval = reiserfs_security_init(parent_dir, inode, &dentry->d_name,
&security);
if (retval < 0) {
drop_new_inode(inode);
return retval;
}
jbegin_count += retval;
reiserfs_write_lock(parent_dir->i_sb);
item_len = ROUND_UP(strlen(symname));
if (item_len > MAX_DIRECT_ITEM_LEN(parent_dir->i_sb->s_blocksize)) {
retval = -ENAMETOOLONG;
drop_new_inode(inode);
goto out_failed;
}
name = kmalloc(item_len, GFP_NOFS);
if (!name) {
drop_new_inode(inode);
retval = -ENOMEM;
goto out_failed;
}
memcpy(name, symname, strlen(symname));
padd_item(name, item_len, strlen(symname));
retval = journal_begin(&th, parent_dir->i_sb, jbegin_count);
if (retval) {
drop_new_inode(inode);
kfree(name);
goto out_failed;
}
retval =
reiserfs_new_inode(&th, parent_dir, mode, name, strlen(symname),
dentry, inode, &security);
kfree(name);
if (retval) { /* reiserfs_new_inode iputs for us */
goto out_failed;
}
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(parent_dir);
inode->i_op = &reiserfs_symlink_inode_operations;
inode->i_mapping->a_ops = &reiserfs_address_space_operations;
// must be sure this inode is written with this transaction
//
//reiserfs_update_sd (&th, inode, READ_BLOCKS);
retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, parent_dir->i_sb, jbegin_count);
if (err)
retval = err;
unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
unlock_new_inode(inode);
d_instantiate(dentry, inode);
retval = journal_end(&th, parent_dir->i_sb, jbegin_count);
out_failed:
reiserfs_write_unlock(parent_dir->i_sb);
return retval;
}
/*
* inode->i_mutex: down
*/
int
reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
struct inode *inode, const char *name,
const void *buffer, size_t buffer_size, int flags)
{
int err = 0;
struct dentry *dentry;
struct page *page;
char *data;
size_t file_pos = 0;
size_t buffer_pos = 0;
size_t new_size;
__u32 xahash = 0;
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
reiserfs_write_unlock(inode->i_sb);
if (!buffer) {
err = lookup_and_delete_xattr(inode, name);
reiserfs_write_lock(inode->i_sb);
return err;
}
dentry = xattr_lookup(inode, name, flags);
if (IS_ERR(dentry)) {
reiserfs_write_lock(inode->i_sb);
return PTR_ERR(dentry);
}
down_write(&REISERFS_I(inode)->i_xattr_sem);
reiserfs_write_lock(inode->i_sb);
xahash = xattr_hash(buffer, buffer_size);
while (buffer_pos < buffer_size || buffer_pos == 0) {
size_t chunk;
size_t skip = 0;
size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE;
else
chunk = buffer_size - buffer_pos;
page = reiserfs_get_page(dentry->d_inode, file_pos);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
lock_page(page);
data = page_address(page);
if (file_pos == 0) {
struct reiserfs_xattr_header *rxh;
skip = file_pos = sizeof(struct reiserfs_xattr_header);
if (chunk + skip > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE - skip;
rxh = (struct reiserfs_xattr_header *)data;
rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
rxh->h_hash = cpu_to_le32(xahash);
}
err = __reiserfs_write_begin(page, page_offset, chunk + skip);
if (!err) {
if (buffer)
memcpy(data + skip, buffer + buffer_pos, chunk);
err = reiserfs_commit_write(NULL, page, page_offset,
page_offset + chunk +
skip);
}
unlock_page(page);
reiserfs_put_page(page);
buffer_pos += chunk;
file_pos += chunk;
skip = 0;
if (err || buffer_size == 0 || !buffer)
break;
}
new_size = buffer_size + sizeof(struct reiserfs_xattr_header);
if (!err && new_size < i_size_read(dentry->d_inode)) {
struct iattr newattrs = {
.ia_ctime = current_fs_time(inode->i_sb),
.ia_size = new_size,
.ia_valid = ATTR_SIZE | ATTR_CTIME,
};
reiserfs_write_unlock(inode->i_sb);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
down_write(&dentry->d_inode->i_alloc_sem);
reiserfs_write_lock(inode->i_sb);
err = reiserfs_setattr(dentry, &newattrs);
up_write(&dentry->d_inode->i_alloc_sem);
mutex_unlock(&dentry->d_inode->i_mutex);
} else
update_ctime(inode);
out_unlock:
up_write(&REISERFS_I(inode)->i_xattr_sem);
dput(dentry);
return err;
}
static int reiserfs_for_each_xattr(struct inode *inode,
int (*action)(struct dentry *, void *),
void *data)
{
struct dentry *dir;
int i, err = 0;
loff_t pos = 0;
struct reiserfs_dentry_buf buf = {
.count = 0,
};
/* Skip out, an xattr has no xattrs associated with it */
if (IS_PRIVATE(inode) || get_inode_sd_version(inode) == STAT_DATA_V1)
return 0;
reiserfs_write_unlock(inode->i_sb);
dir = open_xa_dir(inode, XATTR_REPLACE);
if (IS_ERR(dir)) {
err = PTR_ERR(dir);
reiserfs_write_lock(inode->i_sb);
goto out;
} else if (!dir->d_inode) {
err = 0;
reiserfs_write_lock(inode->i_sb);
goto out_dir;
}
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR);
reiserfs_write_lock(inode->i_sb);
buf.xadir = dir;
err = reiserfs_readdir_dentry(dir, &buf, fill_with_dentries, &pos);
