Merge branch 'for-2.6.34-rc1-batch2' into for-linus

26 files changed, 1344 insertions, 1484 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 5c5a366aa33..b4769e40e8b 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -105,7 +105,6 @@ xfs-y				+= $(addprefix $(XFS_LINUX)/, \
 				   xfs_globals.o \
 				   xfs_ioctl.o \
 				   xfs_iops.o \
-				   xfs_lrw.o \
 				   xfs_super.o \
 				   xfs_sync.o \
 				   xfs_xattr.o)
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 66abe36c121..9083357f9e4 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -39,6 +39,7 @@
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_bmap.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
@@ -163,14 +164,17 @@ xfs_ioend_new_eof(
 }
 
 /*
- * 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.
+ * 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 void
+STATIC int
 xfs_setfilesize(
 	xfs_ioend_t		*ioend)
 {
@@ -181,16 +185,40 @@ xfs_setfilesize(
 	ASSERT(ioend->io_type != IOMAP_READ);
 
 	if (unlikely(ioend->io_error))
-		return;
+		return 0;
+
+	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		return EAGAIN;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	isize = xfs_ioend_new_eof(ioend);
 	if (isize) {
 		ip->i_d.di_size = isize;
-		xfs_mark_inode_dirty_sync(ip);
+		xfs_mark_inode_dirty(ip);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+/*
+ * 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)) {
+		struct workqueue_struct *wq;
+
+		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+			xfsconvertd_workqueue : xfsdatad_workqueue;
+		queue_work(wq, &ioend->io_work);
+		if (wait)
+			flush_workqueue(wq);
+	}
 }
 
 /*
@@ -198,11 +226,11 @@ xfs_setfilesize(
  */
 STATIC void
 xfs_end_io(
-	struct work_struct	*work)
+	struct work_struct *work)
 {
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_ioend_t	*ioend = container_of(work, xfs_ioend_t, io_work);
+	struct xfs_inode *ip = XFS_I(ioend->io_inode);
+	int		error = 0;
 
 	/*
 	 * For unwritten extents we need to issue transactions to convert a
@@ -210,7 +238,6 @@ xfs_end_io(
 	 */
 	if (ioend->io_type == IOMAP_UNWRITTEN &&
 	    likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
-		int error;
 
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
 						 ioend->io_size);
@@ -222,30 +249,23 @@ xfs_end_io(
 	 * We might have to update the on-disk file size after extending
 	 * writes.
 	 */
-	if (ioend->io_type != IOMAP_READ)
-		xfs_setfilesize(ioend);
-	xfs_destroy_ioend(ioend);
-}
-
-/*
- * 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)) {
-		struct workqueue_struct *wq;
-
-		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
-			xfsconvertd_workqueue : xfsdatad_workqueue;
-		queue_work(wq, &ioend->io_work);
-		if (wait)
-			flush_workqueue(wq);
+	if (ioend->io_type != IOMAP_READ) {
+		error = xfs_setfilesize(ioend);
+		ASSERT(!error || error == EAGAIN);
 	}
+
+	/*
+	 * If we didn't complete processing of the ioend, requeue it to the
+	 * tail of the workqueue for another attempt later. Otherwise destroy
+	 * it.
+	 */
+	if (error == EAGAIN) {
+		atomic_inc(&ioend->io_remaining);
+		xfs_finish_ioend(ioend, 0);
+		/* ensure we don't spin on blocked ioends */
+		delay(1);
+	} else
+		xfs_destroy_ioend(ioend);
 }
 
 /*
@@ -341,7 +361,7 @@ xfs_submit_ioend_bio(
 	 * but don't update the inode size until I/O completion.
 	 */
 	if (xfs_ioend_new_eof(ioend))
-		xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
+		xfs_mark_inode_dirty(XFS_I(ioend->io_inode));
 
 	submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
 		   WRITE_SYNC_PLUG : WRITE, bio);
@@ -874,6 +894,118 @@ xfs_cluster_write(
 	}
 }
 
+STATIC void
+xfs_vm_invalidatepage(
+	struct page		*page,
+	unsigned long		offset)
+{
+	trace_xfs_invalidatepage(page->mapping->host, page, offset);
+	block_invalidatepage(page, offset);
+}
+
+/*
+ * If the page has delalloc buffers on it, we need to punch them out before we
+ * invalidate the page. If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
+ * is done on that same region - the delalloc extent is returned when none is
+ * supposed to be there.
+ *
+ * We prevent this by truncating away the delalloc regions on the page before
+ * invalidating it. Because they are delalloc, we can do this without needing a
+ * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
+ * truncation without a transaction as there is no space left for block
+ * reservation (typically why we see a ENOSPC in writeback).
+ *
+ * This is not a performance critical path, so for now just do the punching a
+ * buffer head at a time.
+ */
+STATIC void
+xfs_aops_discard_page(
+	struct page		*page)
+{
+	struct inode		*inode = page->mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct buffer_head	*bh, *head;
+	loff_t			offset = page_offset(page);
+	ssize_t			len = 1 << inode->i_blkbits;
+
+	if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+		goto out_invalidate;
+
+	xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+		"page discard on page %p, inode 0x%llx, offset %llu.",
+			page, ip->i_ino, offset);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	bh = head = page_buffers(page);
+	do {
+		int		done;
+		xfs_fileoff_t	offset_fsb;
+		xfs_bmbt_irec_t	imap;
+		int		nimaps = 1;
+		int		error;
+		xfs_fsblock_t	firstblock;
+		xfs_bmap_free_t flist;
+
+		if (!buffer_delay(bh))
+			goto next_buffer;
+
+		offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+
+		/*
+		 * Map the range first and check that it is a delalloc extent
+		 * before trying to unmap the range. Otherwise we will be
+		 * trying to remove a real extent (which requires a
+		 * transaction) or a hole, which is probably a bad idea...
+		 */
+		error = xfs_bmapi(NULL, ip, offset_fsb, 1,
+				XFS_BMAPI_ENTIRE,  NULL, 0, &imap,
+				&nimaps, NULL, NULL);
+
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard failed delalloc mapping lookup.");
+			break;
+		}
+		if (!nimaps) {
+			/* nothing there */
+			goto next_buffer;
+		}
+		if (imap.br_startblock != DELAYSTARTBLOCK) {
+			/* been converted, ignore */
+			goto next_buffer;
+		}
+		WARN_ON(imap.br_blockcount == 0);
+
+		/*
+		 * Note: while we initialise the firstblock/flist pair, they
+		 * should never be used because blocks should never be
+		 * allocated or freed for a delalloc extent and hence we need
+		 * don't cancel or finish them after the xfs_bunmapi() call.
+		 */
+		xfs_bmap_init(&flist, &firstblock);
+		error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock,
+					&flist, NULL, &done);
+
+		ASSERT(!flist.xbf_count && !flist.xbf_first);
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard unable to remove delalloc mapping.");
+			break;
+		}
+next_buffer:
+		offset += len;
+
+	} while ((bh = bh->b_this_page) != head);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_invalidate:
+	xfs_vm_invalidatepage(page, 0);
+	return;
+}
+
 /*
  * Calling this without startio set means we are being asked to make a dirty
  * page ready for freeing it's buffers.  When called with startio set then
@@ -1125,7 +1257,7 @@ error:
 	 */
 	if (err != -EAGAIN) {
 		if (!unmapped)
-			block_invalidatepage(page, 0);
+			xfs_aops_discard_page(page);
 		ClearPageUptodate(page);
 	}
 	return err;
@@ -1535,15 +1667,6 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-STATIC void
-xfs_vm_invalidatepage(
-	struct page		*page,
-	unsigned long		offset)
-{
-	trace_xfs_invalidatepage(page->mapping->host, page, offset);
-	block_invalidatepage(page, offset);
-}
-
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index e4caeb28ce2..42dd3bcfba6 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_fs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
@@ -34,52 +35,279 @@
 #include "xfs_dir2_sf.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_vnodeops.h"
 #include "xfs_da_btree.h"
 #include "xfs_ioctl.h"
+#include "xfs_trace.h"
 
