xfs_file.c

/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_trans.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
#include "xfs_attr_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_vnodeops.h"
#include "xfs_da_btree.h"
#include "xfs_ioctl.h"

#include <linux/dcache.h>
#include <linux/smp_lock.h>

static struct vm_operations_struct xfs_file_vm_ops;

STATIC_INLINE ssize_t
__xfs_file_read(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	int			ioflags,
	loff_t			pos)
{
	struct file		*file = iocb->ki_filp;

	BUG_ON(iocb->ki_pos != pos);
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	return xfs_read(XFS_I(file->f_path.dentry->d_inode), iocb, iov,
				nr_segs, &iocb->ki_pos, ioflags);
}

STATIC ssize_t
xfs_file_aio_read(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO, pos);
}

STATIC ssize_t
xfs_file_aio_read_invis(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos);
}

STATIC_INLINE ssize_t
__xfs_file_write(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	int			ioflags,
	loff_t			pos)
{
	struct file	*file = iocb->ki_filp;

	BUG_ON(iocb->ki_pos != pos);
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
				&iocb->ki_pos, ioflags);
}

STATIC ssize_t
xfs_file_aio_write(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO, pos);
}

STATIC ssize_t
xfs_file_aio_write_invis(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos);
}

STATIC ssize_t
xfs_file_splice_read(
	struct file		*infilp,
	loff_t			*ppos,
	struct pipe_inode_info	*pipe,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
				   infilp, ppos, pipe, len, flags, 0);
}

STATIC ssize_t
xfs_file_splice_read_invis(
	struct file		*infilp,
	loff_t			*ppos,
	struct pipe_inode_info	*pipe,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
				   infilp, ppos, pipe, len, flags, IO_INVIS);
}

STATIC ssize_t
xfs_file_splice_write(
	struct pipe_inode_info	*pipe,
	struct file		*outfilp,
	loff_t			*ppos,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
				    pipe, outfilp, ppos, len, flags, 0);
}

STATIC ssize_t
xfs_file_splice_write_invis(
	struct pipe_inode_info	*pipe,
	struct file		*outfilp,
	loff_t			*ppos,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
				    pipe, outfilp, ppos, len, flags, IO_INVIS);
}

STATIC int
xfs_file_open(
	struct inode	*inode,
	struct file	*file)
{
	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
		return -EFBIG;
	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
		return -EIO;
	return 0;
}

STATIC int
xfs_dir_open(
	struct inode	*inode,
	struct file	*file)
{
	struct xfs_inode *ip = XFS_I(inode);
	int		mode;
	int		error;

	error = xfs_file_open(inode, file);
	if (error)
		return error;

	/*
	 * If there are any blocks, read-ahead block 0 as we're almost
	 * certain to have the next operation be a read there.
	 */
	mode = xfs_ilock_map_shared(ip);
	if (ip->i_d.di_nextents > 0)
		xfs_da_reada_buf(NULL, ip, 0, XFS_DATA_FORK);
	xfs_iunlock(ip, mode);
	return 0;
}

STATIC int
xfs_file_release(
	struct inode	*inode,
	struct file	*filp)
{
	return -xfs_release(XFS_I(inode));
}

/*
 * We ignore the datasync flag here because a datasync is effectively
 * identical to an fsync. That is, datasync implies that we need to write
 * only the metadata needed to be able to access the data that is written
 * if we crash after the call completes. Hence if we are writing beyond
 * EOF we have to log the inode size change as well, which makes it a
 * full fsync. If we don't write beyond EOF, the inode core will be
 * clean in memory and so we don't need to log the inode, just like
 * fsync.
 */
STATIC int
xfs_file_fsync(
	struct file	*filp,
	struct dentry	*dentry,
	int		datasync)
{
	xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
	return -xfs_fsync(XFS_I(dentry->d_inode));
}

STATIC int
xfs_file_readdir(
	struct file	*filp,
	void		*dirent,
	filldir_t	filldir)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;
	xfs_inode_t	*ip = XFS_I(inode);
	int		error;
	size_t		bufsize;

	/*
	 * The Linux API doesn't pass down the total size of the buffer
	 * we read into down to the filesystem.  With the filldir concept
	 * it's not needed for correct information, but the XFS dir2 leaf
	 * code wants an estimate of the buffer size to calculate it's
	 * readahead window and size the buffers used for mapping to
	 * physical blocks.
	 *
	 * Try to give it an estimate that's good enough, maybe at some
	 * point we can change the ->readdir prototype to include the
	 * buffer size.
	 */
	bufsize = (size_t)min_t(loff_t, PAGE_SIZE, inode->i_size);

	error = xfs_readdir(ip, dirent, bufsize,
				(xfs_off_t *)&filp->f_pos, filldir);
	if (error)
		return -error;
	return 0;
}

STATIC int
xfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	vma->vm_ops = &xfs_file_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;

	file_accessed(filp);
	return 0;
}

STATIC long
xfs_file_ioctl(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	p)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;


	/* NOTE:  some of the ioctl's return positive #'s as a
	 *	  byte count indicating success, such as
	 *	  readlink_by_handle.  So we don't "sign flip"
	 *	  like most other routines.  This means true
	 *	  errors need to be returned as a negative value.
	 */
	return xfs_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
}

STATIC long
xfs_file_ioctl_invis(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	p)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;


	/* NOTE:  some of the ioctl's return positive #'s as a
	 *	  byte count indicating success, such as
	 *	  readlink_by_handle.  So we don't "sign flip"
	 *	  like most other routines.  This means true
	 *	  errors need to be returned as a negative value.
	 */
	return xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
}

/*
 * mmap()d file has taken write protection fault and is being made
 * writable. We can set the page state up correctly for a writable
 * page, which means we can do correct delalloc accounting (ENOSPC
 * checking!) and unwritten extent mapping.
 */
STATIC int
xfs_vm_page_mkwrite(
	struct vm_area_struct	*vma,
	struct page		*page)
{
	return block_page_mkwrite(vma, page, xfs_get_blocks);
}

const struct file_operations xfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= xfs_file_aio_read,
	.aio_write	= xfs_file_aio_write,
	.splice_read	= xfs_file_splice_read,
	.splice_write	= xfs_file_splice_write,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
#ifdef HAVE_FOP_OPEN_EXEC
	.open_exec	= xfs_file_open_exec,
#endif
};

const struct file_operations xfs_invis_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= xfs_file_aio_read_invis,
	.aio_write	= xfs_file_aio_write_invis,
	.splice_read	= xfs_file_splice_read_invis,
	.splice_write	= xfs_file_splice_write_invis,
	.unlocked_ioctl	= xfs_file_ioctl_invis,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_invis_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
};


const struct file_operations xfs_dir_file_operations = {
	.open		= xfs_dir_open,
	.read		= generic_read_dir,
	.readdir	= xfs_file_readdir,
	.llseek		= generic_file_llseek,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.fsync		= xfs_file_fsync,
};

static struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite	= xfs_vm_page_mkwrite,
};