[mirror_ubuntu-bionic-kernel.git] / fs / f2fs / 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 "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.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_SB(inode->i_sb);
	block_t old_blk_addr;
	struct dnode_of_data dn;
	int err;

	f2fs_balance_fs(sbi);

	sb_start_pagefault(inode->i_sb);

	mutex_lock_op(sbi, DATA_NEW);

	/* block allocation */
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
	if (err) {
		mutex_unlock_op(sbi, DATA_NEW);
		goto out;
	}

	old_blk_addr = dn.data_blkaddr;

	if (old_blk_addr == NULL_ADDR) {
		err = reserve_new_block(&dn);
		if (err) {
			f2fs_put_dnode(&dn);
			mutex_unlock_op(sbi, DATA_NEW);
			goto out;
		}
	}
	f2fs_put_dnode(&dn);

	mutex_unlock_op(sbi, DATA_NEW);

	lock_page(page);
	if (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 out;

	/* fill the page */
	wait_on_page_writeback(page);

	/* page is wholly or partially inside EOF */
	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
		unsigned offset;
		offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	}
	set_page_dirty(page);
	SetPageUptodate(page);

	file_update_time(vma->vm_file);
out:
	sb_end_pagefault(inode->i_sb);
	return block_page_mkwrite_return(err);
}

static const struct vm_operations_struct f2fs_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite	= f2fs_vm_page_mkwrite,
	.remap_pages	= generic_file_remap_pages,
};

static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
{
	struct dentry *dentry;
	nid_t pino;

	inode = igrab(inode);
	dentry = d_find_any_alias(inode);
	if (!dentry) {
		iput(inode);
		return 0;
	}
	pino = dentry->d_parent->d_inode->i_ino;
	dput(dentry);
	iput(inode);
	return !is_checkpointed_node(sbi, pino);
}

int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	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 (inode->i_sb->s_flags & MS_RDONLY)
		return 0;

	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (ret)
		return ret;

	/* guarantee free sections for fsync */
	f2fs_balance_fs(sbi);

	mutex_lock(&inode->i_mutex);

	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
		goto out;

	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
		need_cp = true;
	else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
		need_cp = true;
	else if (!space_for_roll_forward(sbi))
		need_cp = true;
	else if (need_to_sync_dir(sbi, inode))
		need_cp = true;

	if (need_cp) {
		/* all the dirty node pages should be flushed for POR */
		ret = f2fs_sync_fs(inode->i_sb, 1);
		clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
	} else {
		/* if there is no written node page, write its inode page */
		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
			ret = f2fs_write_inode(inode, NULL);
			if (ret)
				goto out;
		}
		filemap_fdatawait_range(sbi->node_inode->i_mapping,
							0, LONG_MAX);
		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
	}
out:
	mutex_unlock(&inode->i_mutex);
	return ret;
}

static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	file_accessed(file);
	vma->vm_ops = &f2fs_file_vm_ops;
	return 0;
}

static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
	int nr_free = 0, ofs = dn->ofs_in_node;
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct f2fs_node *raw_node;
	__le32 *addr;

	raw_node = page_address(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;

		update_extent_cache(NULL_ADDR, dn);
		invalidate_blocks(sbi, blkaddr);
		dec_valid_block_count(sbi, dn->inode, 1);
		nr_free++;
	}
	if (nr_free) {
		set_page_dirty(dn->node_page);
		sync_inode_page(dn);
	}
	dn->ofs_in_node = ofs;
	return nr_free;
}

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

static void truncate_partial_data_page(struct inode *inode, u64 from)
{
	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
	struct page *page;

	if (!offset)
		return;

	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT);
	if (IS_ERR(page))
		return;

	lock_page(page);
	wait_on_page_writeback(page);
	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
	set_page_dirty(page);
	f2fs_put_page(page, 1);
}

static int truncate_blocks(struct inode *inode, u64 from)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	unsigned int blocksize = inode->i_sb->s_blocksize;
	struct dnode_of_data dn;
	pgoff_t free_from;
	int count = 0;
	int err;

	free_from = (pgoff_t)
			((from + blocksize - 1) >> (sbi->log_blocksize));

	mutex_lock_op(sbi, DATA_TRUNC);

