file.c

/*
 * fs/f2fs/file.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/stat.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/falloc.h>
#include <linux/types.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
#include <linux/uuid.h>
#include <linux/file.h>

#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include "gc.h"
#include "trace.h"
#include <trace/events/f2fs.h>

static int f2fs_vm_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 f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct dnode_of_data dn;
	int err;

	sb_start_pagefault(inode->i_sb);

	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));

	/* block allocation */
	f2fs_lock_op(sbi);
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = f2fs_reserve_block(&dn, page->index);
	if (err) {
		f2fs_unlock_op(sbi);
		goto out;
	}
	f2fs_put_dnode(&dn);
	f2fs_unlock_op(sbi);

	f2fs_balance_fs(sbi, dn.node_changed);

	file_update_time(vma->vm_file);
	lock_page(page);
	if (unlikely(page->mapping != inode->i_mapping ||
			page_offset(page) > i_size_read(inode) ||
			!PageUptodate(page))) {
		unlock_page(page);
		err = -EFAULT;
		goto out;
	}

	/*
	 * check to see if the page is mapped already (no holes)
	 */
	if (PageMappedToDisk(page))
		goto mapped;

	/* page is wholly or partially inside EOF */
	if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
						i_size_read(inode)) {
		unsigned offset;
		offset = i_size_read(inode) & ~PAGE_MASK;
		zero_user_segment(page, offset, PAGE_SIZE);
	}
	set_page_dirty(page);
	if (!PageUptodate(page))
		SetPageUptodate(page);

	trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
	/* fill the page */
	f2fs_wait_on_page_writeback(page, DATA, false);

	/* wait for GCed encrypted page writeback */
	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);

	/* if gced page is attached, don't write to cold segment */
	clear_cold_data(page);
out:
	sb_end_pagefault(inode->i_sb);
	f2fs_update_time(sbi, REQ_TIME);
	return block_page_mkwrite_return(err);
}

static const struct vm_operations_struct f2fs_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= f2fs_vm_page_mkwrite,
};

static int get_parent_ino(struct inode *inode, nid_t *pino)
{
	struct dentry *dentry;

	inode = igrab(inode);
	dentry = d_find_any_alias(inode);
	iput(inode);
	if (!dentry)
		return 0;

	if (update_dent_inode(inode, inode, &dentry->d_name)) {
		dput(dentry);
		return 0;
	}

	*pino = parent_ino(dentry);
	dput(dentry);
	return 1;
}

static inline bool need_do_checkpoint(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	bool need_cp = false;

	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
		need_cp = true;
	else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino))
		need_cp = true;
	else if (file_wrong_pino(inode))
		need_cp = true;
	else if (!space_for_roll_forward(sbi))
		need_cp = true;
	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
		need_cp = true;
	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
		need_cp = true;
	else if (test_opt(sbi, FASTBOOT))
		need_cp = true;
	else if (sbi->active_logs == 2)
		need_cp = true;

	return need_cp;
}

static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
	bool ret = false;
	/* But we need to avoid that there are some inode updates */
	if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
		ret = true;
	f2fs_put_page(i, 0);
	return ret;
}

static void try_to_fix_pino(struct inode *inode)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	nid_t pino;

	down_write(&fi->i_sem);
	fi->xattr_ver = 0;
	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
			get_parent_ino(inode, &pino)) {
		f2fs_i_pino_write(inode, pino);
		file_got_pino(inode);
	}
	up_write(&fi->i_sem);
}

static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
						int datasync, bool atomic)
{
	struct inode *inode = file->f_mapping->host;
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	nid_t ino = inode->i_ino;
	int ret = 0;
	bool need_cp = false;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.for_reclaim = 0,
	};

	if (unlikely(f2fs_readonly(inode->i_sb)))
		return 0;

	trace_f2fs_sync_file_enter(inode);

	/* if fdatasync is triggered, let's do in-place-update */
	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
		set_inode_flag(inode, FI_NEED_IPU);
	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	clear_inode_flag(inode, FI_NEED_IPU);

	if (ret) {
		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
		return ret;
	}