 #include <linux/dcache.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
-STATIC ssize_t
-xfs_file_aio_read(
-	struct kiocb		*iocb,
-	const struct iovec	*iov,
-	unsigned long		nr_segs,
-	loff_t			pos)
+/*
+ *	xfs_iozero
+ *
+ *	xfs_iozero clears the specified range of buffer supplied,
+ *	and marks all the affected blocks as valid and modified.  If
+ *	an affected block is not allocated, it will be allocated.  If
+ *	an affected block is not completely overwritten, and is not
+ *	valid before the operation, it will be read from disk before
+ *	being partially zeroed.
+ */
+STATIC int
+xfs_iozero(
+	struct xfs_inode	*ip,	/* inode			*/
+	loff_t			pos,	/* offset in file		*/
+	size_t			count)	/* size of data to zero		*/
 {
-	struct file		*file = iocb->ki_filp;
-	int			ioflags = 0;
+	struct page		*page;
+	struct address_space	*mapping;
+	int			status;
 
-	BUG_ON(iocb->ki_pos != pos);
-	if (unlikely(file->f_flags & O_DIRECT))
-		ioflags |= IO_ISDIRECT;
-	if (file->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
-	return xfs_read(XFS_I(file->f_path.dentry->d_inode), iocb, iov,
-				nr_segs, &iocb->ki_pos, ioflags);
+	mapping = VFS_I(ip)->i_mapping;
+	do {
+		unsigned offset, bytes;
+		void *fsdata;
+
+		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		bytes = PAGE_CACHE_SIZE - offset;
+		if (bytes > count)
+			bytes = count;
+
+		status = pagecache_write_begin(NULL, mapping, pos, bytes,
+					AOP_FLAG_UNINTERRUPTIBLE,
+					&page, &fsdata);
+		if (status)
+			break;
+
+		zero_user(page, offset, bytes);
+
+		status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
+					page, fsdata);
+		WARN_ON(status <= 0); /* can't return less than zero! */
+		pos += bytes;
+		count -= bytes;
+		status = 0;
+	} while (count);
+
+	return (-status);
+}
+
+STATIC int
+xfs_file_fsync(
+	struct file		*file,
+	struct dentry		*dentry,
+	int			datasync)
+{
+	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
+	struct xfs_trans	*tp;
+	int			error = 0;
+	int			log_flushed = 0;
+
+	xfs_itrace_entry(ip);
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -XFS_ERROR(EIO);
+
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+
+	/*
+	 * We always need to make sure that the required inode state is safe on
+	 * disk.  The inode might be clean but we still might need to force the
+	 * log because of committed transactions that haven't hit the disk yet.
+	 * Likewise, there could be unflushed non-transactional changes to the
+	 * inode core that have to go to disk and this requires us to issue
+	 * a synchronous transaction to capture these changes correctly.
+	 *
+	 * This code relies on the assumption that if the i_update_core field
+	 * of the inode is clear and the inode is unpinned then it is clean
+	 * and no action is required.
+	 */
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+
+	/*
+	 * First check if the VFS inode is marked dirty.  All the dirtying
+	 * of non-transactional updates no goes through mark_inode_dirty*,
+	 * which allows us to distinguish beteeen pure timestamp updates
+	 * and i_size updates which need to be caught for fdatasync.
+	 * After that also theck for the dirty state in the XFS inode, which
+	 * might gets cleared when the inode gets written out via the AIL
+	 * or xfs_iflush_cluster.
+	 */
+	if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) ||
+	    ((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
+	    ip->i_update_core) {
+		/*
+		 * Kick off a transaction to log the inode core to get the
+		 * updates.  The sync transaction will also force the log.
+		 */
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
+		error = xfs_trans_reserve(tp, 0,
+				XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
+		if (error) {
+			xfs_trans_cancel(tp, 0);
+			return -error;
+		}
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+		/*
+		 * Note - it's possible that we might have pushed ourselves out
+		 * of the way during trans_reserve which would flush the inode.
+		 * But there's no guarantee that the inode buffer has actually
+		 * gone out yet (it's delwri).	Plus the buffer could be pinned
+		 * anyway if it's part of an inode in another recent
+		 * transaction.	 So we play it safe and fire off the
+		 * transaction anyway.
+		 */
+		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+		xfs_trans_ihold(tp, ip);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_set_sync(tp);
+		error = _xfs_trans_commit(tp, 0, &log_flushed);
+
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	} else {
+		/*
+		 * Timestamps/size haven't changed since last inode flush or
+		 * inode transaction commit.  That means either nothing got
+		 * written or a transaction committed which caught the updates.
+		 * If the latter happened and the transaction hasn't hit the
+		 * disk yet, the inode will be still be pinned.  If it is,
+		 * force the log.
+		 */
+		if (xfs_ipincount(ip)) {
+			error = _xfs_log_force_lsn(ip->i_mount,
+					ip->i_itemp->ili_last_lsn,
+					XFS_LOG_SYNC, &log_flushed);
+		}
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	}
+
+	if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
+		/*
+		 * If the log write didn't issue an ordered tag we need
+		 * to flush the disk cache for the data device now.
+		 */
+		if (!log_flushed)
+			xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
+
+		/*
+		 * If this inode is on the RT dev we need to flush that
+		 * cache as well.
+		 */
+		if (XFS_IS_REALTIME_INODE(ip))
+			xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
+	}
+
+	return -error;
 }
 
 STATIC ssize_t
-xfs_file_aio_write(
+xfs_file_aio_read(
 	struct kiocb		*iocb,
-	const struct iovec	*iov,
+	const struct iovec	*iovp,
 	unsigned long		nr_segs,
 	loff_t			pos)
 {
 	struct file		*file = iocb->ki_filp;
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	size_t			size = 0;
+	ssize_t			ret = 0;
 	int			ioflags = 0;
+	xfs_fsize_t		n;
+	unsigned long		seg;
+
+	XFS_STATS_INC(xs_read_calls);
 
