f2fs: add file operations

This adds memory operations and file/file_inode operations.

- F2FS supports fallocate(), mmap(), fsync(), and basic ioctl().

Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>

1 files changed, 637 insertions, 0 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
new file mode 100644
index 00000000000..f5ae36d19f4
--- /dev/null
+++ b/fs/f2fs/file.c
@@ -0,0 +1,637 @@
+/**
+ * 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);
+	struct page *node_page;
+	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;
+	node_page = dn.node_page;
+
+	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,
+	};
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (ret)
+		return ret;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (inode->i_sb->s_flags & MS_RDONLY)
+		goto out;
+	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;
+
+	f2fs_write_inode(inode, NULL);
+
+	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 {
+		while (sync_node_pages(sbi, inode->i_ino, &wbc) == 0)
+			f2fs_write_inode(inode, NULL);
+		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);
+
+		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;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	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);
+
+	f2fs_balance_fs(sbi);
+	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,
+};