	/* if the inode is dirty, let's recover all the time */
	if (!datasync && !f2fs_skip_inode_update(inode)) {
		f2fs_write_inode(inode, NULL);
		goto go_write;
	}

	/*
	 * if there is no written data, don't waste time to write recovery info.
	 */
	if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
			!exist_written_data(sbi, ino, APPEND_INO)) {

		/* it may call write_inode just prior to fsync */
		if (need_inode_page_update(sbi, ino))
			goto go_write;

		if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
				exist_written_data(sbi, ino, UPDATE_INO))
			goto flush_out;
		goto out;
	}
go_write:
	/*
	 * Both of fdatasync() and fsync() are able to be recovered from
	 * sudden-power-off.
	 */
	down_read(&F2FS_I(inode)->i_sem);
	need_cp = need_do_checkpoint(inode);
	up_read(&F2FS_I(inode)->i_sem);

	if (need_cp) {
		/* all the dirty node pages should be flushed for POR */
		ret = f2fs_sync_fs(inode->i_sb, 1);

		/*
		 * We've secured consistency through sync_fs. Following pino
		 * will be used only for fsynced inodes after checkpoint.
		 */
		try_to_fix_pino(inode);
		clear_inode_flag(inode, FI_APPEND_WRITE);
		clear_inode_flag(inode, FI_UPDATE_WRITE);
		goto out;
	}
sync_nodes:
	ret = fsync_node_pages(sbi, inode, &wbc, atomic);
	if (ret)
		goto out;

	/* if cp_error was enabled, we should avoid infinite loop */
	if (unlikely(f2fs_cp_error(sbi))) {
		ret = -EIO;
		goto out;
	}

	if (need_inode_block_update(sbi, ino)) {
		f2fs_mark_inode_dirty_sync(inode);
		f2fs_write_inode(inode, NULL);
		goto sync_nodes;
	}

	ret = wait_on_node_pages_writeback(sbi, ino);
	if (ret)
		goto out;

	/* once recovery info is written, don't need to tack this */
	remove_ino_entry(sbi, ino, APPEND_INO);
	clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
	remove_ino_entry(sbi, ino, UPDATE_INO);
	clear_inode_flag(inode, FI_UPDATE_WRITE);
	ret = f2fs_issue_flush(sbi);
	f2fs_update_time(sbi, REQ_TIME);
out:
	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
	f2fs_trace_ios(NULL, 1);
	return ret;
}

int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	return f2fs_do_sync_file(file, start, end, datasync, false);
}

static pgoff_t __get_first_dirty_index(struct address_space *mapping,
						pgoff_t pgofs, int whence)
{
	struct pagevec pvec;
	int nr_pages;

	if (whence != SEEK_DATA)
		return 0;

	/* find first dirty page index */
	pagevec_init(&pvec, 0);
	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
					PAGECACHE_TAG_DIRTY, 1);
	pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
	pagevec_release(&pvec);
	return pgofs;
}

static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
							int whence)
{
	switch (whence) {
	case SEEK_DATA:
		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
			return true;
		break;
	case SEEK_HOLE:
		if (blkaddr == NULL_ADDR)
			return true;
		break;
	}
	return false;
}

static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes = inode->i_sb->s_maxbytes;
	struct dnode_of_data dn;
	pgoff_t pgofs, end_offset, dirty;
	loff_t data_ofs = offset;
	loff_t isize;
	int err = 0;

	inode_lock(inode);

	isize = i_size_read(inode);
	if (offset >= isize)
		goto fail;

	/* handle inline data case */
	if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
		if (whence == SEEK_HOLE)
			data_ofs = isize;
		goto found;
	}

	pgofs = (pgoff_t)(offset >> PAGE_SHIFT);

	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);

	for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
		if (err && err != -ENOENT) {
			goto fail;
		} else if (err == -ENOENT) {
			/* direct node does not exists */
			if (whence == SEEK_DATA) {
				pgofs = get_next_page_offset(&dn, pgofs);
				continue;
			} else {
				goto found;
			}
		}

		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);