while ((err == 0 || err == -ENOSPC) && buf.count) {
err = 0;
for (i = 0; i < buf.count && buf.dentries[i]; i++) {
int lerr = 0;
struct dentry *dentry = buf.dentries[i];
if (err == 0 && !S_ISDIR(dentry->d_inode->i_mode))
lerr = action(dentry, data);
dput(dentry);
buf.dentries[i] = NULL;
err = lerr ?: err;
}
buf.count = 0;
if (!err)
err = reiserfs_readdir_dentry(dir, &buf,
fill_with_dentries, &pos);
}
mutex_unlock(&dir->d_inode->i_mutex);
/* Clean up after a failed readdir */
cleanup_dentry_buf(&buf);
if (!err) {
/* We start a transaction here to avoid a ABBA situation
* between the xattr root's i_mutex and the journal lock.
* This doesn't incur much additional overhead since the
* new transaction will just nest inside the
* outer transaction. */
int blocks = JOURNAL_PER_BALANCE_CNT * 2 + 2 +
4 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
struct reiserfs_transaction_handle th;
err = journal_begin(&th, inode->i_sb, blocks);
if (!err) {
int jerror;
reiserfs_mutex_lock_nested_safe(
&dir->d_parent->d_inode->i_mutex,
I_MUTEX_XATTR, inode->i_sb);
err = action(dir, data);
jerror = journal_end(&th, inode->i_sb, blocks);
mutex_unlock(&dir->d_parent->d_inode->i_mutex);
err = jerror ?: err;
}
}
static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
{
int retval, err;
struct inode *inode;
struct reiserfs_dir_entry de;
INITIALIZE_PATH(path);
struct reiserfs_transaction_handle th;
int jbegin_count;
unsigned long savelink;
retval = dquot_initialize(dir);
if (retval)
return retval;
inode = d_inode(dentry);
/*
* in this transaction we can be doing at max two balancings and
* update two stat datas, we change quotas of the owner of the
* directory and of the owner of the parent directory. The quota
* structure is possibly deleted only on iput => outside of
* this transaction
*/
jbegin_count =
JOURNAL_PER_BALANCE_CNT * 2 + 2 +
4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
reiserfs_write_lock(dir->i_sb);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval)
goto out_unlink;
de.de_gen_number_bit_string = NULL;
if ((retval =
reiserfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len,
&path, &de)) == NAME_NOT_FOUND) {
retval = -ENOENT;
goto end_unlink;
} else if (retval == IO_ERROR) {
retval = -EIO;
goto end_unlink;
}
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
if (de.de_objectid != inode->i_ino) {
/*
* FIXME: compare key of an object and a key found in the entry
*/
retval = -EIO;
goto end_unlink;
}
if (!inode->i_nlink) {
reiserfs_warning(inode->i_sb, "reiserfs-7042",
"deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
set_nlink(inode, 1);
}
drop_nlink(inode);
/*
* we schedule before doing the add_save_link call, save the link
* count so we don't race
*/
savelink = inode->i_nlink;
retval =
reiserfs_cut_from_item(&th, &path, &de.de_entry_key, dir, NULL,
0);
if (retval < 0) {
inc_nlink(inode);
goto end_unlink;
}
inode->i_ctime = current_time(inode);
reiserfs_update_sd(&th, inode);
dir->i_size -= (de.de_entrylen + DEH_SIZE);
dir->i_ctime = dir->i_mtime = current_time(dir);
reiserfs_update_sd(&th, dir);
if (!savelink)
/* prevent file from getting lost */
add_save_link(&th, inode, 0 /* not truncate */ );
retval = journal_end(&th);
reiserfs_check_path(&path);
reiserfs_write_unlock(dir->i_sb);
return retval;
end_unlink:
pathrelse(&path);
err = journal_end(&th);
reiserfs_check_path(&path);
if (err)
retval = err;
out_unlink:
reiserfs_write_unlock(dir->i_sb);
return retval;
}
static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int retval;
struct inode *inode;
struct reiserfs_transaction_handle th;
struct reiserfs_security_handle security;
/*
* We need blocks for transaction + (user+group)*(quotas
* for new inode + update of quota for directory owner)
*/
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 +
2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb));
retval = dquot_initialize(dir);
if (retval)
return retval;
#ifdef DISPLACE_NEW_PACKING_LOCALITIES
/*
* set flag that new packing locality created and new blocks
* for the content of that directory are not displaced yet
*/
REISERFS_I(dir)->new_packing_locality = 1;
#endif
mode = S_IFDIR | mode;
if (!(inode = new_inode(dir->i_sb))) {
return -ENOMEM;
}
retval = new_inode_init(inode, dir, mode);
if (retval) {
drop_new_inode(inode);
return retval;
}
jbegin_count += reiserfs_cache_default_acl(dir);
retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
if (retval < 0) {
drop_new_inode(inode);
return retval;
}
jbegin_count += retval;
reiserfs_write_lock(dir->i_sb);
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
drop_new_inode(inode);
goto out_failed;
}
/*
* inc the link count now, so another writer doesn't overflow
* it while we sleep later on.