 	BUG_ON(iocb->ki_pos != pos);
+
 	if (unlikely(file->f_flags & O_DIRECT))
 		ioflags |= IO_ISDIRECT;
 	if (file->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
-	return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
-				&iocb->ki_pos, ioflags);
+
+	/* START copy & waste from filemap.c */
+	for (seg = 0; seg < nr_segs; seg++) {
+		const struct iovec *iv = &iovp[seg];
+
+		/*
+		 * If any segment has a negative length, or the cumulative
+		 * length ever wraps negative then return -EINVAL.
+		 */
+		size += iv->iov_len;
+		if (unlikely((ssize_t)(size|iv->iov_len) < 0))
+			return XFS_ERROR(-EINVAL);
+	}
+	/* END copy & waste from filemap.c */
+
+	if (unlikely(ioflags & IO_ISDIRECT)) {
+		xfs_buftarg_t	*target =
+			XFS_IS_REALTIME_INODE(ip) ?
+				mp->m_rtdev_targp : mp->m_ddev_targp;
+		if ((iocb->ki_pos & target->bt_smask) ||
+		    (size & target->bt_smask)) {
+			if (iocb->ki_pos == ip->i_size)
+				return 0;
+			return -XFS_ERROR(EINVAL);
+		}
+	}
+
+	n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
+	if (n <= 0 || size == 0)
+		return 0;
+
+	if (n < size)
+		size = n;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	if (unlikely(ioflags & IO_ISDIRECT))
+		mutex_lock(&inode->i_mutex);
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+
+	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
+		int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
+		int iolock = XFS_IOLOCK_SHARED;
+
+		ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size,
+					dmflags, &iolock);
+		if (ret) {
+			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+			if (unlikely(ioflags & IO_ISDIRECT))
+				mutex_unlock(&inode->i_mutex);
+			return ret;
+		}
+	}
+
+	if (unlikely(ioflags & IO_ISDIRECT)) {
+		if (inode->i_mapping->nrpages) {
+			ret = -xfs_flushinval_pages(ip,
+					(iocb->ki_pos & PAGE_CACHE_MASK),
+					-1, FI_REMAPF_LOCKED);
+		}
+		mutex_unlock(&inode->i_mutex);
+		if (ret) {
+			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+			return ret;
+		}
+	}
+
+	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
+
+	ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
+	if (ret > 0)
+		XFS_STATS_ADD(xs_read_bytes, ret);
+
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	return ret;
 }
 
 STATIC ssize_t
@@ -87,16 +315,44 @@ xfs_file_splice_read(
 	struct file		*infilp,
 	loff_t			*ppos,
 	struct pipe_inode_info	*pipe,
-	size_t			len,
+	size_t			count,
 	unsigned int		flags)
 {
+	struct xfs_inode	*ip = XFS_I(infilp->f_mapping->host);
+	struct xfs_mount	*mp = ip->i_mount;
 	int			ioflags = 0;
+	ssize_t			ret;
+
+	XFS_STATS_INC(xs_read_calls);
 
 	if (infilp->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
 
-	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
-				   infilp, ppos, pipe, len, flags, ioflags);
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+
+	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
+		int iolock = XFS_IOLOCK_SHARED;
+		int error;
+
+		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *ppos, count,
+					FILP_DELAY_FLAG(infilp), &iolock);
+		if (error) {
+			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+			return -error;
+		}
+	}
+
+	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
+
+	ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
+	if (ret > 0)
+		XFS_STATS_ADD(xs_read_bytes, ret);
+
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	return ret;
 }
 
 STATIC ssize_t
@@ -104,16 +360,538 @@ xfs_file_splice_write(
 	struct pipe_inode_info	*pipe,
 	struct file		*outfilp,
 	loff_t			*ppos,
-	size_t			len,
+	size_t			count,
 	unsigned int		flags)
 {
+	struct inode		*inode = outfilp->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fsize_t		isize, new_size;
 	int			ioflags = 0;
+	ssize_t			ret;
+
+	XFS_STATS_INC(xs_write_calls);
 
