kernel-fxtec-pro1x/fs/xfs/linux-2.6/xfs_file.c

490 lines
11 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_ioctl32.h"
#include "xfs_vnodeops.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 *filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EFBIG;
return -xfs_open(XFS_I(inode));
}
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));
}
/*
* Unfortunately we can't just use the clean and simple readdir implementation
* below, because nfs might call back into ->lookup from the filldir callback
* and that will deadlock the low-level btree code.
*
* Hopefully we'll find a better workaround that allows to use the optimal
* version at least for local readdirs for 2.6.25.
*/
#if 0
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;
}
#else
struct hack_dirent {
u64 ino;
loff_t offset;
int namlen;
unsigned int d_type;
char name[];
};
struct hack_callback {
char *dirent;
size_t len;
size_t used;
};
STATIC int
xfs_hack_filldir(
void *__buf,
const char *name,
int namlen,
loff_t offset,
u64 ino,
unsigned int d_type)
{
struct hack_callback *buf = __buf;
struct hack_dirent *de = (struct hack_dirent *)(buf->dirent + buf->used);
unsigned int reclen;
reclen = ALIGN(sizeof(struct hack_dirent) + namlen, sizeof(u64));
if (buf->used + reclen > buf->len)
return -EINVAL;
de->namlen = namlen;
de->offset = offset;
de->ino = ino;
de->d_type = d_type;
memcpy(de->name, name, namlen);
buf->used += reclen;
return 0;
}
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);
struct hack_callback buf;
struct hack_dirent *de;
int error;
loff_t size;
int eof = 0;
xfs_off_t start_offset, curr_offset, offset;
/*
* Try fairly hard to get memory
*/
buf.len = PAGE_CACHE_SIZE;
do {
buf.dirent = kmalloc(buf.len, GFP_KERNEL);
if (buf.dirent)
break;
buf.len >>= 1;
} while (buf.len >= 1024);
if (!buf.dirent)
return -ENOMEM;
curr_offset = filp->f_pos;
if (curr_offset == 0x7fffffff)
offset = 0xffffffff;
else
offset = filp->f_pos;
while (!eof) {
unsigned int reclen;
start_offset = offset;
buf.used = 0;
error = -xfs_readdir(ip, &buf, buf.len, &offset,
xfs_hack_filldir);
if (error || offset == start_offset) {
size = 0;
break;
}
size = buf.used;
de = (struct hack_dirent *)buf.dirent;
while (size > 0) {
curr_offset = de->offset /* & 0x7fffffff */;
if (filldir(dirent, de->name, de->namlen,
curr_offset & 0x7fffffff,
de->ino, de->d_type)) {
goto done;
}
reclen = ALIGN(sizeof(struct hack_dirent) + de->namlen,
sizeof(u64));
size -= reclen;
de = (struct hack_dirent *)((char *)de + reclen);
}
}
done:
if (!error) {
if (size == 0)
filp->f_pos = offset & 0x7fffffff;
else if (de)
filp->f_pos = curr_offset;
}
kfree(buf.dirent);
return error;
}
#endif
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)
{
int error;
struct inode *inode = filp->f_path.dentry->d_inode;
error = xfs_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
/* 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 error;
}
STATIC long
xfs_file_ioctl_invis(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
int error;
struct inode *inode = filp->f_path.dentry->d_inode;
error = xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
/* 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 error;
}
/*
* 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 = {
.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 02:46:59 -06:00
.fault = filemap_fault,
.page_mkwrite = xfs_vm_page_mkwrite,
};