aha/fs/xfs/linux-2.6/xfs_file.c

287 lines
7 KiB
C
Raw Normal View History

/*
* 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>
static struct vm_operations_struct xfs_file_vm_ops;
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iov,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
int ioflags = IO_ISAIO;
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
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_write(
struct kiocb *iocb,
const struct iovec *iov,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
int ioflags = IO_ISAIO;
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
&iocb->ki_pos, ioflags);
}
STATIC ssize_t
xfs_file_splice_read(
struct file *infilp,
loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len,
unsigned int flags)
{
int ioflags = 0;
if (infilp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
infilp, ppos, pipe, len, flags, ioflags);
}
STATIC ssize_t
xfs_file_splice_write(
struct pipe_inode_info *pipe,
struct file *outfilp,
loff_t *ppos,
size_t len,
unsigned int flags)
{
int ioflags = 0;
if (outfilp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
pipe, outfilp, ppos, len, flags, ioflags);
}
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(
xfs: merge fsync and O_SYNC handling The guarantees for O_SYNC are exactly the same as the ones we need to make for an fsync call (and given that Linux O_SYNC is O_DSYNC the equivalent is fdadatasync, but we treat both the same in XFS), except with a range data writeout. Jan Kara has started unifying these two path for filesystems using the generic helpers, and I've started to look at XFS. The actual transaction commited by xfs_fsync and xfs_write_sync_logforce has a different transaction number, but actually is exactly the same. We'll only use the fsync transaction going forward. One major difference is that xfs_write_sync_logforce never issues a cache flush unless we commit a transaction causing that as a side-effect, which is an obvious bug in the O_SYNC handling. Second all the locking and i_update_size vs i_update_core changes from 978b7237123d007b9fa983af6e0e2fa8f97f9934 never made it to xfs_write_sync_logforce, so we add them back. To make xfs_fsync easily usable from the O_SYNC path, the filemap_fdatawait call is moved up to xfs_file_fsync, so that we don't wait on the whole file after we already waited for our portion in xfs_write. We'll also use a plain call to filemap_write_and_wait_range instead of the previous sync_page_rang which did it in two steps including an half-hearted inode write out that doesn't help us. Once we're done with this also remove the now useless i_update_size tracking. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com> Signed-off-by: Felix Blyakher <felixb@sgi.com>
2009-09-01 00:00:31 +00:00
struct file *file,
struct dentry *dentry,
int datasync)
{
xfs: merge fsync and O_SYNC handling The guarantees for O_SYNC are exactly the same as the ones we need to make for an fsync call (and given that Linux O_SYNC is O_DSYNC the equivalent is fdadatasync, but we treat both the same in XFS), except with a range data writeout. Jan Kara has started unifying these two path for filesystems using the generic helpers, and I've started to look at XFS. The actual transaction commited by xfs_fsync and xfs_write_sync_logforce has a different transaction number, but actually is exactly the same. We'll only use the fsync transaction going forward. One major difference is that xfs_write_sync_logforce never issues a cache flush unless we commit a transaction causing that as a side-effect, which is an obvious bug in the O_SYNC handling. Second all the locking and i_update_size vs i_update_core changes from 978b7237123d007b9fa983af6e0e2fa8f97f9934 never made it to xfs_write_sync_logforce, so we add them back. To make xfs_fsync easily usable from the O_SYNC path, the filemap_fdatawait call is moved up to xfs_file_fsync, so that we don't wait on the whole file after we already waited for our portion in xfs_write. We'll also use a plain call to filemap_write_and_wait_range instead of the previous sync_page_rang which did it in two steps including an half-hearted inode write out that doesn't help us. Once we're done with this also remove the now useless i_update_size tracking. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com> Signed-off-by: Felix Blyakher <felixb@sgi.com>
2009-09-01 00:00:31 +00:00
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
int error;
/* capture size updates in I/O completion before writing the inode. */
error = filemap_fdatawait(inode->i_mapping);
if (error)
return error;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
return -xfs_fsync(ip);
}
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, ip->i_d.di_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;
}
/*
* 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 vm_fault *vmf)
{
return block_page_mkwrite(vma, vmf, 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_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 = {
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
.fault = filemap_fault,
.page_mkwrite = xfs_vm_page_mkwrite,
};