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);
}
static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
struct buffer_head **out_bh,
void (*init_block)(struct inode *,
struct buffer_head *,
void *))
{
struct the_nilfs *nilfs = NILFS_MDT(inode)->mi_nilfs;
struct super_block *sb = inode->i_sb;
struct nilfs_transaction_info ti;
struct buffer_head *bh;
int err;
if (!sb) {
/*
* Make sure this function is not called from any
* read-only context.
*/
if (!nilfs->ns_writer) {
WARN_ON(1);
err = -EROFS;
goto out;
}
sb = nilfs->ns_writer->s_super;
}
nilfs_transaction_begin(sb, &ti, 0);
err = -ENOMEM;
bh = nilfs_grab_buffer(inode, inode->i_mapping, block, 0);
if (unlikely(!bh))
goto failed_unlock;
err = -EEXIST;
if (buffer_uptodate(bh))
goto failed_bh;
wait_on_buffer(bh);
if (buffer_uptodate(bh))
goto failed_bh;
bh->b_bdev = nilfs->ns_bdev;
err = nilfs_mdt_insert_new_block(inode, block, bh, init_block);
if (likely(!err)) {
get_bh(bh);
*out_bh = bh;
}
failed_bh:
unlock_page(bh->b_page);
page_cache_release(bh->b_page);
brelse(bh);
failed_unlock:
if (likely(!err))
err = nilfs_transaction_commit(sb);
else
nilfs_transaction_abort(sb);
out:
return err;
}
static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = d_inode(old_dentry);
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inode->i_ctime = current_time(inode);
inode_inc_link_count(inode);
ihold(inode);
err = nilfs_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
err = nilfs_transaction_commit(dir->i_sb);
} else {
inode_dec_link_count(inode);
iput(inode);
nilfs_transaction_abort(dir->i_sb);
}
return err;
}
/*
* 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;
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_delete_inode(struct inode *inode)
{
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
if (unlikely(is_bad_inode(inode))) {
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
return;
}
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
nilfs_truncate_bmap(ii, 0);
nilfs_free_inode(inode);
/* nilfs_free_inode() marks inode buffer dirty */
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))) {
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. */
}
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);
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_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
struct nilfs_transaction_info ti;
int err;
if (inode->i_nlink >= NILFS_LINK_MAX)
return -EMLINK;
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
inode->i_ctime = CURRENT_TIME;
inode_inc_link_count(inode);
atomic_inc(&inode->i_count);
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_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_set_file_dirty(NILFS_SB(sb), inode, 0);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But truncate has no return value. */
}
/**
* nilfs_readpages() - implement readpages() method of nilfs_aops {}
* address_space_operations.
* @file - file struct of the file to be read
* @mapping - address_space struct used for reading multiple pages
* @pages - the pages to be read
* @nr_pages - number of pages to be read
*/
static int nilfs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
}
static int nilfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
int err = 0;
#if NEED_WB_SYNC_NONE_CHECK_FOR_DO_SYNC_MAPPING_RANGE
if (wbc->sync_mode == WB_SYNC_ALL ||
(wbc->sync_mode == WB_SYNC_NONE && !current_is_pdflush()))
#else
if (wbc->sync_mode == WB_SYNC_ALL)
#endif
err = nilfs_construct_dsync_segment(inode->i_sb, inode,
wbc->range_start,
wbc->range_end);
return err;
}
static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
int err;
page_debug(3, "called (page=%p, index=%lu, wbc nonblocking %d, "
"wbc for_reclaim %d)\n",
page, page->index, wbc->nonblocking, wbc->for_reclaim);
redirty_page_for_writepage(wbc, page);
unlock_page(page);
if (wbc->sync_mode == WB_SYNC_ALL) {
err = nilfs_construct_segment(inode->i_sb);
if (unlikely(err))
return err;
} else if (wbc->for_reclaim)
nilfs_flush_segment(inode->i_sb, inode->i_ino);
return 0;
}
static int nilfs_set_page_dirty(struct page *page)
{
int ret = __set_page_dirty_buffers(page);
page_debug(3, "called (page=%p)\n", page);
if (ret) {
struct inode *inode = page->mapping->host;
struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
