path: root/fs/xfs/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_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>

/* flags for direct write completions */
#define XFS_DIO_FLAG_UNWRITTEN	(1 << 0)
#define XFS_DIO_FLAG_APPEND	(1 << 1)

/*
 * structure owned by writepages passed to individual writepage calls
 */
struct xfs_writepage_ctx {
	struct xfs_bmbt_irec    imap;
	bool			imap_valid;
	unsigned int		io_type;
	struct xfs_ioend	*ioend;
	sector_t		last_block;
};

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);
}

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 page.  Update the page state via the
 * associated buffer_heads, paying attention to the start and end offsets that
 * we need to process on the page.
 *
 * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
 * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
 * the page at all, as we may be racing with memory reclaim and it can free both
 * the bufferhead chain and the page as it will see the page as clean and
 * unused.
 */
static void
xfs_finish_page_writeback(
	struct inode		*inode,
	struct bio_vec		*bvec,
	int			error)
{
	unsigned int		end = bvec->bv_offset + bvec->bv_len - 1;
	struct buffer_head	*head, *bh, *next;
	unsigned int		off = 0;
	unsigned int		bsize;

	ASSERT(bvec->bv_offset < PAGE_SIZE);
	ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
	ASSERT(end < PAGE_SIZE);
	ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);

	bh = head = page_buffers(bvec->bv_page);

	bsize = bh->b_size;
	do {
		next = bh->b_this_page;
		if (off < bvec->bv_offset)
			goto next_bh;
		if (off > end)
			break;
		bh->b_end_io(bh, !error);
next_bh:
		off += bsize;
	} while ((bh = next) != head);
}

/*
 * We're now finished for good with this ioend structure.  Update the page
 * state, release holds on bios, and finally free up memory.  Do not use the
 * ioend after this.
 */
STATIC void
xfs_destroy_ioend(
	struct xfs_ioend	*ioend,
	int			error)
{
	struct inode		*inode = ioend->io_inode;
	struct bio		*last = ioend->io_bio;
	struct bio		*bio, *next;

	for (bio = &ioend->io_inline_bio; bio; bio = next) {
		struct bio_vec	*bvec;
		int		i;

		/*
		 * For the last bio, bi_private points to the ioend, so we
		 * need to explicitly end the iteration here.
		 */
		if (bio == last)
			next = NULL;
		else
			next = bio->bi_private;

		/* walk each page on bio, ending page IO on them */
		bio_for_each_segment_all(bvec, bio, i)
			xfs_finish_page_writeback(inode, bvec, error);

		bio_put(bio);
	}
}

/*
 * Fast and loose check if this write could update the on-disk inode size.
 */
static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
{
	return ioend->io_offset + ioend->io_size >
		XFS_I(ioend->io_inode)->i_d.di_size;
}

STATIC int
xfs_setfilesize_trans_alloc(
	struct xfs_ioend	*ioend)
{
	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
	struct xfs_trans	*tp;
	int			error;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
	if (error)
		return error;

	ioend->io_append_trans = tp;

	/*
	 * We may pass freeze protection with a transaction.  So tell lockdep
	 * we released it.
	 */
	__sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
	/*
	 * We hand off the transaction to the completion thread now, so
	 * clear the flag here.
	 */
	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
	return 0;
}

/*
 * Update on-disk file size now that data has been written to disk.
 */
STATIC int
xfs_setfilesize(
	struct xfs_inode	*ip,
	struct xfs_trans	*tp,
	xfs_off_t		offset,
	size_t			size)
{
	xfs_fsize_t		isize;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	isize = xfs_new_eof(ip, offset + size);
	if (!isize) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		xfs_trans_cancel(tp);
		return 0;
	}

	trace_xfs_setfilesize(ip, offset, size);

	ip->i_d.di_size = isize;
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	return xfs_trans_commit(tp);
}

STATIC int
xfs_setfilesize_ioend(
	struct xfs_ioend	*ioend,
	int			error)
{
	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
	struct xfs_trans	*tp = ioend->io_append_trans;

	/*
	 * The transaction may have been allocated in the I/O submission thread,
	 * thus we need to mark ourselves as being in a transaction manually.
	 * Similarly for freeze protection.
	 */
	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);

	/* we abort the update if there was an IO error */
	if (error) {
		xfs_trans_cancel(tp);
		return error;
	}

	return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
}

/*
 * IO write completion.
 */
STATIC void
xfs_end_io(
	struct work_struct *work)
{
	struct xfs_ioend	*ioend =
		container_of(work, struct xfs_ioend, io_work);
	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
	int			error = ioend->io_bio->bi_error;

	/*
	 * Set an error if the mount has shut down and proceed with end I/O
	 * processing so it can perform whatever cleanups are necessary.
	 */
	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		error = -EIO;

	/*
	 * For unwritten extents we need to issue transactions to convert a
	 * range to normal written extens after the data I/O has finished.
	 * Detecting and handling completion IO errors is done individually
	 * for each case as different cleanup operations need to be performed
	 * on error.
	 */
	if (ioend->io_type == XFS_IO_UNWRITTEN) {
		if (error)
			goto done;
		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
						  ioend->io_size);
	} else if (ioend->io_append_trans) {
		error = xfs_setfilesize_ioend(ioend, error);
	} else {
		ASSERT(!xfs_ioend_is_append(ioend));
	}

done:
	xfs_destroy_ioend(ioend, error);
}

STATIC void
xfs_end_bio(
	struct bio		*bio)
{
	struct xfs_ioend	*ioend = bio->bi_private;
	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;

	if (ioend->io_type == XFS_IO_UNWRITTEN)
		queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
	else if (ioend->io_append_trans)
		queue_work(mp->m_data_workqueue, &ioend->io_work);
	else
		xfs_destroy_ioend(ioend, bio->bi_error);