Revision 7fb5409df092589b86cc9412d926879cb572b7f0 authored by Jan Kara on 10 February 2008, 06:08:38 UTC, committed by Theodore Ts'o on 10 February 2008, 06:08:38 UTC
We cannot start transaction in ext4_direct_IO() and just let it last during the whole write because dio_get_page() acquires mmap_sem which ranks above transaction start (e.g. because we have dependency chain mmap_sem->PageLock->journal_start, or because we update atime while holding mmap_sem) and thus deadlocks could happen. We solve the problem by starting a transaction separately for each ext4_get_block() call. We *could* have a problem that we allocate a block and before its data are written out the machine crashes and thus we expose stale data. But that does not happen because for hole-filling generic code falls back to buffered writes and for file extension, we add inode to orphan list and thus in case of crash, journal replay will truncate inode back to the original size. Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
1 parent 8009f9f
vxfs_olt.c
/*
* Copyright (c) 2000-2001 Christoph Hellwig.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions, and the following disclaimer,
* without modification.
* 2. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* Alternatively, this software may be distributed under the terms of the
* GNU General Public License ("GPL").
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
/*
* Veritas filesystem driver - object location table support.
*/
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/kernel.h>
#include "vxfs.h"
#include "vxfs_olt.h"
#include "vxfs_extern.h"
static inline void
vxfs_get_fshead(struct vxfs_oltfshead *fshp, struct vxfs_sb_info *infp)
{
BUG_ON(infp->vsi_fshino);
infp->vsi_fshino = fshp->olt_fsino[0];
}
static inline void
vxfs_get_ilist(struct vxfs_oltilist *ilistp, struct vxfs_sb_info *infp)
{
BUG_ON(infp->vsi_iext);
infp->vsi_iext = ilistp->olt_iext[0];
}
static inline u_long
vxfs_oblock(struct super_block *sbp, daddr_t block, u_long bsize)
{
BUG_ON(sbp->s_blocksize % bsize);
return (block * (sbp->s_blocksize / bsize));
}
/**
* vxfs_read_olt - read olt
* @sbp: superblock of the filesystem
* @bsize: blocksize of the filesystem
*
* Description:
* vxfs_read_olt reads the olt of the filesystem described by @sbp
* into main memory and does some basic setup.
*
* Returns:
* Zero on success, else a negative error code.
*/
int
vxfs_read_olt(struct super_block *sbp, u_long bsize)
{
struct vxfs_sb_info *infp = VXFS_SBI(sbp);
struct buffer_head *bp;
struct vxfs_olt *op;
char *oaddr, *eaddr;
bp = sb_bread(sbp, vxfs_oblock(sbp, infp->vsi_oltext, bsize));
if (!bp || !bp->b_data)
goto fail;
op = (struct vxfs_olt *)bp->b_data;
if (op->olt_magic != VXFS_OLT_MAGIC) {
printk(KERN_NOTICE "vxfs: ivalid olt magic number\n");
goto fail;
}
/*
* It is in theory possible that vsi_oltsize is > 1.
* I've not seen any such filesystem yet and I'm lazy.. --hch
*/
if (infp->vsi_oltsize > 1) {
printk(KERN_NOTICE "vxfs: oltsize > 1 detected.\n");
printk(KERN_NOTICE "vxfs: please notify hch@infradead.org\n");
goto fail;
}
oaddr = bp->b_data + op->olt_size;
eaddr = bp->b_data + (infp->vsi_oltsize * sbp->s_blocksize);
while (oaddr < eaddr) {
struct vxfs_oltcommon *ocp =
(struct vxfs_oltcommon *)oaddr;
switch (ocp->olt_type) {
case VXFS_OLT_FSHEAD:
vxfs_get_fshead((struct vxfs_oltfshead *)oaddr, infp);
break;
case VXFS_OLT_ILIST:
vxfs_get_ilist((struct vxfs_oltilist *)oaddr, infp);
break;
}
oaddr += ocp->olt_size;
}
brelse(bp);
return 0;
fail:
brelse(bp);
return -EINVAL;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...