nilfs_set_file_dirty(sbi, inode, nr_dirty);
}
page_debug(3, "done (ret=%d, page=%p)\n", ret, page);
return ret;
}
#if HAVE_WRITE_BEGIN_WRITE_END
static int nilfs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int err = nilfs_transaction_begin(inode->i_sb, NULL, 1);
if (unlikely(err))
return err;
*pagep = NULL;
err = block_write_begin(file, mapping, pos, len, flags, pagep,
fsdata, nilfs_get_block);
if (unlikely(err))
nilfs_transaction_abort(inode->i_sb);
return err;
}
static int nilfs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned nr_dirty;
int err;
nr_dirty = nilfs_page_count_clean_buffers(page, start,
start + copied);
copied = generic_write_end(file, mapping, pos, len, copied, page,
fsdata);
nilfs_set_file_dirty(NILFS_SB(inode->i_sb), inode, nr_dirty);
err = nilfs_transaction_commit(inode->i_sb);
return err ? : copied;
}
#else /* HAVE_WRITE_BEGIN_WRITE_END */
static int nilfs_prepare_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct address_space *mapping = page->mapping;
pgoff_t offset = page->index;
struct inode *inode = mapping->host;
int err;
unlock_page(page);
err = nilfs_transaction_begin(inode->i_sb, NULL, 1);
lock_page(page);
if (unlikely(page->mapping != mapping || page->index != offset)) {
unlock_page(page);
if (likely(!err))
nilfs_transaction_abort(inode->i_sb);
return AOP_TRUNCATED_PAGE;
}
if (unlikely(err))
return err;
err = block_prepare_write(page, from, to, nilfs_get_block);
if (unlikely(err))
nilfs_transaction_abort(inode->i_sb);
return err;
}
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_unlink(dir, dentry);
if (!err) {
inode->i_size = 0;
inode_dec_link_count(inode);
inode_dec_link_count(dir);
}
}
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
}
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_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_dentry->d_inode;
struct nilfs_transaction_info ti;
int ret;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS;
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
return VM_FAULT_NOPAGE;
}
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
if (unlikely(ret))
return VM_FAULT_SIGBUS;
ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret != VM_FAULT_LOCKED) {
nilfs_transaction_abort(inode->i_sb);
return ret;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_on_page_writeback(page);
return VM_FAULT_LOCKED;
}
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;
}
/**
* 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;
}
static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
struct buffer_head **out_bh,
void (*init_block)(struct inode *,
struct buffer_head *,
void *))
{
struct super_block *sb = inode->i_sb;
struct nilfs_transaction_info ti;
struct buffer_head *bh;
int err;
nilfs_transaction_begin(sb, &ti, 0);
err = -ENOMEM;
bh = nilfs_grab_buffer(inode, inode->i_mapping, block, 0);
if (unlikely(!bh))
goto failed_unlock;
err = -EEXIST;
if (buffer_uptodate(bh))
goto failed_bh;
wait_on_buffer(bh);
if (buffer_uptodate(bh))
goto failed_bh;
bh->b_bdev = sb->s_bdev;
err = nilfs_mdt_insert_new_block(inode, block, bh, init_block);
if (likely(!err)) {
get_bh(bh);
*out_bh = bh;
}
failed_bh:
unlock_page(bh->b_page);
page_cache_release(bh->b_page);
brelse(bh);
failed_unlock:
if (likely(!err))
err = nilfs_transaction_commit(sb);
else
nilfs_transaction_abort(sb);
return err;
}
static int nilfs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int err = nilfs_transaction_begin(inode->i_sb, NULL, 1);
if (unlikely(err))
return err;
*pagep = NULL;
err = block_write_begin(file, mapping, pos, len, flags, pagep,
fsdata, nilfs_get_block);
if (unlikely(err))
nilfs_transaction_abort(inode->i_sb);
return err;
}
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);
}
static int nilfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode;
struct nilfs_dir_entry *de;
struct page *page;
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
if (err)
return err;
err = -ENOENT;
de = nilfs_find_entry(dir, dentry, &page);
if (!de)
goto out;
inode = dentry->d_inode;
err = -EIO;
if (le64_to_cpu(de->inode) != inode->i_ino)
goto out;
if (!inode->i_nlink) {
nilfs_warning(inode->i_sb, __func__,
"deleting nonexistent file (%lu), %d\n",
inode->i_ino, inode->i_nlink);
inode->i_nlink = 1;
}
