mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
![Ryusuke Konishi](/assets/img/avatar_default.png)
From the result of a function test of mmap, mmap write to shared pages
turned out to be broken for hole blocks. It doesn't write out filled
blocks and the data will be lost after umount. This is due to a bug
that the target file is not queued for log writer when filling hole
blocks.
Also, nilfs_page_mkwrite function exits normal code path even after
successfully filled hole blocks due to a change of block_page_mkwrite
function; just after nilfs was merged into the mainline,
block_page_mkwrite() started to return VM_FAULT_LOCKED instead of zero
by the patch "mm: close page_mkwrite races" (commit:
b827e496c8
). The current nilfs_page_mkwrite() is not handling
this value properly.
This corrects nilfs_page_mkwrite() and will resolve the data loss
problem in mmap write.
[This should be applied to every kernel since 2.6.30 but a fix is
needed for 2.6.37 and prior kernels]
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: stable <stable@kernel.org> [2.6.38]
160 lines
4.2 KiB
C
160 lines
4.2 KiB
C
/*
|
|
* file.c - NILFS regular file handling primitives including fsync().
|
|
*
|
|
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
|
|
*
|
|
* 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; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will 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 to the Free Software
|
|
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*
|
|
* Written by Amagai Yoshiji <amagai@osrg.net>,
|
|
* Ryusuke Konishi <ryusuke@osrg.net>
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/writeback.h>
|
|
#include "nilfs.h"
|
|
#include "segment.h"
|
|
|
|
int nilfs_sync_file(struct file *file, int datasync)
|
|
{
|
|
/*
|
|
* Called from fsync() system call
|
|
* This is the only entry point that can catch write and synch
|
|
* timing for both data blocks and intermediate blocks.
|
|
*
|
|
* This function should be implemented when the writeback function
|
|
* will be implemented.
|
|
*/
|
|
struct inode *inode = file->f_mapping->host;
|
|
int err;
|
|
|
|
if (!nilfs_inode_dirty(inode))
|
|
return 0;
|
|
|
|
if (datasync)
|
|
err = nilfs_construct_dsync_segment(inode->i_sb, inode, 0,
|
|
LLONG_MAX);
|
|
else
|
|
err = nilfs_construct_segment(inode->i_sb);
|
|
|
|
return err;
|
|
}
|
|
|
|
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
|
|
{
|
|
struct page *page = vmf->page;
|
|
struct inode *inode = vma->vm_file->f_dentry->d_inode;
|
|
struct nilfs_transaction_info ti;
|
|
int ret;
|
|
|
|
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
|
|
return VM_FAULT_SIGBUS; /* -ENOSPC */
|
|
|
|
lock_page(page);
|
|
if (page->mapping != inode->i_mapping ||
|
|
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
|
|
unlock_page(page);
|
|
return VM_FAULT_NOPAGE; /* make the VM retry the fault */
|
|
}
|
|
|
|
/*
|
|
* check to see if the page is mapped already (no holes)
|
|
*/
|
|
if (PageMappedToDisk(page))
|
|
goto mapped;
|
|
|
|
if (page_has_buffers(page)) {
|
|
struct buffer_head *bh, *head;
|
|
int fully_mapped = 1;
|
|
|
|
bh = head = page_buffers(page);
|
|
do {
|
|
if (!buffer_mapped(bh)) {
|
|
fully_mapped = 0;
|
|
break;
|
|
}
|
|
} while (bh = bh->b_this_page, bh != head);
|
|
|
|
if (fully_mapped) {
|
|
SetPageMappedToDisk(page);
|
|
goto mapped;
|
|
}
|
|
}
|
|
unlock_page(page);
|
|
|
|
/*
|
|
* fill hole blocks
|
|
*/
|
|
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
|
|
/* never returns -ENOMEM, but may return -ENOSPC */
|
|
if (unlikely(ret))
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
|
|
if (ret != VM_FAULT_LOCKED) {
|
|
nilfs_transaction_abort(inode->i_sb);
|
|
return ret;
|
|
}
|
|
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
|
|
nilfs_transaction_commit(inode->i_sb);
|
|
|
|
mapped:
|
|
SetPageChecked(page);
|
|
wait_on_page_writeback(page);
|
|
return VM_FAULT_LOCKED;
|
|
}
|
|
|
|
static const struct vm_operations_struct nilfs_file_vm_ops = {
|
|
.fault = filemap_fault,
|
|
.page_mkwrite = nilfs_page_mkwrite,
|
|
};
|
|
|
|
static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
file_accessed(file);
|
|
vma->vm_ops = &nilfs_file_vm_ops;
|
|
vma->vm_flags |= VM_CAN_NONLINEAR;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* We have mostly NULL's here: the current defaults are ok for
|
|
* the nilfs filesystem.
|
|
*/
|
|
const struct file_operations nilfs_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,
|
|
.unlocked_ioctl = nilfs_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = nilfs_compat_ioctl,
|
|
#endif /* CONFIG_COMPAT */
|
|
.mmap = nilfs_file_mmap,
|
|
.open = generic_file_open,
|
|
/* .release = nilfs_release_file, */
|
|
.fsync = nilfs_sync_file,
|
|
.splice_read = generic_file_splice_read,
|
|
};
|
|
|
|
const struct inode_operations nilfs_file_inode_operations = {
|
|
.truncate = nilfs_truncate,
|
|
.setattr = nilfs_setattr,
|
|
.permission = nilfs_permission,
|
|
.fiemap = nilfs_fiemap,
|
|
};
|
|
|
|
/* end of file */
|