 	if (outfilp->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
 
-	return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
-				    pipe, outfilp, ppos, len, flags, ioflags);
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
+		int iolock = XFS_IOLOCK_EXCL;
+		int error;
+
+		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, *ppos, count,
+					FILP_DELAY_FLAG(outfilp), &iolock);
+		if (error) {
+			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+			return -error;
+		}
+	}
+
+	new_size = *ppos + count;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	if (new_size > ip->i_size)
+		ip->i_new_size = new_size;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
+
+	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
+	if (ret > 0)
+		XFS_STATS_ADD(xs_write_bytes, ret);
+
+	isize = i_size_read(inode);
+	if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
+		*ppos = isize;
+
+	if (*ppos > ip->i_size) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		if (*ppos > ip->i_size)
+			ip->i_size = *ppos;
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+
+	if (ip->i_new_size) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		ip->i_new_size = 0;
+		if (ip->i_d.di_size > ip->i_size)
+			ip->i_d.di_size = ip->i_size;
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return ret;
+}
+
+/*
+ * This routine is called to handle zeroing any space in the last
+ * block of the file that is beyond the EOF.  We do this since the
+ * size is being increased without writing anything to that block
+ * and we don't want anyone to read the garbage on the disk.
+ */
+STATIC int				/* error (positive) */
+xfs_zero_last_block(
+	xfs_inode_t	*ip,
+	xfs_fsize_t	offset,
+	xfs_fsize_t	isize)
+{
+	xfs_fileoff_t	last_fsb;
+	xfs_mount_t	*mp = ip->i_mount;
+	int		nimaps;
+	int		zero_offset;
+	int		zero_len;
+	int		error = 0;
+	xfs_bmbt_irec_t	imap;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	zero_offset = XFS_B_FSB_OFFSET(mp, isize);
+	if (zero_offset == 0) {
+		/*
+		 * There are no extra bytes in the last block on disk to
+		 * zero, so return.
+		 */
+		return 0;
+	}
+
+	last_fsb = XFS_B_TO_FSBT(mp, isize);
+	nimaps = 1;
+	error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
+			  &nimaps, NULL, NULL);
+	if (error) {
+		return error;
+	}
+	ASSERT(nimaps > 0);
+	/*
+	 * If the block underlying isize is just a hole, then there
+	 * is nothing to zero.
+	 */
+	if (imap.br_startblock == HOLESTARTBLOCK) {
+		return 0;
+	}
+	/*
+	 * Zero the part of the last block beyond the EOF, and write it
+	 * out sync.  We need to drop the ilock while we do this so we
+	 * don't deadlock when the buffer cache calls back to us.
+	 */
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	zero_len = mp->m_sb.sb_blocksize - zero_offset;
+	if (isize + zero_len > offset)
+		zero_len = offset - isize;
+	error = xfs_iozero(ip, isize, zero_len);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	ASSERT(error >= 0);
+	return error;
+}
+
+/*
+ * Zero any on disk space between the current EOF and the new,
+ * larger EOF.  This handles the normal case of zeroing the remainder
+ * of the last block in the file and the unusual case of zeroing blocks
+ * out beyond the size of the file.  This second case only happens
+ * with fixed size extents and when the system crashes before the inode
+ * size was updated but after blocks were allocated.  If fill is set,
+ * then any holes in the range are filled and zeroed.  If not, the holes
+ * are left alone as holes.
+ */
+
+int					/* error (positive) */
+xfs_zero_eof(
+	xfs_inode_t	*ip,
+	xfs_off_t	offset,		/* starting I/O offset */
+	xfs_fsize_t	isize)		/* current inode size */
+{
+	xfs_mount_t	*mp = ip->i_mount;
+	xfs_fileoff_t	start_zero_fsb;
+	xfs_fileoff_t	end_zero_fsb;
+	xfs_fileoff_t	zero_count_fsb;
+	xfs_fileoff_t	last_fsb;
+	xfs_fileoff_t	zero_off;
+	xfs_fsize_t	zero_len;
+	int		nimaps;
+	int		error = 0;
+	xfs_bmbt_irec_t	imap;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+	ASSERT(offset > isize);
+
+	/*
+	 * First handle zeroing the block on which isize resides.
+	 * We only zero a part of that block so it is handled specially.
+	 */
+	error = xfs_zero_last_block(ip, offset, isize);
+	if (error) {
+		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+		return error;
+	}
+
+	/*
+	 * Calculate the range between the new size and the old
+	 * where blocks needing to be zeroed may exist.  To get the
+	 * block where the last byte in the file currently resides,
+	 * we need to subtract one from the size and truncate back
+	 * to a block boundary.  We subtract 1 in case the size is
+	 * exactly on a block boundary.
+	 */
+	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
+	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
+	end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
+	ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
+	if (last_fsb == end_zero_fsb) {
+		/*
+		 * The size was only incremented on its last block.
+		 * We took care of that above, so just return.
+		 */
+		return 0;
+	}
+
+	ASSERT(start_zero_fsb <= end_zero_fsb);
+	while (start_zero_fsb <= end_zero_fsb) {
+		nimaps = 1;
+		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
+		error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
+				  0, NULL, 0, &imap, &nimaps, NULL, NULL);
+		if (error) {
+			ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+			return error;
+		}
+		ASSERT(nimaps > 0);
+
+		if (imap.br_state == XFS_EXT_UNWRITTEN ||
+		    imap.br_startblock == HOLESTARTBLOCK) {
+			/*
+			 * This loop handles initializing pages that were
+			 * partially initialized by the code below this
+			 * loop. It basically zeroes the part of the page
+			 * that sits on a hole and sets the page as P_HOLE
+			 * and calls remapf if it is a mapped file.
+			 */
+			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
+			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
+			continue;
+		}
+
+		/*
+		 * There are blocks we need to zero.
+		 * Drop the inode lock while we're doing the I/O.
+		 * We'll still have the iolock to protect us.
+		 */
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
+		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
+
+		if ((zero_off + zero_len) > offset)
+			zero_len = offset - zero_off;
+
+		error = xfs_iozero(ip, zero_off, zero_len);
+		if (error) {
+			goto out_lock;
+		}
+
+		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
+		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
+
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+	}
+
+	return 0;
+
+out_lock:
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	ASSERT(error >= 0);
+	return error;
+}
+
+STATIC ssize_t
+xfs_file_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	ssize_t			ret = 0, error = 0;
+	int			ioflags = 0;
+	xfs_fsize_t		isize, new_size;
+	int			iolock;
+	int			eventsent = 0;
+	size_t			ocount = 0, count;
+	int			need_i_mutex;
+
+	XFS_STATS_INC(xs_write_calls);
+
+	BUG_ON(iocb->ki_pos != pos);
+
+	if (unlikely(file->f_flags & O_DIRECT))
+		ioflags |= IO_ISDIRECT;
+	if (file->f_mode & FMODE_NOCMTIME)
+		ioflags |= IO_INVIS;
+
+	error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+	if (error)
+		return error;
+
+	count = ocount;
+	if (count == 0)
+		return 0;
+
+	xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+relock:
+	if (ioflags & IO_ISDIRECT) {
+		iolock = XFS_IOLOCK_SHARED;
+		need_i_mutex = 0;
+	} else {
+		iolock = XFS_IOLOCK_EXCL;
+		need_i_mutex = 1;
+		mutex_lock(&inode->i_mutex);
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
+
+start:
+	error = -generic_write_checks(file, &pos, &count,
+					S_ISBLK(inode->i_mode));
+	if (error) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+		goto out_unlock_mutex;
+	}
+
+	if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) &&
+	    !(ioflags & IO_INVIS) && !eventsent)) {
+		int		dmflags = FILP_DELAY_FLAG(file);
+
+		if (need_i_mutex)
+			dmflags |= DM_FLAGS_IMUX;
+
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip,
+				      pos, count, dmflags, &iolock);
+		if (error) {
+			goto out_unlock_internal;
+		}
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		eventsent = 1;
+
+		/*
+		 * The iolock was dropped and reacquired in XFS_SEND_DATA
+		 * so we have to recheck the size when appending.
+		 * We will only "goto start;" once, since having sent the
+		 * event prevents another call to XFS_SEND_DATA, which is
+		 * what allows the size to change in the first place.
+		 */
+		if ((file->f_flags & O_APPEND) && pos != ip->i_size)
+			goto start;
+	}
+
+	if (ioflags & IO_ISDIRECT) {
+		xfs_buftarg_t	*target =
+			XFS_IS_REALTIME_INODE(ip) ?
+				mp->m_rtdev_targp : mp->m_ddev_targp;
+
+		if ((pos & target->bt_smask) || (count & target->bt_smask)) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+			return XFS_ERROR(-EINVAL);
+		}
+
+		if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+			iolock = XFS_IOLOCK_EXCL;
+			need_i_mutex = 1;
+			mutex_lock(&inode->i_mutex);
+			xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
+			goto start;
+		}
+	}
+
+	new_size = pos + count;
+	if (new_size > ip->i_size)
+		ip->i_new_size = new_size;
+
+	if (likely(!(ioflags & IO_INVIS)))
+		file_update_time(file);
+
+	/*
+	 * If the offset is beyond the size of the file, we have a couple
+	 * of things to do. First, if there is already space allocated
+	 * we need to either create holes or zero the disk or ...
+	 *
+	 * If there is a page where the previous size lands, we need
+	 * to zero it out up to the new size.
+	 */
+
+	if (pos > ip->i_size) {
+		error = xfs_zero_eof(ip, pos, ip->i_size);
+		if (error) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			goto out_unlock_internal;
+		}
+	}
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	/*
+	 * If we're writing the file then make sure to clear the
+	 * setuid and setgid bits if the process is not being run
+	 * by root.  This keeps people from modifying setuid and
+	 * setgid binaries.
+	 */
+	error = -file_remove_suid(file);
+	if (unlikely(error))
+		goto out_unlock_internal;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = mapping->backing_dev_info;
+
+	if ((ioflags & IO_ISDIRECT)) {
+		if (mapping->nrpages) {
+			WARN_ON(need_i_mutex == 0);
+			error = xfs_flushinval_pages(ip,
+					(pos & PAGE_CACHE_MASK),
+					-1, FI_REMAPF_LOCKED);
+			if (error)
+				goto out_unlock_internal;
+		}
+
+		if (need_i_mutex) {
+			/* demote the lock now the cached pages are gone */
+			xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
+			mutex_unlock(&inode->i_mutex);
+
+			iolock = XFS_IOLOCK_SHARED;
+			need_i_mutex = 0;
+		}
+
+		trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
+		ret = generic_file_direct_write(iocb, iovp,
+				&nr_segs, pos, &iocb->ki_pos, count, ocount);
+
+		/*
+		 * direct-io write to a hole: fall through to buffered I/O
+		 * for completing the rest of the request.
+		 */
+		if (ret >= 0 && ret != count) {
+			XFS_STATS_ADD(xs_write_bytes, ret);
+
+			pos += ret;
+			count -= ret;
+
+			ioflags &= ~IO_ISDIRECT;
+			xfs_iunlock(ip, iolock);
+			goto relock;
+		}
+	} else {
+		int enospc = 0;
+		ssize_t ret2 = 0;
+
+write_retry:
+		trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
+		ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
+				pos, &iocb->ki_pos, count, ret);
+		/*
+		 * if we just got an ENOSPC, flush the inode now we
+		 * aren't holding any page locks and retry *once*
+		 */
+		if (ret2 == -ENOSPC && !enospc) {
+			error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
+			if (error)
+				goto out_unlock_internal;
+			enospc = 1;
+			goto write_retry;
+		}
+		ret = ret2;
+	}
+
+	current->backing_dev_info = NULL;
+
+	isize = i_size_read(inode);
+	if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
+		iocb->ki_pos = isize;
+
+	if (iocb->ki_pos > ip->i_size) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		if (iocb->ki_pos > ip->i_size)
+			ip->i_size = iocb->ki_pos;
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+
+	if (ret == -ENOSPC &&
+	    DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
+		xfs_iunlock(ip, iolock);
+		if (need_i_mutex)
+			mutex_unlock(&inode->i_mutex);
+		error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip,
+				DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL,
+				0, 0, 0); /* Delay flag intentionally  unused */
+		if (need_i_mutex)
+			mutex_lock(&inode->i_mutex);
+		xfs_ilock(ip, iolock);
+		if (error)
+			goto out_unlock_internal;
+		goto start;
+	}
+
+	error = -ret;
+	if (ret <= 0)
+		goto out_unlock_internal;
+
+	XFS_STATS_ADD(xs_write_bytes, ret);
+
+	/* Handle various SYNC-type writes */
+	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
+		loff_t end = pos + ret - 1;
+		int error2;
+
+		xfs_iunlock(ip, iolock);
+		if (need_i_mutex)
+			mutex_unlock(&inode->i_mutex);
+
+		error2 = filemap_write_and_wait_range(mapping, pos, end);
+		if (!error)
+			error = error2;
+		if (need_i_mutex)
+			mutex_lock(&inode->i_mutex);
+		xfs_ilock(ip, iolock);
+
+		error2 = -xfs_file_fsync(file, file->f_path.dentry,
+					 (file->f_flags & __O_SYNC) ? 0 : 1);
+		if (!error)
+			error = error2;
+	}
+
+ out_unlock_internal:
+	if (ip->i_new_size) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		ip->i_new_size = 0;
+		/*
+		 * If this was a direct or synchronous I/O that failed (such
+		 * as ENOSPC) then part of the I/O may have been written to
+		 * disk before the error occured.  In this case the on-disk
+		 * file size may have been adjusted beyond the in-memory file
+		 * size and now needs to be truncated back.
+		 */
+		if (ip->i_d.di_size > ip->i_size)
+			ip->i_d.di_size = ip->i_size;
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+	xfs_iunlock(ip, iolock);
+ out_unlock_mutex:
+	if (need_i_mutex)
+		mutex_unlock(&inode->i_mutex);
+	return -error;
 }
 
