[linux.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/falloc.h>
#include <linux/types.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 = vma->vm_file->f_path.dentry->d_inode;
	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, 0);
	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,
};

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);
	unsigned long long cur_version;
	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;

	mutex_lock(&sbi->cp_mutex);
	cur_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
	mutex_unlock(&sbi->cp_mutex);

	if (F2FS_I(inode)->data_version != cur_version &&
					!(inode->i_state & I_DIRTY))
		goto out;
	F2FS_I(inode)->data_version--;

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

	f2fs_balance_fs(F2FS_SB(inode->i_sb));
}

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);
	}

	__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 page *page;

	if (!len)
		return;

	page = get_new_data_page(inode, index, false);

	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, RDONLY_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, 0);
		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->f_path.dentry->d_inode;
	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 = filp->f_dentry->d_inode;
	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;
	}
}

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,
	.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>
	16	#include <linux/falloc.h>
	17	#include <linux/types.h>
	18	#include <linux/uaccess.h>
	19	#include <linux/mount.h>
	20
	21	#include "f2fs.h"
	22	#include "node.h"
	23	#include "segment.h"
	24	#include "xattr.h"
	25	#include "acl.h"
	26
	27	static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
	28	struct vm_fault *vmf)
	29	{
	30	struct page *page = vmf->page;
	31	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
	32	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
fbfa2cc5 JK	33	block_t old_blk_addr;
	34	struct dnode_of_data dn;
	35	int err;
	36
	37	f2fs_balance_fs(sbi);
	38
	39	sb_start_pagefault(inode->i_sb);
	40
	41	mutex_lock_op(sbi, DATA_NEW);
	42
	43	/* block allocation */
	44	set_new_dnode(&dn, inode, NULL, NULL, 0);
	45	err = get_dnode_of_data(&dn, page->index, 0);
	46	if (err) {
	47	mutex_unlock_op(sbi, DATA_NEW);
	48	goto out;
	49	}
	50
	51	old_blk_addr = dn.data_blkaddr;
fbfa2cc5 JK	52
	53	if (old_blk_addr == NULL_ADDR) {
	54	err = reserve_new_block(&dn);
	55	if (err) {
	56	f2fs_put_dnode(&dn);
	57	mutex_unlock_op(sbi, DATA_NEW);
	58	goto out;
	59	}
	60	}
	61	f2fs_put_dnode(&dn);
	62
	63	mutex_unlock_op(sbi, DATA_NEW);
	64
	65	lock_page(page);
	66	if (page->mapping != inode->i_mapping \|\|
	67	page_offset(page) >= i_size_read(inode) \|\|
	68	!PageUptodate(page)) {
	69	unlock_page(page);
	70	err = -EFAULT;
	71	goto out;
	72	}
	73
	74	/*
	75	* check to see if the page is mapped already (no holes)
	76	*/
	77	if (PageMappedToDisk(page))
	78	goto out;
	79
	80	/* fill the page */
	81	wait_on_page_writeback(page);
	82
	83	/* page is wholly or partially inside EOF */
	84	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
	85	unsigned offset;
	86	offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
	87	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	88	}
	89	set_page_dirty(page);
	90	SetPageUptodate(page);
	91
	92	file_update_time(vma->vm_file);
	93	out:
	94	sb_end_pagefault(inode->i_sb);
	95	return block_page_mkwrite_return(err);
	96	}
	97
	98	static const struct vm_operations_struct f2fs_file_vm_ops = {
	99	.fault = filemap_fault,
	100	.page_mkwrite = f2fs_vm_page_mkwrite,
	101	};
	102