err = nilfs_delete_entry(de, page);
if (err)
goto out;
inode->i_ctime = dir->i_ctime;
inode_dec_link_count(inode);
err = 0;
out:
if (!err)
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, int flags)
{
struct nilfs_transaction_info ti;
struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
if (is_bad_inode(inode)) {
nilfs_msg(inode->i_sb, KERN_WARNING,
"tried to mark bad_inode dirty. ignored.");
dump_stack();
return;
}
if (mdi) {
nilfs_mdt_mark_dirty(inode);
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
__nilfs_mark_inode_dirty(inode, flags);
nilfs_transaction_commit(inode->i_sb); /* never fails */
}
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;
}
int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct nilfs_transaction_info ti;
struct inode *inode = dentry->d_inode;
struct super_block *sb = inode->i_sb;
int err;
err = inode_change_ok(inode, iattr);
if (err)
return err;
err = nilfs_transaction_begin(sb, &ti, 0);
if (unlikely(err))
return err;
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
err = vmtruncate(inode, iattr->ia_size);
if (unlikely(err))
goto out_err;
}
setattr_copy(inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE) {
err = nilfs_acl_chmod(inode);
if (unlikely(err))
goto out_err;
}
return nilfs_transaction_commit(sb);
out_err:
nilfs_transaction_abort(sb);
return err;
}
static int nilfs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int err = nilfs_transaction_begin(inode->i_sb, NULL, 1);
if (unlikely(err))
return err;
err = block_write_begin(mapping, pos, len, flags, pagep,
nilfs_get_block);
if (unlikely(err)) {
loff_t isize = mapping->host->i_size;
if (pos + len > isize)
vmtruncate(mapping->host, isize);
nilfs_transaction_abort(inode->i_sb);
}
return err;
}
int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct nilfs_transaction_info ti;
struct inode *inode = dentry->d_inode;
struct super_block *sb = inode->i_sb;
int err;
err = inode_change_ok(inode, iattr);
if (err)
return err;
err = nilfs_transaction_begin(sb, &ti, 0);
if (unlikely(err))
return err;
err = inode_setattr(inode, iattr);
if (!err && (iattr->ia_valid & ATTR_MODE))
err = nilfs_acl_chmod(inode);
if (likely(!err))
err = nilfs_transaction_commit(sb);
else
nilfs_transaction_abort(sb);
return err;
}
/**
* 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, &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, &new_page);
if (!new_de)
goto out_dir;
inode_inc_link_count(old_inode);
nilfs_set_link(new_dir, new_de, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME;
if (dir_de)
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
if (dir_de) {
err = -EMLINK;
if (new_dir->i_nlink >= NILFS_LINK_MAX)
goto out_dir;
}
inode_inc_link_count(old_inode);
err = nilfs_add_link(new_dentry, old_inode);
if (err) {
inode_dec_link_count(old_inode);
goto out_dir;
}
if (dir_de)
inode_inc_link_count(new_dir);
}
/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
* inode_dec_link_count() will mark the inode dirty.
*/
old_inode->i_ctime = CURRENT_TIME;
nilfs_delete_entry(old_de, old_page);
inode_dec_link_count(old_inode);
if (dir_de) {
nilfs_set_link(old_inode, dir_de, dir_page, new_dir);
inode_dec_link_count(old_dir);
}
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;
}
static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
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;
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
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(new_inode);
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(old_inode);
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);
put_page(dir_page);
}
out_old:
kunmap(old_page);
put_page(old_page);
out:
nilfs_transaction_abort(old_dir->i_sb);
return err;
}
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS; /* -ENOSPC */
sb_start_pagefault(inode->i_sb);
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
ret = -EFAULT; /* make the VM retry the fault */
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
/*
* fill hole blocks
*/
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
/* never returns -ENOMEM, but may return -ENOSPC */
if (unlikely(ret))
goto out;
file_update_time(vma->vm_file);
ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret) {
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}