		/* find data/hole in dnode block */
		for (; dn.ofs_in_node < end_offset;
				dn.ofs_in_node++, pgofs++,
				data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
			block_t blkaddr;
			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
				f2fs_put_dnode(&dn);
				goto found;
			}
		}
		f2fs_put_dnode(&dn);
	}

	if (whence == SEEK_DATA)
		goto fail;
found:
	if (whence == SEEK_HOLE && data_ofs > isize)
		data_ofs = isize;
	inode_unlock(inode);
	return vfs_setpos(file, data_ofs, maxbytes);
fail:
	inode_unlock(inode);
	return -ENXIO;
}

static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes = inode->i_sb->s_maxbytes;

	switch (whence) {
	case SEEK_SET:
	case SEEK_CUR:
	case SEEK_END:
		return generic_file_llseek_size(file, offset, whence,
						maxbytes, i_size_read(inode));
	case SEEK_DATA:
	case SEEK_HOLE:
		if (offset < 0)
			return -ENXIO;
		return f2fs_seek_block(file, offset, whence);
	}

	return -EINVAL;
}

static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file_inode(file);
	int err;

	if (f2fs_encrypted_inode(inode)) {
		err = fscrypt_get_encryption_info(inode);
		if (err)
			return 0;
		if (!f2fs_encrypted_inode(inode))
			return -ENOKEY;
	}

	/* we don't need to use inline_data strictly */
	err = f2fs_convert_inline_inode(inode);
	if (err)
		return err;

	file_accessed(file);
	vma->vm_ops = &f2fs_file_vm_ops;
	return 0;
}

static int f2fs_file_open(struct inode *inode, struct file *filp)
{
	int ret = generic_file_open(inode, filp);
	struct dentry *dir;

	if (!ret && f2fs_encrypted_inode(inode)) {
		ret = fscrypt_get_encryption_info(inode);
		if (ret)
			return -EACCES;
		if (!fscrypt_has_encryption_key(inode))
			return -ENOKEY;
	}
	dir = dget_parent(file_dentry(filp));
	if (f2fs_encrypted_inode(d_inode(dir)) &&
			!fscrypt_has_permitted_context(d_inode(dir), inode)) {
		dput(dir);
		return -EPERM;
	}
	dput(dir);
	return ret;
}

int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
	struct f2fs_node *raw_node;
	int nr_free = 0, ofs = dn->ofs_in_node, len = count;
	__le32 *addr;

	raw_node = F2FS_NODE(dn->node_page);
	addr = blkaddr_in_node(raw_node) + ofs;

	for (; count > 0; count--, addr++, dn->ofs_in_node++) {
		block_t blkaddr = le32_to_cpu(*addr);
		if (blkaddr == NULL_ADDR)
			continue;

		dn->data_blkaddr = NULL_ADDR;
		set_data_blkaddr(dn);
		invalidate_blocks(sbi, blkaddr);
		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
			clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
		nr_free++;
	}

	if (nr_free) {
		pgoff_t fofs;
		/*
		 * once we invalidate valid blkaddr in range [ofs, ofs + count],
		 * we will invalidate all blkaddr in the whole range.
		 */
		fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
							dn->inode) + ofs;
		f2fs_update_extent_cache_range(dn, fofs, 0, len);
		dec_valid_block_count(sbi, dn->inode, nr_free);
	}
	dn->ofs_in_node = ofs;

	f2fs_update_time(sbi, REQ_TIME);
	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
					 dn->ofs_in_node, nr_free);
	return nr_free;
}

void truncate_data_blocks(struct dnode_of_data *dn)
{
	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}

static int truncate_partial_data_page(struct inode *inode, u64 from,
								bool cache_only)
{
	unsigned offset = from & (PAGE_SIZE - 1);
	pgoff_t index = from >> PAGE_SHIFT;
	struct address_space *mapping = inode->i_mapping;
	struct page *page;

	if (!offset && !cache_only)
		return 0;

	if (cache_only) {
		page = f2fs_grab_cache_page(mapping, index, false);
		if (page && PageUptodate(page))
			goto truncate_out;
		f2fs_put_page(page, 1);
		return 0;
	}