	103	static int need_to_sync_dir(struct f2fs_sb_info sbi, struct inode inode)
	104	{
	105	struct dentry *dentry;
	106	nid_t pino;
	107
	108	inode = igrab(inode);
	109	dentry = d_find_any_alias(inode);
	110	if (!dentry) {
	111	iput(inode);
	112	return 0;
	113	}
	114	pino = dentry->d_parent->d_inode->i_ino;
	115	dput(dentry);
116	iput(inode);
117	return !is_checkpointed_node(sbi, pino);
118	}
119
120	int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
121	{
122	struct inode *inode = file->f_mapping->host;
123	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
124	unsigned long long cur_version;
125	int ret = 0;
126	bool need_cp = false;
127	struct writeback_control wbc = {
128	.sync_mode = WB_SYNC_ALL,
129	.nr_to_write = LONG_MAX,
130	.for_reclaim = 0,
131	};
132
1fa95b0b NJ	133	if (inode->i_sb->s_flags & MS_RDONLY)
	134	return 0;
	135
fbfa2cc5 JK	136	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	137	if (ret)
	138	return ret;
	139
7d82db83 JK	140	/* guarantee free sections for fsync */
	141	f2fs_balance_fs(sbi);
	142
fbfa2cc5 JK	143	mutex_lock(&inode->i_mutex);
fbfa2cc5 JK	144
fbfa2cc5 JK	145	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
	146	goto out;
	147
	148	mutex_lock(&sbi->cp_mutex);
	149	cur_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
	150	mutex_unlock(&sbi->cp_mutex);
	151
	152	if (F2FS_I(inode)->data_version != cur_version &&
	153	!(inode->i_state & I_DIRTY))
	154	goto out;
	155	F2FS_I(inode)->data_version--;
	156
	157	if (!S_ISREG(inode->i_mode) \|\| inode->i_nlink != 1)
	158	need_cp = true;
	159	if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
	160	need_cp = true;
	161	if (!space_for_roll_forward(sbi))
	162	need_cp = true;
	163	if (need_to_sync_dir(sbi, inode))
	164	need_cp = true;
	165
fbfa2cc5 JK	166	if (need_cp) {
	167	/* all the dirty node pages should be flushed for POR */
	168	ret = f2fs_sync_fs(inode->i_sb, 1);
	169	clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
	170	} else {
398b1ac5 JK	171	/* if there is no written node page, write its inode page */
	172	while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
	173	ret = f2fs_write_inode(inode, NULL);
	174	if (ret)
	175	goto out;
	176	}
fbfa2cc5 JK	177	filemap_fdatawait_range(sbi->node_inode->i_mapping,
	178	0, LONG_MAX);
	179	}
	180	out:
	181	mutex_unlock(&inode->i_mutex);
	182	return ret;
	183	}
	184
	185	static int f2fs_file_mmap(struct file file, struct vm_area_struct vma)
	186	{
	187	file_accessed(file);
	188	vma->vm_ops = &f2fs_file_vm_ops;
	189	return 0;
	190	}
	191
	192	static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
	193	{
	194	int nr_free = 0, ofs = dn->ofs_in_node;
	195	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	196	struct f2fs_node *raw_node;
	197	__le32 *addr;
	198
	199	raw_node = page_address(dn->node_page);
	200	addr = blkaddr_in_node(raw_node) + ofs;
	201
	202	for ( ; count > 0; count--, addr++, dn->ofs_in_node++) {
	203	block_t blkaddr = le32_to_cpu(*addr);
	204	if (blkaddr == NULL_ADDR)
	205	continue;
	206
	207	update_extent_cache(NULL_ADDR, dn);
	208	invalidate_blocks(sbi, blkaddr);
	209	dec_valid_block_count(sbi, dn->inode, 1);
	210	nr_free++;
	211	}
	212	if (nr_free) {
	213	set_page_dirty(dn->node_page);
	214	sync_inode_page(dn);
	215	}
	216	dn->ofs_in_node = ofs;
	217	return nr_free;
	218	}
	219
	220	void truncate_data_blocks(struct dnode_of_data *dn)
	221	{
	222	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
	223	}
	224
	225	static void truncate_partial_data_page(struct inode *inode, u64 from)
	226	{
	227	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
	228	struct page *page;
	229
	230	if (!offset)