	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
	if (err) {
		if (err == -ENOENT)
			goto free_next;
		mutex_unlock_op(sbi, DATA_TRUNC);
		return err;
	}

	if (IS_INODE(dn.node_page))
		count = ADDRS_PER_INODE;
	else
		count = ADDRS_PER_BLOCK;

	count -= dn.ofs_in_node;
	BUG_ON(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);
	mutex_unlock_op(sbi, DATA_TRUNC);

	/* lastly zero out the first data page */
	truncate_partial_data_page(inode, from);

	return err;
}

void f2fs_truncate(struct inode *inode)
{
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
				S_ISLNK(inode->i_mode)))
		return;

	if (!truncate_blocks(inode, i_size_read(inode))) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty(inode);
	}
}

static int f2fs_getattr(struct vfsmount *mnt,
			 struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	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)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	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(fi, mode);
	}
}
#else
#define __setattr_copy setattr_copy
#endif

int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct f2fs_inode_info *fi = F2FS_I(inode);
	int err;

	err = inode_change_ok(inode, attr);
	if (err)
		return err;

	if ((attr->ia_valid & ATTR_SIZE) &&
			attr->ia_size != i_size_read(inode)) {
		truncate_setsize(inode, attr->ia_size);
		f2fs_truncate(inode);
		f2fs_balance_fs(F2FS_SB(inode->i_sb));
	}

	__setattr_copy(inode, attr);

	if (attr->ia_valid & ATTR_MODE) {
		err = f2fs_acl_chmod(inode);
		if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
			inode->i_mode = fi->i_acl_mode;
			clear_inode_flag(fi, FI_ACL_MODE);
		}
	}

	mark_inode_dirty(inode);
	return err;
}

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

static void fill_zero(struct inode *inode, pgoff_t index,
					loff_t start, loff_t len)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct page *page;

	if (!len)
		return;

	f2fs_balance_fs(sbi);

	mutex_lock_op(sbi, DATA_NEW);
	page = get_new_data_page(inode, index, false);
	mutex_unlock_op(sbi, DATA_NEW);

	if (!IS_ERR(page)) {
		wait_on_page_writeback(page);
		zero_user(page, start, len);
		set_page_dirty(page);
		f2fs_put_page(page, 1);
	}
}

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

	for (index = pg_start; index < pg_end; index++) {
		struct dnode_of_data dn;
		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);

		f2fs_balance_fs(sbi);

		mutex_lock_op(sbi, DATA_TRUNC);
		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
		if (err) {
			mutex_unlock_op(sbi, DATA_TRUNC);
			if (err == -ENOENT)
				continue;
			return err;
		}

		if (dn.data_blkaddr != NULL_ADDR)
			truncate_data_blocks_range(&dn, 1);
		f2fs_put_dnode(&dn);
		mutex_unlock_op(sbi, DATA_TRUNC);
	}
	return 0;
}

static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
{
	pgoff_t pg_start, pg_end;
	loff_t off_start, off_end;
	int ret = 0;

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

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

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

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

			blk_start = pg_start << PAGE_CACHE_SHIFT;
			blk_end = pg_end << PAGE_CACHE_SHIFT;
			truncate_inode_pages_range(mapping, blk_start,
					blk_end - 1);
			ret = truncate_hole(inode, pg_start, pg_end);
		}
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		i_size_read(inode) <= (offset + len)) {
		i_size_write(inode, offset);
		mark_inode_dirty(inode);
	}

	return ret;
}

static int expand_inode_data(struct inode *inode, loff_t offset,
					loff_t len, int mode)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	pgoff_t index, pg_start, pg_end;
	loff_t new_size = i_size_read(inode);
	loff_t off_start, off_end;
	int ret = 0;

	ret = inode_newsize_ok(inode, (len + offset));
	if (ret)
		return ret;

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

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

	for (index = pg_start; index <= pg_end; index++) {
		struct dnode_of_data dn;

		mutex_lock_op(sbi, DATA_NEW);

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
		if (ret) {
			mutex_unlock_op(sbi, DATA_NEW);
			break;
		}

		if (dn.data_blkaddr == NULL_ADDR) {
			ret = reserve_new_block(&dn);
			if (ret) {
				f2fs_put_dnode(&dn);
				mutex_unlock_op(sbi, DATA_NEW);
				break;
			}
		}
		f2fs_put_dnode(&dn);

		mutex_unlock_op(sbi, DATA_NEW);