 STATIC int
@@ -160,28 +938,6 @@ xfs_file_release(
 	return -xfs_release(XFS_I(inode));
 }
 
-/*
- * We ignore the datasync flag here because a datasync is effectively
- * identical to an fsync. That is, datasync implies that we need to write
- * only the metadata needed to be able to access the data that is written
- * if we crash after the call completes. Hence if we are writing beyond
- * EOF we have to log the inode size change as well, which makes it a
- * full fsync. If we don't write beyond EOF, the inode core will be
- * clean in memory and so we don't need to log the inode, just like
- * fsync.
- */
-STATIC int
-xfs_file_fsync(
-	struct file		*file,
-	struct dentry		*dentry,
-	int			datasync)
-{
-	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
-
-	xfs_iflags_clear(ip, XFS_ITRUNCATED);
-	return -xfs_fsync(ip);
-}
-
 STATIC int
 xfs_file_readdir(
 	struct file	*filp,
@@ -203,9 +959,9 @@ xfs_file_readdir(
 	 *
 	 * Try to give it an estimate that's good enough, maybe at some
 	 * point we can change the ->readdir prototype to include the
-	 * buffer size.
+	 * buffer size.  For now we use the current glibc buffer size.
 	 */
-	bufsize = (size_t)min_t(loff_t, PAGE_SIZE, ip->i_d.di_size);
+	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);
 
 	error = xfs_readdir(ip, dirent, bufsize,
 				(xfs_off_t *)&filp->f_pos, filldir);
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index e8566bbf0f0..61a99608731 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -91,6 +91,16 @@ xfs_mark_inode_dirty_sync(
 		mark_inode_dirty_sync(inode);
 }
 