*/
INC_DIR_INODE_NLINK(dir)
retval = reiserfs_new_inode(&th, dir, mode, NULL /*symlink */ ,
old_format_only(dir->i_sb) ?
EMPTY_DIR_SIZE_V1 : EMPTY_DIR_SIZE,
dentry, inode, &security);
if (retval) {
DEC_DIR_INODE_NLINK(dir)
goto out_failed;
}
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
inode->i_op = &reiserfs_dir_inode_operations;
inode->i_fop = &reiserfs_dir_operations;
/* note, _this_ add_entry will not update dir's stat data */
retval =
reiserfs_add_entry(&th, dir, dentry->d_name.name,
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
clear_nlink(inode);
DEC_DIR_INODE_NLINK(dir);
reiserfs_update_sd(&th, inode);
err = journal_end(&th);
if (err)
retval = err;
unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
/* the above add_entry did not update dir's stat data */
reiserfs_update_sd(&th, dir);
d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(dir->i_sb);
return retval;
}
/*
* reiserfs_ioctl - handler for ioctl for inode
* supported commands:
* 1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
* and prevent packing file (argument arg has to be non-zero)
* 2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
* 3) That's all for a while ...
*/
long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_path.dentry->d_inode;
unsigned int flags;
int err = 0;
reiserfs_write_lock(inode->i_sb);
switch (cmd) {
case REISERFS_IOC_UNPACK:
if (S_ISREG(inode->i_mode)) {
if (arg)
err = reiserfs_unpack(inode, filp);
} else
err = -ENOTTY;
break;
/*
* following two cases are taken from fs/ext2/ioctl.c by Remy
* Card ([email protected])
*/
case REISERFS_IOC_GETFLAGS:
if (!reiserfs_attrs(inode->i_sb)) {
err = -ENOTTY;
break;
}
flags = REISERFS_I(inode)->i_attrs;
i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
err = put_user(flags, (int __user *)arg);
break;
case REISERFS_IOC_SETFLAGS:{
if (!reiserfs_attrs(inode->i_sb)) {
err = -ENOTTY;
break;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
break;
if (!is_owner_or_cap(inode)) {
err = -EPERM;
goto setflags_out;
}
if (get_user(flags, (int __user *)arg)) {
err = -EFAULT;
goto setflags_out;
}
/*
* Is it quota file? Do not allow user to mess with it
*/
if (IS_NOQUOTA(inode)) {
err = -EPERM;
goto setflags_out;
}
if (((flags ^ REISERFS_I(inode)->
i_attrs) & (REISERFS_IMMUTABLE_FL |
REISERFS_APPEND_FL))
&& !capable(CAP_LINUX_IMMUTABLE)) {
err = -EPERM;
goto setflags_out;
}
if ((flags & REISERFS_NOTAIL_FL) &&
S_ISREG(inode->i_mode)) {
int result;
result = reiserfs_unpack(inode, filp);
if (result) {
err = result;
goto setflags_out;
}
}
sd_attrs_to_i_attrs(flags, inode);
REISERFS_I(inode)->i_attrs = flags;
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
setflags_out:
mnt_drop_write(filp->f_path.mnt);
break;
}
case REISERFS_IOC_GETVERSION:
err = put_user(inode->i_generation, (int __user *)arg);
break;
case REISERFS_IOC_SETVERSION:
if (!is_owner_or_cap(inode)) {
err = -EPERM;
break;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
break;
if (get_user(inode->i_generation, (int __user *)arg)) {
err = -EFAULT;
goto setversion_out;
}
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
setversion_out:
mnt_drop_write(filp->f_path.mnt);
break;
default:
err = -ENOTTY;
}
reiserfs_write_unlock(inode->i_sb);
return err;
}
