path: root/fs/xfs/linux-2.6/xfs_aops.c

/*
 * 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_trans.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_iomap.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>

/*
 * Types of I/O for bmap clustering and I/O completion tracking.
 */
enum {
	IO_READ,	/* mapping for a read */
	IO_DELAY,	/* mapping covers delalloc region */
	IO_UNWRITTEN,	/* mapping covers allocated but uninitialized data */
	IO_NEW		/* just allocated */
};

/*
 * Prime number of hash buckets since address is used as the key.
 */
#define NVSYNC		37
#define to_ioend_wq(v)	(&xfs_ioend_wq[((unsigned long)v) % NVSYNC])
static wait_queue_head_t xfs_ioend_wq[NVSYNC];

void __init
xfs_ioend_init(void)
{
	int i;

	for (i = 0; i < NVSYNC; i++)
		init_waitqueue_head(&xfs_ioend_wq[i]);
}

void
xfs_ioend_wait(
	xfs_inode_t	*ip)
{
	wait_queue_head_t *wq = to_ioend_wq(ip);

	wait_event(*wq, (atomic_read(&ip->i_iocount) == 0));
}

STATIC void
xfs_ioend_wake(
	xfs_inode_t	*ip)
{
	if (atomic_dec_and_test(&ip->i_iocount))
		wake_up(to_ioend_wq(ip));
}

void
xfs_count_page_state(
	struct page		*page,
	int			*delalloc,
	int			*unwritten)
{
	struct buffer_head	*bh, *head;

	*delalloc = *unwritten = 0;

	bh = head = page_buffers(page);
	do {
		if (buffer_unwritten(bh))
			(*unwritten) = 1;
		else if (buffer_delay(bh))
			(*delalloc) = 1;
	} while ((bh = bh->b_this_page) != head);
}

STATIC struct block_device *
xfs_find_bdev_for_inode(
	struct inode		*inode)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;

	if (XFS_IS_REALTIME_INODE(ip))
		return mp->m_rtdev_targp->bt_bdev;
	else
		return mp->m_ddev_targp->bt_bdev;
}

/*
 * We're now finished for good with this ioend structure.
 * Update the page state via the associated buffer_heads,
 * release holds on the inode and bio, and finally free
 * up memory.  Do not use the ioend after this.
 */
STATIC void
xfs_destroy_ioend(
	xfs_ioend_t		*ioend)
{
	struct buffer_head	*bh, *next;
	struct xfs_inode	*ip = XFS_I(ioend->io_inode);

	for (bh = ioend->io_buffer_head; bh; bh = next) {
		next = bh->b_private;
		bh->b_end_io(bh, !ioend->io_error);
	}

	/*
	 * Volume managers supporting multiple paths can send back ENODEV
	 * when the final path disappears.  In this case continuing to fill
	 * the page cache with dirty data which cannot be written out is
	 * evil, so prevent that.
	 */
	if (unlikely(ioend->io_error == -ENODEV)) {
		xfs_do_force_shutdown(ip->i_mount, SHUTDOWN_DEVICE_REQ,
				      __FILE__, __LINE__);
	}

	xfs_ioend_wake(ip);
	mempool_free(ioend, xfs_ioend_pool);
}

/*
 * If the end of the current ioend is beyond the current EOF,
 * return the new EOF value, otherwise zero.
 */
STATIC xfs_fsize_t
xfs_ioend_new_eof(
	xfs_ioend_t		*ioend)
{
	xfs_inode_t		*ip = XFS_I(ioend->io_inode);
	xfs_fsize_t		isize;
	xfs_fsize_t		bsize;

	bsize = ioend->io_offset + ioend->io_size;
	isize = MAX(ip->i_size, ip->i_new_size);
	isize = MIN(isize, bsize);
	return isize > ip->i_d.di_size ? isize : 0;
}

/*
 * Update on-disk file size now that data has been written to disk.  The
 * current in-memory file size is i_size.  If a write is beyond eof i_new_size
 * will be the intended file size until i_size is updated.  If this write does
 * not extend all the way to the valid file size then restrict this update to
 * the end of the write.
 *
 * This function does not block as blocking on the inode lock in IO completion
 * can lead to IO completion order dependency deadlocks.. If it can't get the
 * inode ilock it will return EAGAIN. Callers must handle this.
 */
STATIC int
xfs_setfilesize(
	xfs_ioend_t		*ioend)
{
	xfs_inode_t		*ip = XFS_I(ioend->io_inode);
	xfs_fsize_t		isize;

	ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFRE