static struct dentry *fuse_get_dentry(struct super_block *sb, void *vobjp)
{
__u32 *objp = vobjp;
unsigned long nodeid = objp[0];
__u32 generation = objp[1];
struct inode *inode;
struct dentry *entry;
if (nodeid == 0)
return ERR_PTR(-ESTALE);
inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid);
if (!inode)
return ERR_PTR(-ESTALE);
if (inode->i_generation != generation) {
iput(inode);
return ERR_PTR(-ESTALE);
}
entry = d_alloc_anon(inode);
if (!entry) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
return entry;
}
struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
{
unsigned long hash = (unsigned long)no_addr;
struct gfs2_skip_data data;
data.no_addr = no_addr;
data.skipped = 0;
data.non_block = non_block;
return ilookup5(sb, hash, iget_test, &data);
}
struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
{
struct ocfs2_find_inode_args args;
args.fi_blkno = blkno;
args.fi_flags = 0;
args.fi_ino = ino_from_blkno(sb, blkno);
args.fi_sysfile_type = 0;
return ilookup5(sb, blkno, ocfs2_find_actor, &args);
}
static struct dentry *fuse_get_dentry(struct super_block *sb,
struct fuse_inode_handle *handle)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
struct inode *inode;
struct dentry *entry;
int err = -ESTALE;
if (handle->nodeid == 0)
goto out_err;
inode = ilookup5(sb, handle->nodeid, fuse_inode_eq, &handle->nodeid);
if (!inode) {
struct fuse_entry_out outarg;
struct qstr name;
if (!fc->export_support)
goto out_err;
name.len = 1;
name.name = ".";
err = fuse_lookup_name(sb, handle->nodeid, &name, &outarg,
&inode);
if (err && err != -ENOENT)
goto out_err;
if (err || !inode) {
err = -ESTALE;
goto out_err;
}
err = -EIO;
if (get_node_id(inode) != handle->nodeid)
goto out_iput;
}
err = -ESTALE;
if (inode->i_generation != handle->generation)
goto out_iput;
entry = d_obtain_alias(inode);
if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) {
entry->d_op = &fuse_dentry_operations;
fuse_invalidate_entry_cache(entry);
}
return entry;
out_iput:
iput(inode);
out_err:
return ERR_PTR(err);
}
struct inode *search_inode_for_lustre(struct super_block *sb,
const struct lu_fid *fid)
{
struct ll_sb_info *sbi = ll_s2sbi(sb);
struct ptlrpc_request *req = NULL;
struct inode *inode = NULL;
int eadatalen = 0;
unsigned long hash = cl_fid_build_ino(fid,
ll_need_32bit_api(sbi));
struct md_op_data *op_data;
int rc;
CDEBUG(D_INFO, "searching inode for:(%lu,"DFID")\n", hash, PFID(fid));
inode = ilookup5(sb, hash, ll_nfs_test_inode, (void *)fid);
if (inode)
return inode;
rc = ll_get_default_mdsize(sbi, &eadatalen);
if (rc)
return ERR_PTR(rc);
/* Because inode is NULL, ll_prep_md_op_data can not
* be used here. So we allocate op_data ourselves */
op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
if (!op_data)
return ERR_PTR(-ENOMEM);
op_data->op_fid1 = *fid;
op_data->op_mode = eadatalen;
op_data->op_valid = OBD_MD_FLEASIZE;
/* mds_fid2dentry ignores f_type */
rc = md_getattr(sbi->ll_md_exp, op_data, &req);
kfree(op_data);
if (rc) {
CERROR("can't get object attrs, fid "DFID", rc %d\n",
PFID(fid), rc);
return ERR_PTR(rc);
}
rc = ll_prep_inode(&inode, req, sb, NULL);
ptlrpc_req_finished(req);
if (rc)
return ERR_PTR(rc);
return inode;
}
struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
{
struct inode *inode;
unsigned long hash = coda_f2i(fid);
if ( !sb ) {
printk("coda_fid_to_inode: no sb!\n");
return NULL;
}
inode = ilookup5(sb, hash, coda_test_inode, fid);
if ( !inode )
return NULL;
BUG_ON(inode->i_state & I_NEW);
return inode;
}
/* convert a fid to an inode. */
struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
{
struct inode *inode;
unsigned long hash = coda_f2i(fid);
if ( !sb ) {
printk("coda_fid_to_inode: no sb!\n");
return NULL;
}
inode = ilookup5(sb, hash, coda_test_inode, fid);
if ( !inode )
return NULL;
/* we should never see newly created inodes because we intentionally
* fail in the initialization callback */
BUG_ON(inode->i_state & I_NEW);
return inode;
}
int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
loff_t offset, loff_t len)
{
struct inode *inode;
pgoff_t pg_start;
pgoff_t pg_end;
inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid);
if (!inode)
return -ENOENT;
fuse_invalidate_attr(inode);
if (offset >= 0) {
pg_start = offset >> PAGE_CACHE_SHIFT;
if (len <= 0)
pg_end = -1;
else
pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
invalidate_inode_pages2_range(inode->i_mapping,
pg_start, pg_end);
}
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
struct qstr *name)
{
int err = -ENOTDIR;
struct inode *parent;
struct dentry *dir;
struct dentry *entry;
parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid);
if (!parent)
return -ENOENT;
mutex_lock(&parent->i_mutex);
if (!S_ISDIR(parent->i_mode))
goto unlock;
err = -ENOENT;
dir = d_find_alias(parent);
if (!dir)
goto unlock;
entry = d_lookup(dir, name);
dput(dir);
if (!entry)
goto unlock;
fuse_invalidate_attr(parent);
fuse_invalidate_entry(entry);
dput(entry);
err = 0;
unlock:
mutex_unlock(&parent->i_mutex);
iput(parent);
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. */
}
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
u64 child_nodeid, struct qstr *name)
{
int err = -ENOTDIR;
struct inode *parent;
struct dentry *dir;
struct dentry *entry;
parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid);
if (!parent)
return -ENOENT;
mutex_lock(&parent->i_mutex);
if (!S_ISDIR(parent->i_mode))
goto unlock;
err = -ENOENT;
dir = d_find_alias(parent);
if (!dir)
goto unlock;
entry = d_lookup(dir, name);
dput(dir);
if (!entry)
goto unlock;
fuse_invalidate_attr(parent);
fuse_invalidate_entry(entry);
if (child_nodeid != 0 && entry->d_inode) {
mutex_lock(&entry->d_inode->i_mutex);
if (get_node_id(entry->d_inode) != child_nodeid) {
err = -ENOENT;
goto badentry;
}
if (d_mountpoint(entry)) {
err = -EBUSY;
goto badentry;
}
if (S_ISDIR(entry->d_inode->i_mode)) {
shrink_dcache_parent(entry);
if (!simple_empty(entry)) {
err = -ENOTEMPTY;
goto badentry;
}
entry->d_inode->i_flags |= S_DEAD;
}
dont_mount(entry);
clear_nlink(entry->d_inode);
err = 0;
badentry:
mutex_unlock(&entry->d_inode->i_mutex);
if (!err)
d_delete(entry);
} else {
err = 0;
}
dput(entry);
unlock:
mutex_unlock(&parent->i_mutex);
iput(parent);
return err;
}
struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
{
unsigned long hash = (unsigned long)no_addr;
return ilookup5(sb, hash, iget_test, &no_addr);
}
struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino)
{
struct f2fs_iget_args args = {
.ino = ino,
.on_free = 0
};
struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args);
if (inode)
return inode;
if (!args.on_free)
return f2fs_iget(sb, ino);
return ERR_PTR(-ENOENT);
}
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_node *rn;
struct f2fs_inode *ri;
/* Check if ino is within scope */
check_nid_range(sbi, inode->i_ino);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
rn = page_address(node_page);
ri = &(rn->i);
inode->i_mode = le16_to_cpu(ri->i_mode);
i_uid_write(inode, le32_to_cpu(ri->i_uid));
i_gid_write(inode, le32_to_cpu(ri->i_gid));
set_nlink(inode, le32_to_cpu(ri->i_links));
inode->i_size = le64_to_cpu(ri->i_size);
inode->i_blocks = le64_to_cpu(ri->i_blocks);
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
fi->data_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver) - 1;
fi->i_advise = ri->i_advise;
fi->i_pino = le32_to_cpu(ri->i_pino);
get_extent_info(&fi->ext, ri->i_ext);
f2fs_put_page(node_page, 1);
return 0;
}
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
int ret;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
goto make_now;
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
if (!sbi->por_doing && inode->i_nlink == 0) {
ret = -ENOENT;
goto bad_inode;
}
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE |
__GFP_ZERO);
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &f2fs_special_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
} else {
ret = -EIO;
goto bad_inode;
}
unlock_new_inode(inode);
return inode;
bad_inode:
iget_failed(inode);
return ERR_PTR(ret);
}
void update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_node *rn;
struct f2fs_inode *ri;
wait_on_page_writeback(node_page);
rn = page_address(node_page);
ri = &(rn->i);
ri->i_mode = cpu_to_le16(inode->i_mode);
ri->i_advise = F2FS_I(inode)->i_advise;
ri->i_uid = cpu_to_le32(i_uid_read(inode));
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(inode->i_blocks);
set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
set_cold_node(inode, node_page);
set_page_dirty(node_page);
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *node_page;
bool need_lock = false;
