linux/fs/ocfs2/mmap.c
Gang He c4c2416ab0 ocfs2: nowait aio support
Return EAGAIN if any of the following checks fail for direct I/O:

 - Cannot get the related locks immediately

 - Blocks are not allocated at the write location, it will trigger block
   allocation and block IO operations.

[ghe@suse.com: v4]
  Link: http://lkml.kernel.org/r/1516007283-29932-4-git-send-email-ghe@suse.com
[ghe@suse.com: v2]
  Link: http://lkml.kernel.org/r/1511944612-9629-4-git-send-email-ghe@suse.com
Link: http://lkml.kernel.org/r/1511775987-841-4-git-send-email-ghe@suse.com
Signed-off-by: Gang He <ghe@suse.com>
Reviewed-by: Alex Chen <alex.chen@huawei.com>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <ge.changwei@h3c.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-01-31 17:18:35 -08:00

198 lines
5.0 KiB
C

/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* mmap.c
*
* Code to deal with the mess that is clustered mmap.
*
* Copyright (C) 2002, 2004 Oracle. 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; 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., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/signal.h>
#include <linux/rbtree.h>
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "aops.h"
#include "dlmglue.h"
#include "file.h"
#include "inode.h"
#include "mmap.h"
#include "super.h"
#include "ocfs2_trace.h"
static int ocfs2_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
sigset_t oldset;
int ret;
ocfs2_block_signals(&oldset);
ret = filemap_fault(vmf);
ocfs2_unblock_signals(&oldset);
trace_ocfs2_fault(OCFS2_I(vma->vm_file->f_mapping->host)->ip_blkno,
vma, vmf->page, vmf->pgoff);
return ret;
}
static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
struct page *page)
{
int ret = VM_FAULT_NOPAGE;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
loff_t pos = page_offset(page);
unsigned int len = PAGE_SIZE;
pgoff_t last_index;
struct page *locked_page = NULL;
void *fsdata;
loff_t size = i_size_read(inode);
last_index = (size - 1) >> PAGE_SHIFT;
/*
* There are cases that lead to the page no longer bebongs to the
* mapping.
* 1) pagecache truncates locally due to memory pressure.
* 2) pagecache truncates when another is taking EX lock against
* inode lock. see ocfs2_data_convert_worker.
*
* The i_size check doesn't catch the case where nodes truncated and
* then re-extended the file. We'll re-check the page mapping after
* taking the page lock inside of ocfs2_write_begin_nolock().
*
* Let VM retry with these cases.
*/
if ((page->mapping != inode->i_mapping) ||
(!PageUptodate(page)) ||
(page_offset(page) >= size))
goto out;
/*
* Call ocfs2_write_begin() and ocfs2_write_end() to take
* advantage of the allocation code there. We pass a write
* length of the whole page (chopped to i_size) to make sure
* the whole thing is allocated.
*
* Since we know the page is up to date, we don't have to
* worry about ocfs2_write_begin() skipping some buffer reads
* because the "write" would invalidate their data.
*/
if (page->index == last_index)
len = ((size - 1) & ~PAGE_MASK) + 1;
ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
&locked_page, &fsdata, di_bh, page);
if (ret) {
if (ret != -ENOSPC)
mlog_errno(ret);
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
else
ret = VM_FAULT_SIGBUS;
goto out;
}
if (!locked_page) {
ret = VM_FAULT_NOPAGE;
goto out;
}
ret = ocfs2_write_end_nolock(mapping, pos, len, len, fsdata);
BUG_ON(ret != len);
ret = VM_FAULT_LOCKED;
out:
return ret;
}
static int ocfs2_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct buffer_head *di_bh = NULL;
sigset_t oldset;
int ret;
sb_start_pagefault(inode->i_sb);
ocfs2_block_signals(&oldset);
/*
* The cluster locks taken will block a truncate from another
* node. Taking the data lock will also ensure that we don't
* attempt page truncation as part of a downconvert.
*/
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
else
ret = VM_FAULT_SIGBUS;
goto out;
}
/*
* The alloc sem should be enough to serialize with
* ocfs2_truncate_file() changing i_size as well as any thread
* modifying the inode btree.
*/
down_write(&OCFS2_I(inode)->ip_alloc_sem);
ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page);
up_write(&OCFS2_I(inode)->ip_alloc_sem);
brelse(di_bh);
ocfs2_inode_unlock(inode, 1);
out:
ocfs2_unblock_signals(&oldset);
sb_end_pagefault(inode->i_sb);
return ret;
}
static const struct vm_operations_struct ocfs2_file_vm_ops = {
.fault = ocfs2_fault,
.page_mkwrite = ocfs2_page_mkwrite,
};
int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
int ret = 0, lock_level = 0;
ret = ocfs2_inode_lock_atime(file_inode(file),
file->f_path.mnt, &lock_level, 1);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
ocfs2_inode_unlock(file_inode(file), lock_level);
out:
vma->vm_ops = &ocfs2_file_vm_ops;
return 0;
}