		if (pg_start == pg_end)
			new_size = offset + len;
		else if (index == pg_start && off_start)
			new_size = (index + 1) << PAGE_CACHE_SHIFT;
		else if (index == pg_end)
			new_size = (index << PAGE_CACHE_SHIFT) + off_end;
		else
			new_size += PAGE_CACHE_SIZE;
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		i_size_read(inode) < new_size) {
		i_size_write(inode, new_size);
		mark_inode_dirty(inode);
	}

	return ret;
}

static long f2fs_fallocate(struct file *file, int mode,
				loff_t offset, loff_t len)
{
	struct inode *inode = file_inode(file);
	long ret;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	if (mode & FALLOC_FL_PUNCH_HOLE)
		ret = punch_hole(inode, offset, len, mode);
	else
		ret = expand_inode_data(inode, offset, len, mode);

	if (!ret) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty(inode);
	}
	return ret;
}

#define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
#define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)

static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & F2FS_REG_FLMASK;
	else
		return flags & F2FS_OTHER_FLMASK;
}

long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	struct inode *inode = file_inode(filp);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	unsigned int flags;
	int ret;

	switch (cmd) {
	case FS_IOC_GETFLAGS:
		flags = fi->i_flags & FS_FL_USER_VISIBLE;
		return put_user(flags, (int __user *) arg);
	case FS_IOC_SETFLAGS:
	{
		unsigned int oldflags;

		ret = mnt_want_write(filp->f_path.mnt);
		if (ret)
			return ret;

		if (!inode_owner_or_capable(inode)) {
			ret = -EACCES;
			goto out;
		}

		if (get_user(flags, (int __user *) arg)) {
			ret = -EFAULT;
			goto out;
		}

		flags = f2fs_mask_flags(inode->i_mode, flags);

		mutex_lock(&inode->i_mutex);

		oldflags = fi->i_flags;

		if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
			if (!capable(CAP_LINUX_IMMUTABLE)) {
				mutex_unlock(&inode->i_mutex);
				ret = -EPERM;
				goto out;
			}
		}

		flags = flags & FS_FL_USER_MODIFIABLE;
		flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
		fi->i_flags = flags;
		mutex_unlock(&inode->i_mutex);

		f2fs_set_inode_flags(inode);
		inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty(inode);
out:
		mnt_drop_write(filp->f_path.mnt);
		return ret;
	}
	default:
		return -ENOTTY;
	}
}

#ifdef CONFIG_COMPAT
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case F2FS_IOC32_GETFLAGS:
		cmd = F2FS_IOC_GETFLAGS;
		break;
	case F2FS_IOC32_SETFLAGS:
		cmd = F2FS_IOC_SETFLAGS;
		break;
	default:
		return -ENOIOCTLCMD;
	}
	return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif

const struct file_operations f2fs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= generic_file_aio_read,
	.aio_write	= generic_file_aio_write,
	.open		= generic_file_open,
	.mmap		= f2fs_file_mmap,
	.fsync		= f2fs_sync_file,
	.fallocate	= f2fs_fallocate,
	.unlocked_ioctl	= f2fs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= f2fs_compat_ioctl,
#endif
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
};
Commit	Line	Data
0a8165d7	1	/*
fbfa2cc5 JK	2	* fs/f2fs/file.c
	3	*
	4	* Copyright (c) 2012 Samsung Electronics Co., Ltd.
	5	* http://www.samsung.com/
	6	*
	7	* This program is free software; you can redistribute it and/or modify
	8	* it under the terms of the GNU General Public License version 2 as
	9	* published by the Free Software Foundation.
	10	*/
	11	#include <linux/fs.h>
	12	#include <linux/f2fs_fs.h>
	13	#include <linux/stat.h>
	14	#include <linux/buffer_head.h>
	15	#include <linux/writeback.h>
ae51fb31	16	#include <linux/blkdev.h>
fbfa2cc5 JK	17	#include <linux/falloc.h>
fbfa2cc5 JK	18	#include <linux/types.h>
e9750824	19	#include <linux/compat.h>
fbfa2cc5 JK	20	#include <linux/uaccess.h>
	21	#include <linux/mount.h>
	22
	23	#include "f2fs.h"
	24	#include "node.h"
	25	#include "segment.h"
	26	#include "xattr.h"
	27	#include "acl.h"
	28
	29	static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
	30	struct vm_fault *vmf)
	31	{
	32	struct page *page = vmf->page;
6131ffaa	33	struct inode *inode = file_inode(vma->vm_file);
fbfa2cc5	34	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
fbfa2cc5 JK	35	block_t old_blk_addr;
	36	struct dnode_of_data dn;
	37	int err;
	38
	39	f2fs_balance_fs(sbi);
	40
	41	sb_start_pagefault(inode->i_sb);
	42
	43	mutex_lock_op(sbi, DATA_NEW);
	44
	45	/* block allocation */
	46	set_new_dnode(&dn, inode, NULL, NULL, 0);
266e97a8	47	err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
fbfa2cc5 JK	48	if (err) {
	49	mutex_unlock_op(sbi, DATA_NEW);
	50	goto out;
	51	}
	52
	53	old_blk_addr = dn.data_blkaddr;
fbfa2cc5 JK	54
	55	if (old_blk_addr == NULL_ADDR) {
	56	err = reserve_new_block(&dn);
	57	if (err) {
	58	f2fs_put_dnode(&dn);
	59	mutex_unlock_op(sbi, DATA_NEW);
	60	goto out;
	61	}
	62	}
	63	f2fs_put_dnode(&dn);
	64
	65	mutex_unlock_op(sbi, DATA_NEW);
	66
	67	lock_page(page);
	68	if (page->mapping != inode->i_mapping \|\|
	69	page_offset(page) >= i_size_read(inode) \|\|
	70	!PageUptodate(page)) {
	71	unlock_page(page);
	72	err = -EFAULT;
	73	goto out;
	74	}
	75
	76	/*
	77	* check to see if the page is mapped already (no holes)
	78	*/
	79	if (PageMappedToDisk(page))
	80	goto out;
	81
	82	/* fill the page */
	83	wait_on_page_writeback(page);
	84
	85	/* page is wholly or partially inside EOF */
	86	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
	87	unsigned offset;
	88	offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
	89	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	90	}
	91	set_page_dirty(page);
	92	SetPageUptodate(page);
	93
	94	file_update_time(vma->vm_file);
	95	out:
	96	sb_end_pagefault(inode->i_sb);
	97	return block_page_mkwrite_return(err);
	98	}
	99
	100	static const struct vm_operations_struct f2fs_file_vm_ops = {
692bb55d JK	101	.fault = filemap_fault,
	102	.page_mkwrite = f2fs_vm_page_mkwrite,
	103	.remap_pages = generic_file_remap_pages,
fbfa2cc5 JK	104	};
	105
	106	static int need_to_sync_dir(struct f2fs_sb_info sbi, struct inode inode)
	107	{
	108	struct dentry *dentry;
	109	nid_t pino;
	110
	111	inode = igrab(inode);
	112	dentry = d_find_any_alias(inode);
	113	if (!dentry) {
	114	iput(inode);
	115	return 0;
	116	}
	117	pino = dentry->d_parent->d_inode->i_ino;
	118	dput(dentry);
	119	iput(inode);
	120	return !is_checkpointed_node(sbi, pino);
	121	}
	122
	123	int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
	124	{
	125	struct inode *inode = file->f_mapping->host;
	126	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
fbfa2cc5 JK	127	int ret = 0;
	128	bool need_cp = false;
	129	struct writeback_control wbc = {
	130	.sync_mode = WB_SYNC_ALL,
	131	.nr_to_write = LONG_MAX,
	132	.for_reclaim = 0,
	133	};
	134
1fa95b0b NJ	135	if (inode->i_sb->s_flags & MS_RDONLY)
	136	return 0;
	137
fbfa2cc5 JK	138	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	139	if (ret)
	140	return ret;
	141
7d82db83 JK	142	/* guarantee free sections for fsync */
	143	f2fs_balance_fs(sbi);
	144
fbfa2cc5 JK	145	mutex_lock(&inode->i_mutex);
fbfa2cc5 JK	146
fbfa2cc5 JK	147	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
	148	goto out;
	149
fbfa2cc5 JK	150	if (!S_ISREG(inode->i_mode) \|\| inode->i_nlink != 1)
fbfa2cc5 JK	151	need_cp = true;
facb0205	152	else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
fbfa2cc5	153	need_cp = true;
facb0205	154	else if (!space_for_roll_forward(sbi))
fbfa2cc5	155	need_cp = true;
facb0205	156	else if (need_to_sync_dir(sbi, inode))
fbfa2cc5 JK	157	need_cp = true;
fbfa2cc5 JK	158
fbfa2cc5 JK	159	if (need_cp) {
	160	/* all the dirty node pages should be flushed for POR */
	161	ret = f2fs_sync_fs(inode->i_sb, 1);
	162	clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
	163	} else {
398b1ac5 JK	164	/* if there is no written node page, write its inode page */
	165	while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
	166	ret = f2fs_write_inode(inode, NULL);
	167	if (ret)
	168	goto out;
	169	}
fbfa2cc5 JK	170	filemap_fdatawait_range(sbi->node_inode->i_mapping,
fbfa2cc5 JK	171	0, LONG_MAX);
ae51fb31	172	ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
fbfa2cc5 JK	173	}
	174	out:
	175	mutex_unlock(&inode->i_mutex);
	176	return ret;
	177	}
	178
	179	static int f2fs_file_mmap(struct file file, struct vm_area_struct vma)
	180	{
	181	file_accessed(file);
	182	vma->vm_ops = &f2fs_file_vm_ops;
	183	return 0;
	184	}
	185
	186	static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
	187	{
	188	int nr_free = 0, ofs = dn->ofs_in_node;
	189	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	190	struct f2fs_node *raw_node;
	191	__le32 *addr;
	192
	193	raw_node = page_address(dn->node_page);
	194	addr = blkaddr_in_node(raw_node) + ofs;
	195
	196	for ( ; count > 0; count--, addr++, dn->ofs_in_node++) {
	197	block_t blkaddr = le32_to_cpu(*addr);
	198	if (blkaddr == NULL_ADDR)
	199	continue;
	200
	201	update_extent_cache(NULL_ADDR, dn);
	202	invalidate_blocks(sbi, blkaddr);
	203	dec_valid_block_count(sbi, dn->inode, 1);
	204	nr_free++;
	205	}
	206	if (nr_free) {
	207	set_page_dirty(dn->node_page);
	208	sync_inode_page(dn);
	209	}
	210	dn->ofs_in_node = ofs;
	211	return nr_free;
	212	}
	213
	214	void truncate_data_blocks(struct dnode_of_data *dn)
	215	{
	216	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
	217	}
	218
	219	static void truncate_partial_data_page(struct inode *inode, u64 from)
	220	{
	221	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
	222	struct page *page;
	223
	224	if (!offset)
	225	return;
	226
	227	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT);
	228	if (IS_ERR(page))
	229	return;
	230
	231	lock_page(page);
	232	wait_on_page_writeback(page);
	233	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
	234	set_page_dirty(page);
	235	f2fs_put_page(page, 1);
	236	}
237
238	static int truncate_blocks(struct inode *inode, u64 from)
239	{
240	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
241	unsigned int blocksize = inode->i_sb->s_blocksize;
242	struct dnode_of_data dn;
243	pgoff_t free_from;
244	int count = 0;
245	int err;
246
247	free_from = (pgoff_t)
248	((from + blocksize - 1) >> (sbi->log_blocksize));
249
250	mutex_lock_op(sbi, DATA_TRUNC);