	page = get_lock_data_page(inode, index, true);
	if (IS_ERR(page))
		return 0;
truncate_out:
	f2fs_wait_on_page_writeback(page, DATA, true);
	zero_user(page, offset, PAGE_SIZE - offset);
	if (!cache_only || !f2fs_encrypted_inode(inode) ||
					!S_ISREG(inode->i_mode))
		set_page_dirty(page);
	f2fs_put_page(page, 1);
	return 0;
}

int truncate_blocks(struct inode *inode, u64 from, bool lock)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	unsigned int blocksize = inode->i_sb->s_blocksize;
	struct dnode_of_data dn;
	pgoff_t free_from;
	int count = 0, err = 0;
	struct page *ipage;
	bool truncate_page = false;

	trace_f2fs_truncate_blocks_enter(inode, from);

	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);

	if (free_from >= sbi->max_file_blocks)
		goto free_partial;

	if (lock)
		f2fs_lock_op(sbi);

	ipage = get_node_page(sbi, inode->i_ino);
	if (IS_ERR(ipage)) {
		err = PTR_ERR(ipage);
		goto out;
	}

	if (f2fs_has_inline_data(inode)) {
		if (truncate_inline_inode(ipage, from))
			set_page_dirty(ipage);
		f2fs_put_page(ipage, 1);
		truncate_page = true;
		goto out;
	}

	set_new_dnode(&dn, inode, ipage, NULL, 0);
	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
	if (err) {
		if (err == -ENOENT)
			goto free_next;
		goto out;
	}

	count = ADDRS_PER_PAGE(dn.node_page, inode);

	count -= dn.ofs_in_node;
	f2fs_bug_on(sbi, count < 0);

	if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
		truncate_data_blocks_range(&dn, count);
		free_from += count;
	}

	f2fs_put_dnode(&dn);
free_next:
	err = truncate_inode_blocks(inode, free_from);
out:
	if (lock)
		f2fs_unlock_op(sbi);
free_partial:
	/* lastly zero out the first data page */
	if (!err)
		err = truncate_partial_data_page(inode, from, truncate_page);

	trace_f2fs_truncate_blocks_exit(inode, err);
	return err;
}

int f2fs_truncate(struct inode *inode)
{
	int err;

	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
				S_ISLNK(inode->i_mode)))
		return 0;

	trace_f2fs_truncate(inode);

	/* we should check inline_data size */
	if (!f2fs_may_inline_data(inode)) {
		err = f2fs_convert_inline_inode(inode);
		if (err)
			return err;
	}

	err = truncate_blocks(inode, i_size_read(inode), true);
	if (err)
		return err;

	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	f2fs_mark_inode_dirty_sync(inode);
	return 0;
}

int f2fs_getattr(struct vfsmount *mnt,
			 struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = d_inode(dentry);
	generic_fillattr(inode, stat);
	stat->blocks <<= 3;
	return 0;
}

#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct inode *inode, const struct iattr *attr)
{
	unsigned int ia_valid = attr->ia_valid;

	if (ia_valid & ATTR_UID)
		inode->i_uid = attr->ia_uid;
	if (ia_valid & ATTR_GID)
		inode->i_gid = attr->ia_gid;
	if (ia_valid & ATTR_ATIME)
		inode->i_atime = timespec_trunc(attr->ia_atime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_MTIME)
		inode->i_mtime = timespec_trunc(attr->ia_mtime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_CTIME)
		inode->i_ctime = timespec_trunc(attr->ia_ctime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_MODE) {
		umode_t mode = attr->ia_mode;

		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
			mode &= ~S_ISGID;
		set_acl_inode(inode, mode);
	}
}
#else
#define __setattr_copy setattr_copy
#endif

int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	int err;

	err = setattr_prepare(dentry, attr);
	if (err)
		return err;

	if (attr->ia_valid & ATTR_SIZE) {
		if (f2fs_encrypted_inode(inode) &&
				fscrypt_get_encryption_info(inode))
			return -EACCES;

		if (attr->ia_size <= i_size_read(inode)) {
			truncate_setsize(inode, attr->ia_size);
			err = f2fs_truncate(inode);
			if (err)
				return err;
			f2fs_balance_fs(F2FS_I_SB(inode), true);
		} else {
			/*
			 * do not trim all blocks after i_size if target size is
			 * larger than i_size.
			 */
			truncate_setsize(inode, attr->ia_size);