	231	return;
	232
	233	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT);
	234	if (IS_ERR(page))
	235	return;
	236
	237	lock_page(page);
	238	wait_on_page_writeback(page);
	239	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
	240	set_page_dirty(page);
241	f2fs_put_page(page, 1);
242	}
243
244	static int truncate_blocks(struct inode *inode, u64 from)
245	{
246	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
247	unsigned int blocksize = inode->i_sb->s_blocksize;
248	struct dnode_of_data dn;
249	pgoff_t free_from;
250	int count = 0;
251	int err;
252
253	free_from = (pgoff_t)
254	((from + blocksize - 1) >> (sbi->log_blocksize));
255
256	mutex_lock_op(sbi, DATA_TRUNC);
257
258	set_new_dnode(&dn, inode, NULL, NULL, 0);
259	err = get_dnode_of_data(&dn, free_from, RDONLY_NODE);
260	if (err) {
261	if (err == -ENOENT)
262	goto free_next;
263	mutex_unlock_op(sbi, DATA_TRUNC);
264	return err;
265	}
266
267	if (IS_INODE(dn.node_page))
268	count = ADDRS_PER_INODE;
269	else
270	count = ADDRS_PER_BLOCK;
271
272	count -= dn.ofs_in_node;
273	BUG_ON(count < 0);
274	if (dn.ofs_in_node \|\| IS_INODE(dn.node_page)) {
275	truncate_data_blocks_range(&dn, count);
276	free_from += count;
277	}
278
279	f2fs_put_dnode(&dn);
280	free_next:
281	err = truncate_inode_blocks(inode, free_from);
282	mutex_unlock_op(sbi, DATA_TRUNC);
283
284	/* lastly zero out the first data page */
285	truncate_partial_data_page(inode, from);
286
287	return err;
288	}
289
290	void f2fs_truncate(struct inode *inode)
291	{
292	if (!(S_ISREG(inode->i_mode) \|\| S_ISDIR(inode->i_mode) \|\|
293	S_ISLNK(inode->i_mode)))
294	return;
295
296	if (!truncate_blocks(inode, i_size_read(inode))) {
297	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
298	mark_inode_dirty(inode);
299	}
300
301	f2fs_balance_fs(F2FS_SB(inode->i_sb));
302	}
303
304	static int f2fs_getattr(struct vfsmount *mnt,
305	struct dentry dentry, struct kstat stat)
306	{
307	struct inode *inode = dentry->d_inode;
308	generic_fillattr(inode, stat);
309	stat->blocks <<= 3;
310	return 0;
311	}
312
313	#ifdef CONFIG_F2FS_FS_POSIX_ACL
314	static void __setattr_copy(struct inode inode, const struct iattr attr)
315	{
316	struct f2fs_inode_info *fi = F2FS_I(inode);
317	unsigned int ia_valid = attr->ia_valid;
318
319	if (ia_valid & ATTR_UID)
320	inode->i_uid = attr->ia_uid;
321	if (ia_valid & ATTR_GID)
322	inode->i_gid = attr->ia_gid;
323	if (ia_valid & ATTR_ATIME)
324	inode->i_atime = timespec_trunc(attr->ia_atime,
325	inode->i_sb->s_time_gran);
326	if (ia_valid & ATTR_MTIME)
327	inode->i_mtime = timespec_trunc(attr->ia_mtime,
328	inode->i_sb->s_time_gran);
329	if (ia_valid & ATTR_CTIME)
330	inode->i_ctime = timespec_trunc(attr->ia_ctime,
331	inode->i_sb->s_time_gran);
332	if (ia_valid & ATTR_MODE) {
333	umode_t mode = attr->ia_mode;
334
335	if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
336	mode &= ~S_ISGID;
337	set_acl_inode(fi, mode);
338	}
339	}
340	#else
341	#define __setattr_copy setattr_copy
342	#endif
343
344	int f2fs_setattr(struct dentry dentry, struct iattr attr)
345	{
346	struct inode *inode = dentry->d_inode;
347	struct f2fs_inode_info *fi = F2FS_I(inode);
348	int err;
349
350	err = inode_change_ok(inode, attr);
351	if (err)
352	return err;
353
354	if ((attr->ia_valid & ATTR_SIZE) &&
355	attr->ia_size != i_size_read(inode)) {
356	truncate_setsize(inode, attr->ia_size);
357	f2fs_truncate(inode);
358	}
359
360	__setattr_copy(inode, attr);
361
362	if (attr->ia_valid & ATTR_MODE) {
363	err = f2fs_acl_chmod(inode);
364	if (err \|\| is_inode_flag_set(fi, FI_ACL_MODE)) {
365	inode->i_mode = fi->i_acl_mode;
366	clear_inode_flag(fi, FI_ACL_MODE);