251
252	set_new_dnode(&dn, inode, NULL, NULL, 0);
266e97a8	253	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
fbfa2cc5 JK	254	if (err) {
	255	if (err == -ENOENT)
	256	goto free_next;
	257	mutex_unlock_op(sbi, DATA_TRUNC);
	258	return err;
	259	}
	260
	261	if (IS_INODE(dn.node_page))
	262	count = ADDRS_PER_INODE;
	263	else
	264	count = ADDRS_PER_BLOCK;
	265
	266	count -= dn.ofs_in_node;
	267	BUG_ON(count < 0);
	268	if (dn.ofs_in_node \|\| IS_INODE(dn.node_page)) {
	269	truncate_data_blocks_range(&dn, count);
	270	free_from += count;
	271	}
	272
	273	f2fs_put_dnode(&dn);
	274	free_next:
	275	err = truncate_inode_blocks(inode, free_from);
	276	mutex_unlock_op(sbi, DATA_TRUNC);
	277
	278	/* lastly zero out the first data page */
	279	truncate_partial_data_page(inode, from);
	280
	281	return err;
	282	}
	283
	284	void f2fs_truncate(struct inode *inode)
	285	{
	286	if (!(S_ISREG(inode->i_mode) \|\| S_ISDIR(inode->i_mode) \|\|
	287	S_ISLNK(inode->i_mode)))
	288	return;
	289
	290	if (!truncate_blocks(inode, i_size_read(inode))) {
	291	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	292	mark_inode_dirty(inode);
	293	}
fbfa2cc5 JK	294	}
	295
	296	static int f2fs_getattr(struct vfsmount *mnt,
	297	struct dentry dentry, struct kstat stat)
	298	{
	299	struct inode *inode = dentry->d_inode;
	300	generic_fillattr(inode, stat);
	301	stat->blocks <<= 3;
	302	return 0;
	303	}
	304
	305	#ifdef CONFIG_F2FS_FS_POSIX_ACL
	306	static void __setattr_copy(struct inode inode, const struct iattr attr)
	307	{
	308	struct f2fs_inode_info *fi = F2FS_I(inode);
	309	unsigned int ia_valid = attr->ia_valid;
	310
	311	if (ia_valid & ATTR_UID)
	312	inode->i_uid = attr->ia_uid;
	313	if (ia_valid & ATTR_GID)
	314	inode->i_gid = attr->ia_gid;
	315	if (ia_valid & ATTR_ATIME)
	316	inode->i_atime = timespec_trunc(attr->ia_atime,
	317	inode->i_sb->s_time_gran);
	318	if (ia_valid & ATTR_MTIME)
	319	inode->i_mtime = timespec_trunc(attr->ia_mtime,
	320	inode->i_sb->s_time_gran);
	321	if (ia_valid & ATTR_CTIME)
	322	inode->i_ctime = timespec_trunc(attr->ia_ctime,
	323	inode->i_sb->s_time_gran);
	324	if (ia_valid & ATTR_MODE) {
	325	umode_t mode = attr->ia_mode;
	326
	327	if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
	328	mode &= ~S_ISGID;
	329	set_acl_inode(fi, mode);
	330	}
	331	}
	332	#else
	333	#define __setattr_copy setattr_copy
	334	#endif
	335
	336	int f2fs_setattr(struct dentry dentry, struct iattr attr)
	337	{
	338	struct inode *inode = dentry->d_inode;
	339	struct f2fs_inode_info *fi = F2FS_I(inode);
	340	int err;
	341
	342	err = inode_change_ok(inode, attr);
	343	if (err)
	344	return err;
	345
	346	if ((attr->ia_valid & ATTR_SIZE) &&
	347	attr->ia_size != i_size_read(inode)) {
	348	truncate_setsize(inode, attr->ia_size);
	349	f2fs_truncate(inode);
d4686d56	350	f2fs_balance_fs(F2FS_SB(inode->i_sb));
fbfa2cc5 JK	351	}
	352
	353	__setattr_copy(inode, attr);
	354
	355	if (attr->ia_valid & ATTR_MODE) {
	356	err = f2fs_acl_chmod(inode);
	357	if (err \|\| is_inode_flag_set(fi, FI_ACL_MODE)) {
	358	inode->i_mode = fi->i_acl_mode;
	359	clear_inode_flag(fi, FI_ACL_MODE);
	360	}
	361	}
	362
	363	mark_inode_dirty(inode);
	364	return err;
	365	}
	366
	367	const struct inode_operations f2fs_file_inode_operations = {
	368	.getattr = f2fs_getattr,
	369	.setattr = f2fs_setattr,
	370	.get_acl = f2fs_get_acl,
	371	#ifdef CONFIG_F2FS_FS_XATTR
	372	.setxattr = generic_setxattr,
	373	.getxattr = generic_getxattr,
	374	.listxattr = f2fs_listxattr,
	375	.removexattr = generic_removexattr,
	376	#endif
	377	};
	378
	379	static void fill_zero(struct inode *inode, pgoff_t index,
	380	loff_t start, loff_t len)
	381	{
bd43df02	382	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
fbfa2cc5 JK	383	struct page *page;
	384
	385	if (!len)