			/* should convert inline inode here */
			if (!f2fs_may_inline_data(inode)) {
				err = f2fs_convert_inline_inode(inode);
				if (err)
					return err;
			}
			inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		}
	}

	__setattr_copy(inode, attr);

	if (attr->ia_valid & ATTR_MODE) {
		err = posix_acl_chmod(inode, get_inode_mode(inode));
		if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
			inode->i_mode = F2FS_I(inode)->i_acl_mode;
			clear_inode_flag(inode, FI_ACL_MODE);
		}
	}

	f2fs_mark_inode_dirty_sync(inode);
	return err;
}

const struct inode_operations f2fs_file_inode_operations = {
	.getattr	= f2fs_getattr,
	.setattr	= f2fs_setattr,
	.get_acl	= f2fs_get_acl,
	.set_acl	= f2fs_set_acl,
#ifdef CONFIG_F2FS_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= f2fs_listxattr,
	.removexattr	= generic_removexattr,
#endif
	.fiemap		= f2fs_fiemap,
};

static int fill_zero(struct inode *inode, pgoff_t index,
					loff_t start, loff_t len)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct page *page;

	if (!len)
		return 0;

	f2fs_balance_fs(sbi, true);

	f2fs_lock_op(sbi);
	page = get_new_data_page(inode, NULL, index, false);
	f2fs_unlock_op(sbi);

	if (IS_ERR(page))
		return PTR_ERR(page);

	f2fs_wait_on_page_writeback(page, DATA, true);
	zero_user(page, start, len);
	set_page_dirty(page);
	f2fs_put_page(page, 1);
	return 0;
}

int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
	int err;

	while (pg_start < pg_end) {
		struct dnode_of_data dn;
		pgoff_t end_offset, count;

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
		if (err) {
			if (err == -ENOENT) {
				pg_start++;
				continue;
			}
			return err;
		}

		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);

		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);

		truncate_data_blocks_range(&dn, count);
		f2fs_put_dnode(&dn);

		pg_start += count;
	}
	return 0;
}

static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	pgoff_t pg_start, pg_end;
	loff_t off_start, off_end;
	int ret;

	ret = f2fs_convert_inline_inode(inode);
	if (ret)
		return ret;

	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;

	off_start = offset & (PAGE_SIZE - 1);
	off_end = (offset + len) & (PAGE_SIZE - 1);

	if (pg_start == pg_end) {
		ret = fill_zero(inode, pg_start, off_start,
						off_end - off_start);
		if (ret)
			return ret;
	} else {
		if (off_start) {
			ret = fill_zero(inode, pg_start++, off_start,
						PAGE_SIZE - off_start);
			if (ret)
				return ret;
		}
		if (off_end) {
			ret = fill_zero(inode, pg_end, 0, off_end);
			if (ret)
				return ret;
		}

		if (pg_start < pg_end) {
			struct address_space *mapping = inode->i_mapping;
			loff_t blk_start, blk_end;
			struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

			f2fs_balance_fs(sbi, true);

			blk_start = (loff_t)pg_start << PAGE_SHIFT;
			blk_end = (loff_t)pg_end << PAGE_SHIFT;
			truncate_inode_pages_range(mapping, blk_start,
					blk_end - 1);

			f2fs_lock_op(sbi);
			ret = truncate_hole(inode, pg_start, pg_end);
			f2fs_unlock_op(sbi);
		}
	}

	return ret;
}

static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
				int *do_replace, pgoff_t off, pgoff_t len)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct dnode_of_data dn;
	int ret, done, i;

next_dnode:
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
	if (ret && ret != -ENOENT) {
		return ret;
	} else if (ret == -ENOENT) {
		if (dn.max_level == 0)
			return -ENOENT;
		done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len);
		blkaddr += done;
		do_replace += done;
		goto next;
	}

	done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
							dn.ofs_in_node, len);
	for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
		*blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
		if (!is_checkpointed_data(sbi, *blkaddr)) {

			if (test_opt(sbi, LFS)) {
				f2fs_put_dnode(&dn);
				return -ENOTSUPP;
			}

			/* do not invalidate this block address */
			f2fs_update_data_blkaddr(&dn, NULL_ADDR);
			*do_replace = 1;
		}
	}
	f2fs_put_dnode(&dn);
next:
	len -= done;
	off += done;
	if (len)
		goto next_dnode;
	return 0;
}

static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
				int *do_replace, pgoff_t off, int len)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct dnode_of_data dn;
	int ret, i;

	for (i = 0; i < len; i++, do_replace++, blkaddr++) {
		if (*do_replace == 0)
			continue;

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
		if (ret) {
			dec_valid_block_count(sbi, inode, 1);
			invalidate_blocks(sbi, *blkaddr);
		} else {
			f2fs_update_data_blkaddr(&dn, *blkaddr);
		}
		f2fs_put_dnode(&dn);
	}
	return 0;
}

static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
			block_t *blkaddr, int *do_replace,
			pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
	pgoff_t i = 0;
	int ret;

	while (i < len) {
		if (blkaddr[i] == NULL_ADDR && !full) {
			i++;
			continue;
		}

		if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
			struct dnode_of_data dn;
			struct node_info ni;
			size_t new_size;
			pgoff_t ilen;

			set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
			ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
			if (ret)
				return ret;

			get_node_info(sbi, dn.nid, &ni);
			ilen = min((pgoff_t)
				ADDRS_PER_PAGE(dn.node_page, dst_inode) -
						dn.ofs_in_node, len - i);
			do {
				dn.data_blkaddr = datablock_addr(dn.node_page,
								dn.ofs_in_node);
				truncate_data_blocks_range(&dn, 1);

				if (do_replace[i]) {
					f2fs_i_blocks_write(src_inode,
								1, false);
					f2fs_i_blocks_write(dst_inode,
								1, true);
					f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
					blkaddr[i], ni.version, true, false);

					do_replace[i] = 0;
				}
				dn.ofs_in_node++;
				i++;
				new_size = (dst + i) << PAGE_SHIFT;
				if (dst_inode->i_size < new_size)
					f2fs_i_size_write(dst_inode, new_size);
			} while ((do_replace[i] || blkaddr[i] == NULL_ADDR) && --ilen);

			f2fs_put_dnode(&dn);
		} else {
			struct page *psrc, *pdst;

			psrc = get_lock_data_page(src_inode, src + i, true);
			if (IS_ERR(psrc))
				return PTR_ERR(psrc);
			pdst = get_new_data_page(dst_inode, NULL, dst + i,
								true);
			if (IS_ERR(pdst)) {
				f2fs_put_page(psrc, 1);
				return PTR_ERR(pdst);
			}
			f2fs_copy_page(psrc, pdst);
			set_page_dirty(pdst);
			f2fs_put_page(pdst, 1);
			f2fs_put_page(psrc, 1);

			ret = truncate_hole(src_inode, src + i, src + i + 1);
			if (ret)
				return ret;
			i++;
		}
	}
	return 0;
}

static int __exchange_data_block(struct inode *src_inode,
			struct inode *dst_inode, pgoff_t src, pgoff_t dst,
			pgoff_t len, bool full)
{
	block_t *src_blkaddr;
	int *do_replace;
	pgoff_t olen;
	int ret;

	while (len) {
		olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);

		src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
		if (!src_blkaddr)
			return -ENOMEM;

		do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
		if (!do_replace) {
			kvfree(src_blkaddr);
			return -ENOMEM;
		}

		ret = __read_out_blkaddrs(src_inode, src_blkaddr,
					do_replace, src, olen);
		if (ret)
			goto roll_back;

		ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
					do_replace, src, dst, olen, full);
		if (ret)
			goto roll_back;

		src += olen;
		dst += olen;
		len -= olen;

		kvfree(src_blkaddr);
		kvfree(do_replace);
	}
	return 0;

roll_back:
	__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
	kvfree(src_blkaddr);
	kvfree(do_replace);
	return ret;
}