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_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_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_iomap.h"
#include <linux/mpage.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>

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

	*delalloc = *unmapped = *unwritten = 0;

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

#if defined(XFS_RW_TRACE)
void
xfs_page_trace(
	int		tag,
	struct inode	*inode,
	struct page	*page,
	unsigned long	pgoff)
{
	xfs_inode_t	*ip;
	bhv_vnode_t	*vp = vn_from_inode(inode);
	loff_t		isize = i_size_read(inode);
	loff_t		offset = page_offset(page);
	int		delalloc = -1, unmapped = -1, unwritten = -1;

	if (page_has_buffers(page))
		xfs_count_page_state(page, &delalloc, &unmapped, &unwritten);

	ip = xfs_vtoi(vp);
	if (!ip->i_rwtrace)
		return;

	ktrace_enter(ip->i_rwtrace,
		(void *)((unsigned long)tag),
		(void *)ip,
		(void *)inode,
		(void *)page,
		(void *)pgoff,
		(void *)((unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff)),
		(void *)((unsigned long)(ip->i_d.di_size & 0xffffffff)),
		(void *)((unsigned long)((isize >> 32) & 0xffffffff)),
		(void *)((unsigned long)(isize & 0xffffffff)),
		(void *)((unsigned long)((offset >> 32) & 0xffffffff)),
		(void *)((unsigned long)(offset & 0xffffffff)),
		(void *)((unsigned long)delalloc),
		(void *)((unsigned long)unmapped),
		(void *)((unsigned long)unwritten),
		(void *)((unsigned long)current_pid()),
		(void *)NULL);
}
#else
#define xfs_page_trace(tag, inode, page, pgoff)
#endif

/*
 * Schedule IO completion handling on a xfsdatad if this was
 * the final hold on this ioend. If we are asked to wait,
 * flush the workqueue.
 */
STATIC void
xfs_finish_ioend(
	xfs_ioend_t	*ioend,
	int		wait)
{
	if (atomic_dec_and_test(&ioend->io_remaining)) {
		queue_work(xfsdatad_workqueue, &ioend->io_work);
		if (wait)
			flush_workqueue(xfsdatad_workqueue);
	}
}

/*
 * 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;

	for (bh = ioend->io_buffer_head; bh; bh = next) {
		next = bh->b_private;
		bh->b_end_io(bh, !ioend->io_error);
	}
	if (unlikely(ioend->io_error))
		vn_ioerror(ioend->io_vnode, ioend->io_error, __FILE__,__LINE__);
	vn_iowake(ioend->io_vnode);
	mempool_free(ioend, xfs_ioend_pool);
}

/*
 * 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 io_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.
 */
STATIC void
xfs_setfilesize(
	xfs_ioend_t		*ioend)
{
	xfs_inode_t		*ip;
	xfs_fsize_t		isize;
	xfs_fsize_t		bsize;

	ip = xfs_vtoi(ioend->io_vnode);
	if (!ip)
		return;

	ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
	ASSERT(ioend->io_type != IOMAP_READ);

	if (unlikely(ioend->io_error))
		return;

	bsize = ioend->io_offset + ioend->io_size;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	isize = MAX(ip->i_size, ip->i_iocore.io_new_size);
	isize = MIN(isize, bsize);

	if (ip->i_d.di_size < isize) {
		ip->i_d.di_size = isize;
		ip->i_update_core = 1;
		ip->i_update_size = 1;
		mark_inode_dirty_sync(vn_to_inode(ioend->io_vnode));
	}

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
}

/*
 * Buffered IO write completion for delayed allocate extents.
 */
STATIC void
xfs_end_bio_delalloc(
	struct work_struct	*work)
{
	xfs_ioend_t		*ioend =
		container_of(work, xfs_ioend_t, io_work);

	xfs_setfilesize(ioend);
	xfs_destroy_ioend(ioend);
}

/*
 * Buffered IO write completion for regular, written extents.
 */
STATIC void
xfs_end_bio_written(
	struct work_struct	*work)
{
	xfs_ioend_t		*ioend =
		container_of(work, xfs_ioend_t, io_work);

	xfs_setfilesize(ioend);
	xfs_destroy_ioend(ioend);
}

/*
 * IO write completion for unwr