	386	return;
	387
bd43df02 JK	388	f2fs_balance_fs(sbi);
	389
	390	mutex_lock_op(sbi, DATA_NEW);
fbfa2cc5	391	page = get_new_data_page(inode, index, false);
bd43df02	392	mutex_unlock_op(sbi, DATA_NEW);
fbfa2cc5 JK	393
	394	if (!IS_ERR(page)) {
	395	wait_on_page_writeback(page);
	396	zero_user(page, start, len);
	397	set_page_dirty(page);
	398	f2fs_put_page(page, 1);
	399	}
	400	}
	401
	402	int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
	403	{
	404	pgoff_t index;
	405	int err;
	406
	407	for (index = pg_start; index < pg_end; index++) {
	408	struct dnode_of_data dn;
	409	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	410
9eaeba70 JK	411	f2fs_balance_fs(sbi);
9eaeba70 JK	412
fbfa2cc5 JK	413	mutex_lock_op(sbi, DATA_TRUNC);
fbfa2cc5 JK	414	set_new_dnode(&dn, inode, NULL, NULL, 0);
266e97a8	415	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
fbfa2cc5 JK	416	if (err) {
	417	mutex_unlock_op(sbi, DATA_TRUNC);
	418	if (err == -ENOENT)
	419	continue;
	420	return err;
	421	}
	422
	423	if (dn.data_blkaddr != NULL_ADDR)
	424	truncate_data_blocks_range(&dn, 1);
	425	f2fs_put_dnode(&dn);
	426	mutex_unlock_op(sbi, DATA_TRUNC);
	427	}
	428	return 0;
	429	}
	430
	431	static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
	432	{
	433	pgoff_t pg_start, pg_end;
	434	loff_t off_start, off_end;
	435	int ret = 0;
	436
	437	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
	438	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
	439
	440	off_start = offset & (PAGE_CACHE_SIZE - 1);
	441	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
	442
	443	if (pg_start == pg_end) {
	444	fill_zero(inode, pg_start, off_start,
	445	off_end - off_start);
	446	} else {
	447	if (off_start)
	448	fill_zero(inode, pg_start++, off_start,
	449	PAGE_CACHE_SIZE - off_start);
	450	if (off_end)
	451	fill_zero(inode, pg_end, 0, off_end);
	452
	453	if (pg_start < pg_end) {
	454	struct address_space *mapping = inode->i_mapping;
	455	loff_t blk_start, blk_end;
	456
	457	blk_start = pg_start << PAGE_CACHE_SHIFT;
	458	blk_end = pg_end << PAGE_CACHE_SHIFT;
	459	truncate_inode_pages_range(mapping, blk_start,
	460	blk_end - 1);
	461	ret = truncate_hole(inode, pg_start, pg_end);
	462	}
	463	}
	464
	465	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
	466	i_size_read(inode) <= (offset + len)) {
	467	i_size_write(inode, offset);
	468	mark_inode_dirty(inode);
	469	}
	470
	471	return ret;
	472	}
	473
	474	static int expand_inode_data(struct inode *inode, loff_t offset,
	475	loff_t len, int mode)
	476	{
	477	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	478	pgoff_t index, pg_start, pg_end;
	479	loff_t new_size = i_size_read(inode);
480	loff_t off_start, off_end;
481	int ret = 0;
482
483	ret = inode_newsize_ok(inode, (len + offset));
484	if (ret)
485	return ret;
486
487	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
488	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
489
490	off_start = offset & (PAGE_CACHE_SIZE - 1);
491	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
492
493	for (index = pg_start; index <= pg_end; index++) {
494	struct dnode_of_data dn;
495
496	mutex_lock_op(sbi, DATA_NEW);
497
498	set_new_dnode(&dn, inode, NULL, NULL, 0);
266e97a8	499	ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
fbfa2cc5 JK	500	if (ret) {
	501	mutex_unlock_op(sbi, DATA_NEW);
	502	break;
	503	}
	504
	505	if (dn.data_blkaddr == NULL_ADDR) {
	506	ret = reserve_new_block(&dn);
	507	if (ret) {
	508	f2fs_put_dnode(&dn);
	509	mutex_unlock_op(sbi, DATA_NEW);
	510	break;
	511	}
	512	}
	513	f2fs_put_dnode(&dn);
	514
	515	mutex_unlock_op(sbi, DATA_NEW);
	516
	517	if (pg_start == pg_end)
	518	new_size = offset + len;
	519	else if (index == pg_start && off_start)
	520	new_size = (index + 1) << PAGE_CACHE_SHIFT;