367	}
368	}
369
370	mark_inode_dirty(inode);
371	return err;
372	}
373
374	const struct inode_operations f2fs_file_inode_operations = {
375	.getattr = f2fs_getattr,
376	.setattr = f2fs_setattr,
377	.get_acl = f2fs_get_acl,
378	#ifdef CONFIG_F2FS_FS_XATTR
379	.setxattr = generic_setxattr,
380	.getxattr = generic_getxattr,
381	.listxattr = f2fs_listxattr,
382	.removexattr = generic_removexattr,
383	#endif
384	};
385
386	static void fill_zero(struct inode *inode, pgoff_t index,
387	loff_t start, loff_t len)
388	{
389	struct page *page;
390
391	if (!len)
392	return;
393
394	page = get_new_data_page(inode, index, false);
395
396	if (!IS_ERR(page)) {
397	wait_on_page_writeback(page);
398	zero_user(page, start, len);
399	set_page_dirty(page);
400	f2fs_put_page(page, 1);
401	}
402	}
403
404	int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
405	{
406	pgoff_t index;
407	int err;
408
409	for (index = pg_start; index < pg_end; index++) {
410	struct dnode_of_data dn;
411	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
412
9eaeba70 JK	413	f2fs_balance_fs(sbi);
9eaeba70 JK	414
fbfa2cc5 JK	415	mutex_lock_op(sbi, DATA_TRUNC);
	416	set_new_dnode(&dn, inode, NULL, NULL, 0);
	417	err = get_dnode_of_data(&dn, index, RDONLY_NODE);
	418	if (err) {
	419	mutex_unlock_op(sbi, DATA_TRUNC);
	420	if (err == -ENOENT)
	421	continue;
	422	return err;
	423	}
	424
	425	if (dn.data_blkaddr != NULL_ADDR)
	426	truncate_data_blocks_range(&dn, 1);
	427	f2fs_put_dnode(&dn);
	428	mutex_unlock_op(sbi, DATA_TRUNC);
	429	}
	430	return 0;
	431	}
	432
	433	static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
	434	{
	435	pgoff_t pg_start, pg_end;
	436	loff_t off_start, off_end;
	437	int ret = 0;
	438
	439	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
	440	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
	441
	442	off_start = offset & (PAGE_CACHE_SIZE - 1);
	443	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
	444
	445	if (pg_start == pg_end) {
	446	fill_zero(inode, pg_start, off_start,
	447	off_end - off_start);
	448	} else {
	449	if (off_start)
	450	fill_zero(inode, pg_start++, off_start,
	451	PAGE_CACHE_SIZE - off_start);
	452	if (off_end)
	453	fill_zero(inode, pg_end, 0, off_end);
	454
	455	if (pg_start < pg_end) {
	456	struct address_space *mapping = inode->i_mapping;
	457	loff_t blk_start, blk_end;
	458
	459	blk_start = pg_start << PAGE_CACHE_SHIFT;
	460	blk_end = pg_end << PAGE_CACHE_SHIFT;
	461	truncate_inode_pages_range(mapping, blk_start,
	462	blk_end - 1);
	463	ret = truncate_hole(inode, pg_start, pg_end);
	464	}
	465	}
	466
	467	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
	468	i_size_read(inode) <= (offset + len)) {
	469	i_size_write(inode, offset);
	470	mark_inode_dirty(inode);
	471	}
	472
	473	return ret;
	474	}
	475
	476	static int expand_inode_data(struct inode *inode, loff_t offset,
	477	loff_t len, int mode)
	478	{
479	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
480	pgoff_t index, pg_start, pg_end;
481	loff_t new_size = i_size_read(inode);
482	loff_t off_start, off_end;
483	int ret = 0;
484
485	ret = inode_newsize_ok(inode, (len + offset));
486	if (ret)
487	return ret;
488
489	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
490	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
491
492	off_start = offset & (PAGE_CACHE_SIZE - 1);
493	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
494
495	for (index = pg_start; index <= pg_end; index++) {
496	struct dnode_of_data dn;
497
498	mutex_lock_op(sbi, DATA_NEW);
499
500	set_new_dnode(&dn, inode, NULL, NULL, 0);
501	ret = get_dnode_of_data(&dn, index, 0);
502	if (ret) {