+void
+xfs_mark_inode_dirty(
+	xfs_inode_t	*ip)
+{
+	struct inode	*inode = VFS_I(ip);
+
+	if (!(inode->i_state & (I_WILL_FREE|I_FREEING|I_CLEAR)))
+		mark_inode_dirty(inode);
+}
+
 /*
  * Change the requested timestamp in the given inode.
  * We don't lock across timestamp updates, and we don't log them but
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 5af0c81ca1a..facfb323a70 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -88,7 +88,6 @@
 #include <xfs_super.h>
 #include <xfs_globals.h>
 #include <xfs_fs_subr.h>
-#include <xfs_lrw.h>
 #include <xfs_buf.h>
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
deleted file mode 100644
index eac6f80d786..00000000000
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ /dev/null
@@ -1,796 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 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_fs.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_dir2.h"
-#include "xfs_alloc.h"
-#include "xfs_dmapi.h"
-#include "xfs_quota.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_bmap.h"
-#include "xfs_btree.h"
-#include "xfs_ialloc.h"
-#include "xfs_rtalloc.h"
-#include "xfs_error.h"
-#include "xfs_itable.h"
-#include "xfs_rw.h"
-#include "xfs_attr.h"
-#include "xfs_inode_item.h"
-#include "xfs_buf_item.h"
-#include "xfs_utils.h"
-#include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
-#include "xfs_trace.h"
-
-#include <linux/capability.h>
-#include <linux/writeback.h>
-
-
-/*
- *	xfs_iozero
- *
- *	xfs_iozero clears the specified range of buffer supplied,
- *	and marks all the affected blocks as valid and modified.  If
- *	an affected block is not allocated, it will be allocated.  If
- *	an affected block is not completely overwritten, and is not
- *	valid before the operation, it will be read from disk before
- *	being partially zeroed.
- */
-STATIC int
-xfs_iozero(
-	struct xfs_inode	*ip,	/* inode			*/
-	loff_t			pos,	/* offset in file		*/
-	size_t			count)	/* size of data to zero		*/
-{
-	struct page		*page;
-	struct address_space	*mapping;
-	int			status;
-
-	mapping = VFS_I(ip)->i_mapping;
-	do {
-		unsigned offset, bytes;
-		void *fsdata;
-
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
-		bytes = PAGE_CACHE_SIZE - offset;
-		if (bytes > count)
-			bytes = count;
-
-		status = pagecache_write_begin(NULL, mapping, pos, bytes,
-					AOP_FLAG_UNINTERRUPTIBLE,
-					&page, &fsdata);
-		if (status)
-			break;
-
-		zero_user(page, offset, bytes);
-
-		status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
-					page, fsdata);
-		WARN_ON(status <= 0); /* can't return less than zero! */
-		pos += bytes;
-		count -= bytes;
-		status = 0;
-	} while (count);
-
-	return (-status);
-}
-
-ssize_t			/* bytes read, or (-)  error */
-xfs_read(
-	xfs_inode_t		*ip,
-	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned int		segs,
-	loff_t			*offset,
-	int			ioflags)
-{
-	struct file		*file = iocb->ki_filp;
-	struct inode		*inode = file->f_mapping->host;
-	xfs_mount_t		*mp = ip->i_mount;
-	size_t			size = 0;
-	ssize_t			ret = 0;
-	xfs_fsize_t		n;
-	unsigned long		seg;
-
-
-	XFS_STATS_INC(xs_read_calls);
-
-	/* START copy & waste from filemap.c */
-	for (seg = 0; seg < segs; seg++) {
-		const struct iovec *iv = &iovp[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		size += iv->iov_len;
-		if (unlikely((ssize_t)(size|iv->iov_len) < 0))
-			return XFS_ERROR(-EINVAL);
-	}
-	/* END copy & waste from filemap.c */
-
-	if (unlikely(ioflags & IO_ISDIRECT)) {
-		xfs_buftarg_t	*target =
-			XFS_IS_REALTIME_INODE(ip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp;
-		if ((*offset & target->bt_smask) ||
-		    (size & target->bt_smask)) {
-			if (*offset == ip->i_size) {
-				return (0);
-			}
-			return -XFS_ERROR(EINVAL);
-		}
-	}
-
-	n = XFS_MAXIOFFSET(mp) - *offset;
-	if ((n <= 0) || (size == 0))
-		return 0;
-
-	if (n < size)
-		size = n;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	if (unlikely(ioflags & IO_ISDIRECT))
-		mutex_lock(&inode->i_mutex);
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
-	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-		int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
-		int iolock = XFS_IOLOCK_SHARED;
-
-		ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *offset, size,
-					dmflags, &iolock);
-		if (ret) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			if (unlikely(ioflags & IO_ISDIRECT))
-				mutex_unlock(&inode->i_mutex);
-			return ret;
-		}
-	}
-
-	if (unlikely(ioflags & IO_ISDIRECT)) {
-		if (inode->i_mapping->nrpages)
-			ret = -xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK),
-						    -1, FI_REMAPF_LOCKED);
-		mutex_unlock(&inode->i_mutex);
-		if (ret) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			return ret;
-		}
-	}
-
-	trace_xfs_file_read(ip, size, *offset, ioflags);
-
-	iocb->ki_pos = *offset;
-	ret = generic_file_aio_read(iocb, iovp, segs, *offset);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
-
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-	return ret;
-}
-
-ssize_t
-xfs_splice_read(
-	xfs_inode_t		*ip,
-	struct file		*infilp,
-	loff_t			*ppos,
-	struct pipe_inode_info	*pipe,
-	size_t			count,
-	int			flags,
-	int			ioflags)
-{
-	xfs_mount_t		*mp = ip->i_mount;
-	ssize_t			ret;
-
-	XFS_STATS_INC(xs_read_calls);
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
-
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
-	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-		int iolock = XFS_IOLOCK_SHARED;
-		int error;
-
-		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *ppos, count,
-					FILP_DELAY_FLAG(infilp), &iolock);
-		if (error) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			return -error;
-		}
-	}
-
-	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
-
-	ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
-
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-	return ret;
-}
-
-ssize_t
-xfs_splice_write(
-	xfs_inode_t		*ip,
-	struct pipe_inode_info	*pipe,
-	struct file		*outfilp,
-	loff_t			*ppos,
-	size_t			count,
-	int			flags,
-	int			ioflags)
-{
-	xfs_mount_t		*mp = ip->i_mount;
-	ssize_t			ret;
-	struct inode		*inode = outfilp->f_mapping->host;
-	xfs_fsize_t		isize, new_size;
-
-	XFS_STATS_INC(xs_write_calls);
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
-
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-	if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
-		int iolock = XFS_IOLOCK_EXCL;
-		int error;
-
-		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, *ppos, count,
-					FILP_DELAY_FLAG(outfilp), &iolock);
-		if (error) {
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			return -error;
-		}
-	}
-
-	new_size = *ppos + count;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (new_size > ip->i_size)
-		ip->i_new_size = new_size;
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
-
-	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_write_bytes, ret);
-