	521	else if (index == pg_end)
	522	new_size = (index << PAGE_CACHE_SHIFT) + off_end;
	523	else
	524	new_size += PAGE_CACHE_SIZE;
	525	}
	526
	527	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
	528	i_size_read(inode) < new_size) {
	529	i_size_write(inode, new_size);
	530	mark_inode_dirty(inode);
	531	}
	532
	533	return ret;
	534	}
	535
	536	static long f2fs_fallocate(struct file *file, int mode,
	537	loff_t offset, loff_t len)
	538	{
6131ffaa	539	struct inode *inode = file_inode(file);
fbfa2cc5 JK	540	long ret;
	541
	542	if (mode & ~(FALLOC_FL_KEEP_SIZE \| FALLOC_FL_PUNCH_HOLE))
	543	return -EOPNOTSUPP;
	544
	545	if (mode & FALLOC_FL_PUNCH_HOLE)
	546	ret = punch_hole(inode, offset, len, mode);
	547	else
	548	ret = expand_inode_data(inode, offset, len, mode);
	549
3af60a49 NJ	550	if (!ret) {
	551	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	552	mark_inode_dirty(inode);
	553	}
fbfa2cc5 JK	554	return ret;
	555	}
	556
	557	#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL \| FS_TOPDIR_FL))
	558	#define F2FS_OTHER_FLMASK (FS_NODUMP_FL \| FS_NOATIME_FL)
	559
	560	static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
	561	{
	562	if (S_ISDIR(mode))
	563	return flags;
	564	else if (S_ISREG(mode))
	565	return flags & F2FS_REG_FLMASK;
	566	else
	567	return flags & F2FS_OTHER_FLMASK;
	568	}
	569
	570	long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
	571	{
6131ffaa	572	struct inode *inode = file_inode(filp);
fbfa2cc5 JK	573	struct f2fs_inode_info *fi = F2FS_I(inode);
	574	unsigned int flags;
	575	int ret;
	576
	577	switch (cmd) {
	578	case FS_IOC_GETFLAGS:
	579	flags = fi->i_flags & FS_FL_USER_VISIBLE;
	580	return put_user(flags, (int __user *) arg);
	581	case FS_IOC_SETFLAGS:
	582	{
	583	unsigned int oldflags;
	584
	585	ret = mnt_want_write(filp->f_path.mnt);
	586	if (ret)
	587	return ret;
	588
	589	if (!inode_owner_or_capable(inode)) {
	590	ret = -EACCES;
	591	goto out;
	592	}
	593
	594	if (get_user(flags, (int __user *) arg)) {
	595	ret = -EFAULT;
	596	goto out;
	597	}
	598
	599	flags = f2fs_mask_flags(inode->i_mode, flags);
	600
	601	mutex_lock(&inode->i_mutex);
	602
	603	oldflags = fi->i_flags;
	604
	605	if ((flags ^ oldflags) & (FS_APPEND_FL \| FS_IMMUTABLE_FL)) {
	606	if (!capable(CAP_LINUX_IMMUTABLE)) {
	607	mutex_unlock(&inode->i_mutex);
	608	ret = -EPERM;
	609	goto out;
	610	}
	611	}
	612
	613	flags = flags & FS_FL_USER_MODIFIABLE;
	614	flags \|= oldflags & ~FS_FL_USER_MODIFIABLE;
	615	fi->i_flags = flags;
	616	mutex_unlock(&inode->i_mutex);
	617
	618	f2fs_set_inode_flags(inode);
	619	inode->i_ctime = CURRENT_TIME;
	620	mark_inode_dirty(inode);
	621	out:
	622	mnt_drop_write(filp->f_path.mnt);
	623	return ret;
	624	}
	625	default:
	626	return -ENOTTY;
	627	}
	628	}
	629
e9750824 NJ	630	#ifdef CONFIG_COMPAT
	631	long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
	632	{
	633	switch (cmd) {
	634	case F2FS_IOC32_GETFLAGS:
	635	cmd = F2FS_IOC_GETFLAGS;
	636	break;
	637	case F2FS_IOC32_SETFLAGS:
	638	cmd = F2FS_IOC_SETFLAGS;
	639	break;
	640	default:
	641	return -ENOIOCTLCMD;
	642	}
	643	return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
	644	}
	645	#endif
	646
fbfa2cc5 JK	647	const struct file_operations f2fs_file_operations = {
	648	.llseek = generic_file_llseek,
	649	.read = do_sync_read,
	650	.write = do_sync_write,
	651	.aio_read = generic_file_aio_read,
	652	.aio_write = generic_file_aio_write,
	653	.open = generic_file_open,
	654	.mmap = f2fs_file_mmap,
	655	.fsync = f2fs_sync_file,
	656	.fallocate = f2fs_fallocate,
	657	.unlocked_ioctl = f2fs_ioctl,
e9750824 NJ	658	#ifdef CONFIG_COMPAT
	659	.compat_ioctl = f2fs_compat_ioctl,
	660	#endif
fbfa2cc5 JK	661	.splice_read = generic_file_splice_read,
	662	.splice_write = generic_file_splice_write,
	663	};