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
return 0;
if (wbc)
f2fs_balance_fs(sbi);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
if (!PageDirty(node_page)) {
need_lock = true;
f2fs_put_page(node_page, 1);
mutex_lock(&sbi->write_inode);
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
mutex_unlock(&sbi->write_inode);
return PTR_ERR(node_page);
}
}
update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
if (need_lock)
mutex_unlock(&sbi->write_inode);
return 0;
}
/*
* Called at the last iput() if i_nlink is zero
*/
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
goto no_delete;
BUG_ON(atomic_read(&F2FS_I(inode)->dirty_dents));
remove_dirty_dir_inode(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode);
remove_inode_page(inode);
no_delete:
clear_inode(inode);
}
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
u64 child_nodeid, struct qstr *name)
{
int err = -ENOTDIR;
struct inode *parent;
struct dentry *dir;
struct dentry *entry;
parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid);
if (!parent)
return -ENOENT;
inode_lock(parent);
if (!S_ISDIR(parent->i_mode))
goto unlock;
err = -ENOENT;
dir = d_find_alias(parent);
if (!dir)
goto unlock;
name->hash = full_name_hash(dir, name->name, name->len);
entry = d_lookup(dir, name);
dput(dir);
if (!entry)
goto unlock;
fuse_dir_changed(parent);
fuse_invalidate_entry(entry);
if (child_nodeid != 0 && d_really_is_positive(entry)) {
inode_lock(d_inode(entry));
if (get_node_id(d_inode(entry)) != child_nodeid) {
err = -ENOENT;
goto badentry;
}
if (d_mountpoint(entry)) {
err = -EBUSY;
goto badentry;
}
if (d_is_dir(entry)) {
shrink_dcache_parent(entry);
if (!simple_empty(entry)) {
err = -ENOTEMPTY;
goto badentry;
}
d_inode(entry)->i_flags |= S_DEAD;
}
dont_mount(entry);
clear_nlink(d_inode(entry));
err = 0;
badentry:
inode_unlock(d_inode(entry));
if (!err)
d_delete(entry);
} else {
err = 0;
}
dput(entry);
unlock:
inode_unlock(parent);
iput(parent);
return err;
}
/**
* ntfs_mft_writepage - check if a metadata page contains dirty mft records
* @page: metadata page possibly containing dirty mft records
* @wbc: writeback control structure
*
* This is called from the VM when it wants to have a dirty $MFT/$DATA metadata
* page cache page cleaned. The VM has already locked the page and marked it
* clean. Instead of writing the page as a conventional ->writepage function
* would do, we check if the page still contains any dirty mft records (it must
* have done at some point in the past since the page was marked dirty) and if
* none are found, i.e. all mft records are clean, we unlock the page and
* return. The VM is then free to do with the page as it pleases. If on the
* other hand we do find any dirty mft records in the page, we redirty the page
* before unlocking it and returning so the VM knows that the page is still
* busy and cannot be thrown out.
*
* Note, we do not actually write any dirty mft records here because they are
* dirty inodes and hence will be written by the VFS inode dirty code paths.
* There is no need to write them from the VM page dirty code paths, too and in
* fact once we implement journalling it would be a complete nightmare having
* two code paths leading to mft record writeout.
*/
static int ntfs_mft_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *mft_vi = page->mapping->host;
struct super_block *sb = mft_vi->i_sb;
ntfs_volume *vol = NTFS_SB(sb);
u8 *maddr;
MFT_RECORD *m;
ntfs_inode **extent_nis;
unsigned long mft_no;
int nr, i, j;
BOOL is_dirty = FALSE;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
BUG_ON(mft_vi != vol->mft_ino);
/* The first mft record number in the page. */
mft_no = page->index << (PAGE_CACHE_SHIFT - vol->mft_record_size_bits);
/* Number of mft records in the page. */
nr = PAGE_CACHE_SIZE >> vol->mft_record_size_bits;
BUG_ON(!nr);
ntfs_debug("Entering for %i inodes starting at 0x%lx.", nr, mft_no);
/* Iterate over the mft records in the page looking for a dirty one. */
maddr = (u8*)kmap(page);
for (i = 0; i < nr; ++i, ++mft_no, maddr += vol->mft_record_size) {
struct inode *vi;
ntfs_inode *ni, *eni;
ntfs_attr na;
na.mft_no = mft_no;
na.name = NULL;
na.name_len = 0;
na.type = AT_UNUSED;
/*
* Check if the inode corresponding to this mft record is in
* the VFS inode cache and obtain a reference to it if it is.
*/
ntfs_debug("Looking for inode 0x%lx in icache.", mft_no);
/*
* For inode 0, i.e. $MFT itself, we cannot use ilookup5() from
* here or we deadlock because the inode is already locked by
* the kernel (fs/fs-writeback.c::__sync_single_inode()) and
* ilookup5() waits until the inode is unlocked before
* returning it and it never gets unlocked because
* ntfs_mft_writepage() never returns. )-: Fortunately, we
* have inode 0 pinned in icache for the duration of the mount
* so we can access it directly.
*/
if (!mft_no) {
/* Balance the below iput(). */
vi = igrab(mft_vi);
BUG_ON(vi != mft_vi);
} else
vi = ilookup5(sb, mft_no, (test_t)ntfs_test_inode, &na);
if (vi) {
ntfs_debug("Inode 0x%lx is in icache.", mft_no);
/* The inode is in icache. Check if it is dirty. */
ni = NTFS_I(vi);
if (!NInoDirty(ni)) {
/* The inode is not dirty, skip this record. */
ntfs_debug("Inode 0x%lx is not dirty, "
"continuing search.", mft_no);
iput(vi);
continue;
}
ntfs_debug("Inode 0x%lx is dirty, aborting search.",
mft_no);
/* The inode is dirty, no need to search further. */
iput(vi);
is_dirty = TRUE;
break;
}
ntfs_debug("Inode 0x%lx is not in icache.", mft_no);
/* The inode is not in icache. */
/* Skip the record if it is not a mft record (type "FILE"). */
if (!ntfs_is_mft_recordp(maddr)) {
ntfs_debug("Mft record 0x%lx is not a FILE record, "
"continuing search.", mft_no);
continue;
}
m = (MFT_RECORD*)maddr;
/*
* Skip the mft record if it is not in use. FIXME: What about
* deleted/deallocated (extent) inodes? (AIA)
*/
if (!(m->flags & MFT_RECORD_IN_USE)) {
ntfs_debug("Mft record 0x%lx is not in use, "
"continuing search.", mft_no);
continue;
}
/* Skip the mft record if it is a base inode. */
if (!m->base_mft_record) {
ntfs_debug("Mft record 0x%lx is a base record, "
"continuing search.", mft_no);
continue;
}
/*
* This is an extent mft record. Check if the inode
* corresponding to its base mft record is in icache.
*/
na.mft_no = MREF_LE(m->base_mft_record);
ntfs_debug("Mft record 0x%lx is an extent record. Looking "
"for base inode 0x%lx in icache.", mft_no,
na.mft_no);
vi = ilookup5(sb, na.mft_no, (test_t)ntfs_test_inode,
&na);
if (!vi) {
/*
* The base inode is not in icache. Skip this extent
* mft record.
*/
ntfs_debug("Base inode 0x%lx is not in icache, "
"continuing search.", na.mft_no);
continue;
}
ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no);
/*
* The base inode is in icache. Check if it has the extent
* inode corresponding to this extent mft record attached.
*/
ni = NTFS_I(vi);
down(&ni->extent_lock);
if (ni->nr_extents <= 0) {
/*
* The base inode has no attached extent inodes. Skip
* this extent mft record.
*/
up(&ni->extent_lock);
iput(vi);
continue;
}
/* Iterate over the attached extent inodes. */
extent_nis = ni->ext.extent_ntfs_inos;
for (eni = NULL, j = 0; j < ni->nr_extents; ++j) {
if (mft_no == extent_nis[j]->mft_no) {
/*
* Found the extent inode corresponding to this
* extent mft record.
*/
eni = extent_nis[j];
break;
}
}
/*
* If the extent inode was not attached to the base inode, skip
* this extent mft record.
*/
if (!eni) {
up(&ni->extent_lock);
iput(vi);
continue;
}
/*
* Found the extent inode corrsponding to this extent mft
* record. If it is dirty, no need to search further.
*/
if (NInoDirty(eni)) {
up(&ni->extent_lock);
iput(vi);
is_dirty = TRUE;
break;
}
/* The extent inode is not dirty, so do the next record. */
up(&ni->extent_lock);
iput(vi);
}
kunmap(page);
/* If a dirty mft record was found, redirty the page. */
if (is_dirty) {
ntfs_debug("Inode 0x%lx is dirty. Redirtying the page "
"starting at inode 0x%lx.", mft_no,
page->index << (PAGE_CACHE_SHIFT -
vol->mft_record_size_bits));
redirty_page_for_writepage(wbc, page);
unlock_page(page);
} else {
/*
* Keep the VM happy. This must be done otherwise the
* radix-tree tag PAGECACHE_TAG_DIRTY remains set even though
* the page is clean.
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
}
ntfs_debug("Done.");
return 0;
}