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
-		*ppos = isize;
-
-	if (*ppos > ip->i_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		if (*ppos > ip->i_size)
-			ip->i_size = *ppos;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-
-	if (ip->i_new_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		ip->i_new_size = 0;
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	return ret;
-}
-
-/*
- * This routine is called to handle zeroing any space in the last
- * block of the file that is beyond the EOF.  We do this since the
- * size is being increased without writing anything to that block
- * and we don't want anyone to read the garbage on the disk.
- */
-STATIC int				/* error (positive) */
-xfs_zero_last_block(
-	xfs_inode_t	*ip,
-	xfs_fsize_t	offset,
-	xfs_fsize_t	isize)
-{
-	xfs_fileoff_t	last_fsb;
-	xfs_mount_t	*mp = ip->i_mount;
-	int		nimaps;
-	int		zero_offset;
-	int		zero_len;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	zero_offset = XFS_B_FSB_OFFSET(mp, isize);
-	if (zero_offset == 0) {
-		/*
-		 * There are no extra bytes in the last block on disk to
-		 * zero, so return.
-		 */
-		return 0;
-	}
-
-	last_fsb = XFS_B_TO_FSBT(mp, isize);
-	nimaps = 1;
-	error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
-			  &nimaps, NULL, NULL);
-	if (error) {
-		return error;
-	}
-	ASSERT(nimaps > 0);
-	/*
-	 * If the block underlying isize is just a hole, then there
-	 * is nothing to zero.
-	 */
-	if (imap.br_startblock == HOLESTARTBLOCK) {
-		return 0;
-	}
-	/*
-	 * Zero the part of the last block beyond the EOF, and write it
-	 * out sync.  We need to drop the ilock while we do this so we
-	 * don't deadlock when the buffer cache calls back to us.
-	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	zero_len = mp->m_sb.sb_blocksize - zero_offset;
-	if (isize + zero_len > offset)
-		zero_len = offset - isize;
-	error = xfs_iozero(ip, isize, zero_len);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
-}
-
-/*
- * Zero any on disk space between the current EOF and the new,
- * larger EOF.  This handles the normal case of zeroing the remainder
- * of the last block in the file and the unusual case of zeroing blocks
- * out beyond the size of the file.  This second case only happens
- * with fixed size extents and when the system crashes before the inode
- * size was updated but after blocks were allocated.  If fill is set,
- * then any holes in the range are filled and zeroed.  If not, the holes
- * are left alone as holes.
- */
-
-int					/* error (positive) */
-xfs_zero_eof(
-	xfs_inode_t	*ip,
-	xfs_off_t	offset,		/* starting I/O offset */
-	xfs_fsize_t	isize)		/* current inode size */
-{
-	xfs_mount_t	*mp = ip->i_mount;
-	xfs_fileoff_t	start_zero_fsb;
-	xfs_fileoff_t	end_zero_fsb;
-	xfs_fileoff_t	zero_count_fsb;
-	xfs_fileoff_t	last_fsb;
-	xfs_fileoff_t	zero_off;
-	xfs_fsize_t	zero_len;
-	int		nimaps;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-	ASSERT(offset > isize);
-
-	/*
-	 * First handle zeroing the block on which isize resides.
-	 * We only zero a part of that block so it is handled specially.
-	 */
-	error = xfs_zero_last_block(ip, offset, isize);
-	if (error) {
-		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-		return error;
-	}
-
-	/*
-	 * Calculate the range between the new size and the old
-	 * where blocks needing to be zeroed may exist.  To get the
-	 * block where the last byte in the file currently resides,
-	 * we need to subtract one from the size and truncate back
-	 * to a block boundary.  We subtract 1 in case the size is
-	 * exactly on a block boundary.
-	 */
-	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
-	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
-	end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
-	ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
-	if (last_fsb == end_zero_fsb) {
-		/*
-		 * The size was only incremented on its last block.
-		 * We took care of that above, so just return.
-		 */
-		return 0;
-	}
-
-	ASSERT(start_zero_fsb <= end_zero_fsb);
-	while (start_zero_fsb <= end_zero_fsb) {
-		nimaps = 1;
-		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
-		error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
-				  0, NULL, 0, &imap, &nimaps, NULL, NULL);
-		if (error) {
-			ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-			return error;
-		}
-		ASSERT(nimaps > 0);
-
-		if (imap.br_state == XFS_EXT_UNWRITTEN ||
-		    imap.br_startblock == HOLESTARTBLOCK) {
-			/*
-			 * This loop handles initializing pages that were
-			 * partially initialized by the code below this
-			 * loop. It basically zeroes the part of the page
-			 * that sits on a hole and sets the page as P_HOLE
-			 * and calls remapf if it is a mapped file.
-			 */
-			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-			continue;
-		}
-
-		/*
-		 * There are blocks we need to zero.
-		 * Drop the inode lock while we're doing the I/O.
-		 * We'll still have the iolock to protect us.
-		 */
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
-		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
-
-		if ((zero_off + zero_len) > offset)
-			zero_len = offset - zero_off;
-
-		error = xfs_iozero(ip, zero_off, zero_len);
-		if (error) {
-			goto out_lock;
-		}
-
-		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-	}
-
-	return 0;
-
-out_lock:
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
-}
-
-ssize_t				/* bytes written, or (-) error */
-xfs_write(
-	struct xfs_inode	*xip,
-	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned int		nsegs,
-	loff_t			*offset,
-	int			ioflags)
-{
-	struct file		*file = iocb->ki_filp;
-	struct address_space	*mapping = file->f_mapping;
-	struct inode		*inode = mapping->host;
-	unsigned long		segs = nsegs;
-	xfs_mount_t		*mp;
-	ssize_t			ret = 0, error = 0;
-	xfs_fsize_t		isize, new_size;
-	int			iolock;
-	int			eventsent = 0;
-	size_t			ocount = 0, count;
-	loff_t			pos;
-	int			need_i_mutex;
-
-	XFS_STATS_INC(xs_write_calls);
-
-	error = generic_segment_checks(iovp, &segs, &ocount, VERIFY_READ);
-	if (error)
-		return error;
-
-	count = ocount;
-	pos = *offset;
-
-	if (count == 0)
-		return 0;
-
-	mp = xip->i_mount;
-
-	xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-relock:
-	if (ioflags & IO_ISDIRECT) {
-		iolock = XFS_IOLOCK_SHARED;
-		need_i_mutex = 0;
-	} else {
-		iolock = XFS_IOLOCK_EXCL;
-		need_i_mutex = 1;
-		mutex_lock(&inode->i_mutex);
-	}
-
-	xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
-
-start:
-	error = -generic_write_checks(file, &pos, &count,
-					S_ISBLK(inode->i_mode));
-	if (error) {
-		xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-		goto out_unlock_mutex;
-	}
-
-	if ((DM_EVENT_ENABLED(xip, DM_EVENT_WRITE) &&
-	    !(ioflags & IO_INVIS) && !eventsent)) {
-		int		dmflags = FILP_DELAY_FLAG(file);
-
-		if (need_i_mutex)
-			dmflags |= DM_FLAGS_IMUX;
-
-		xfs_iunlock(xip, XFS_ILOCK_EXCL);
-		error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, xip,