503	mutex_unlock_op(sbi, DATA_NEW);
504	break;
505	}
506
507	if (dn.data_blkaddr == NULL_ADDR) {
508	ret = reserve_new_block(&dn);
509	if (ret) {
510	f2fs_put_dnode(&dn);
511	mutex_unlock_op(sbi, DATA_NEW);
512	break;
513	}
514	}
515	f2fs_put_dnode(&dn);
516
517	mutex_unlock_op(sbi, DATA_NEW);
518
519	if (pg_start == pg_end)
520	new_size = offset + len;
521	else if (index == pg_start && off_start)
522	new_size = (index + 1) << PAGE_CACHE_SHIFT;
523	else if (index == pg_end)
524	new_size = (index << PAGE_CACHE_SHIFT) + off_end;
525	else
526	new_size += PAGE_CACHE_SIZE;
527	}
528
529	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
530	i_size_read(inode) < new_size) {
531	i_size_write(inode, new_size);
532	mark_inode_dirty(inode);
533	}
534
535	return ret;
536	}
537
538	static long f2fs_fallocate(struct file *file, int mode,
539	loff_t offset, loff_t len)
540	{
541	struct inode *inode = file->f_path.dentry->d_inode;
fbfa2cc5 JK	542	long ret;
	543
	544	if (mode & ~(FALLOC_FL_KEEP_SIZE \| FALLOC_FL_PUNCH_HOLE))
	545	return -EOPNOTSUPP;
	546
	547	if (mode & FALLOC_FL_PUNCH_HOLE)
	548	ret = punch_hole(inode, offset, len, mode);
	549	else
	550	ret = expand_inode_data(inode, offset, len, mode);
	551
3af60a49 NJ	552	if (!ret) {
	553	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	554	mark_inode_dirty(inode);
	555	}
fbfa2cc5 JK	556	return ret;
	557	}
	558
	559	#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL \| FS_TOPDIR_FL))
	560	#define F2FS_OTHER_FLMASK (FS_NODUMP_FL \| FS_NOATIME_FL)
	561
	562	static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
	563	{
	564	if (S_ISDIR(mode))
	565	return flags;
	566	else if (S_ISREG(mode))
	567	return flags & F2FS_REG_FLMASK;
	568	else
	569	return flags & F2FS_OTHER_FLMASK;
	570	}
	571
	572	long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
	573	{
	574	struct inode *inode = filp->f_dentry->d_inode;
	575	struct f2fs_inode_info *fi = F2FS_I(inode);
	576	unsigned int flags;
	577	int ret;
	578
	579	switch (cmd) {
	580	case FS_IOC_GETFLAGS:
	581	flags = fi->i_flags & FS_FL_USER_VISIBLE;
	582	return put_user(flags, (int __user *) arg);
	583	case FS_IOC_SETFLAGS:
	584	{
	585	unsigned int oldflags;
	586
	587	ret = mnt_want_write(filp->f_path.mnt);
	588	if (ret)
	589	return ret;
	590
	591	if (!inode_owner_or_capable(inode)) {
	592	ret = -EACCES;
	593	goto out;
	594	}
	595
	596	if (get_user(flags, (int __user *) arg)) {
	597	ret = -EFAULT;
	598	goto out;
	599	}
	600
	601	flags = f2fs_mask_flags(inode->i_mode, flags);
	602
	603	mutex_lock(&inode->i_mutex);
	604
	605	oldflags = fi->i_flags;
	606
	607	if ((flags ^ oldflags) & (FS_APPEND_FL \| FS_IMMUTABLE_FL)) {
	608	if (!capable(CAP_LINUX_IMMUTABLE)) {
	609	mutex_unlock(&inode->i_mutex);
	610	ret = -EPERM;
	611	goto out;
	612	}
	613	}
	614
	615	flags = flags & FS_FL_USER_MODIFIABLE;
	616	flags \|= oldflags & ~FS_FL_USER_MODIFIABLE;
	617	fi->i_flags = flags;
	618	mutex_unlock(&inode->i_mutex);
	619
620	f2fs_set_inode_flags(inode);
621	inode->i_ctime = CURRENT_TIME;
622	mark_inode_dirty(inode);
623	out:
624	mnt_drop_write(filp->f_path.mnt);
625	return ret;
626	}
627	default:
628	return -ENOTTY;
629	}
630	}
631
632	const struct file_operations f2fs_file_operations = {
633	.llseek = generic_file_llseek,
634	.read = do_sync_read,
635	.write = do_sync_write,
636	.aio_read = generic_file_aio_read,
637	.aio_write = generic_file_aio_write,
638	.open = generic_file_open,
639	.mmap = f2fs_file_mmap,
640	.fsync = f2fs_sync_file,
641	.fallocate = f2fs_fallocate,
642	.unlocked_ioctl = f2fs_ioctl,
643	.splice_read = generic_file_splice_read,
644	.splice_write = generic_file_splice_write,
645	};