-				      pos, count, dmflags, &iolock);
-		if (error) {
-			goto out_unlock_internal;
-		}
-		xfs_ilock(xip, XFS_ILOCK_EXCL);
-		eventsent = 1;
-
-		/*
-		 * The iolock was dropped and reacquired in XFS_SEND_DATA
-		 * so we have to recheck the size when appending.
-		 * We will only "goto start;" once, since having sent the
-		 * event prevents another call to XFS_SEND_DATA, which is
-		 * what allows the size to change in the first place.
-		 */
-		if ((file->f_flags & O_APPEND) && pos != xip->i_size)
-			goto start;
-	}
-
-	if (ioflags & IO_ISDIRECT) {
-		xfs_buftarg_t	*target =
-			XFS_IS_REALTIME_INODE(xip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp;
-
-		if ((pos & target->bt_smask) || (count & target->bt_smask)) {
-			xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-			return XFS_ERROR(-EINVAL);
-		}
-
-		if (!need_i_mutex && (mapping->nrpages || pos > xip->i_size)) {
-			xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-			iolock = XFS_IOLOCK_EXCL;
-			need_i_mutex = 1;
-			mutex_lock(&inode->i_mutex);
-			xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
-			goto start;
-		}
-	}
-
-	new_size = pos + count;
-	if (new_size > xip->i_size)
-		xip->i_new_size = new_size;
-
-	if (likely(!(ioflags & IO_INVIS)))
-		file_update_time(file);
-
-	/*
-	 * If the offset is beyond the size of the file, we have a couple
-	 * of things to do. First, if there is already space allocated
-	 * we need to either create holes or zero the disk or ...
-	 *
-	 * If there is a page where the previous size lands, we need
-	 * to zero it out up to the new size.
-	 */
-
-	if (pos > xip->i_size) {
-		error = xfs_zero_eof(xip, pos, xip->i_size);
-		if (error) {
-			xfs_iunlock(xip, XFS_ILOCK_EXCL);
-			goto out_unlock_internal;
-		}
-	}
-	xfs_iunlock(xip, XFS_ILOCK_EXCL);
-
-	/*
-	 * If we're writing the file then make sure to clear the
-	 * setuid and setgid bits if the process is not being run
-	 * by root.  This keeps people from modifying setuid and
-	 * setgid binaries.
-	 */
-	error = -file_remove_suid(file);
-	if (unlikely(error))
-		goto out_unlock_internal;
-
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
-
-	if ((ioflags & IO_ISDIRECT)) {
-		if (mapping->nrpages) {
-			WARN_ON(need_i_mutex == 0);
-			error = xfs_flushinval_pages(xip,
-					(pos & PAGE_CACHE_MASK),
-					-1, FI_REMAPF_LOCKED);
-			if (error)
-				goto out_unlock_internal;
-		}
-
-		if (need_i_mutex) {
-			/* demote the lock now the cached pages are gone */
-			xfs_ilock_demote(xip, XFS_IOLOCK_EXCL);
-			mutex_unlock(&inode->i_mutex);
-
-			iolock = XFS_IOLOCK_SHARED;
-			need_i_mutex = 0;
-		}
-
-		trace_xfs_file_direct_write(xip, count, *offset, ioflags);
-		ret = generic_file_direct_write(iocb, iovp,
-				&segs, pos, offset, count, ocount);
-
-		/*
-		 * direct-io write to a hole: fall through to buffered I/O
-		 * for completing the rest of the request.
-		 */
-		if (ret >= 0 && ret != count) {
-			XFS_STATS_ADD(xs_write_bytes, ret);
-
-			pos += ret;
-			count -= ret;
-
-			ioflags &= ~IO_ISDIRECT;
-			xfs_iunlock(xip, iolock);
-			goto relock;
-		}
-	} else {
-		int enospc = 0;
-		ssize_t ret2 = 0;
-
-write_retry:
-		trace_xfs_file_buffered_write(xip, count, *offset, ioflags);
-		ret2 = generic_file_buffered_write(iocb, iovp, segs,
-				pos, offset, count, ret);
-		/*
-		 * if we just got an ENOSPC, flush the inode now we
-		 * aren't holding any page locks and retry *once*
-		 */
-		if (ret2 == -ENOSPC && !enospc) {
-			error = xfs_flush_pages(xip, 0, -1, 0, FI_NONE);
-			if (error)
-				goto out_unlock_internal;
-			enospc = 1;
-			goto write_retry;
-		}
-		ret = ret2;
-	}
-
-	current->backing_dev_info = NULL;
-
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
-		*offset = isize;
-
-	if (*offset > xip->i_size) {
-		xfs_ilock(xip, XFS_ILOCK_EXCL);
-		if (*offset > xip->i_size)
-			xip->i_size = *offset;
-		xfs_iunlock(xip, XFS_ILOCK_EXCL);
-	}
-
-	if (ret == -ENOSPC &&
-	    DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
-		xfs_iunlock(xip, iolock);
-		if (need_i_mutex)
-			mutex_unlock(&inode->i_mutex);
-		error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, xip,
-				DM_RIGHT_NULL, xip, DM_RIGHT_NULL, NULL, NULL,
-				0, 0, 0); /* Delay flag intentionally  unused */
-		if (need_i_mutex)
-			mutex_lock(&inode->i_mutex);
-		xfs_ilock(xip, iolock);
-		if (error)
-			goto out_unlock_internal;
-		goto start;
-	}
-
-	error = -ret;
-	if (ret <= 0)
-		goto out_unlock_internal;
-
-	XFS_STATS_ADD(xs_write_bytes, ret);
-
-	/* Handle various SYNC-type writes */
-	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
-		loff_t end = pos + ret - 1;
-		int error2;
-
-		xfs_iunlock(xip, iolock);
-		if (need_i_mutex)
-			mutex_unlock(&inode->i_mutex);
-
-		error2 = filemap_write_and_wait_range(mapping, pos, end);
-		if (!error)
-			error = error2;
-		if (need_i_mutex)
-			mutex_lock(&inode->i_mutex);
-		xfs_ilock(xip, iolock);
-
-		error2 = xfs_fsync(xip);
-		if (!error)
-			error = error2;
-	}
-
- out_unlock_internal:
-	if (xip->i_new_size) {
-		xfs_ilock(xip, XFS_ILOCK_EXCL);
-		xip->i_new_size = 0;
-		/*
-		 * If this was a direct or synchronous I/O that failed (such
-		 * as ENOSPC) then part of the I/O may have been written to
-		 * disk before the error occured.  In this case the on-disk
-		 * file size may have been adjusted beyond the in-memory file
-		 * size and now needs to be truncated back.
-		 */
-		if (xip->i_d.di_size > xip->i_size)
-			xip->i_d.di_size = xip->i_size;
-		xfs_iunlock(xip, XFS_ILOCK_EXCL);
-	}
-	xfs_iunlock(xip, iolock);
- out_unlock_mutex:
-	if (need_i_mutex)
-		mutex_unlock(&inode->i_mutex);
-	return -error;
-}
-
-/*
- * If the underlying (data/log/rt) device is readonly, there are some
- * operations that cannot proceed.
- */
-int
-xfs_dev_is_read_only(
-	xfs_mount_t		*mp,
-	char			*message)
-{
-	if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
-	    xfs_readonly_buftarg(mp->m_logdev_targp) ||
-	    (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
-		cmn_err(CE_NOTE,
-			"XFS: %s required on read-only device.", message);
-		cmn_err(CE_NOTE,
-			"XFS: write access unavailable, cannot proceed.");
-		return EROFS;
-	}
-	return 0;
-}
diff --git a/fs/xfs/linux-2.6/xfs_lrw.h b/fs/xfs/linux-2.6/xfs_lrw.h
deleted file mode 100644
index 342ae8c0d01..00000000000
--- a/fs/xfs/linux-2.6/xfs_lrw.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 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
- */
-#ifndef __XFS_LRW_H__
-#define __XFS_LRW_H__
-
-struct xfs_mount;
-struct xfs_inode;
-struct xfs_buf;
-
-extern int xfs_dev_is_read_only(struct xfs_mount *, char *);
-
-extern int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-
-#endif	/* __XFS_LRW_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index a9f6d20aff4..05cd85317f6 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -607,7 +607,8 @@ xfssyncd(
 	set_freezable();
 	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
 	for (;;) {
-		timeleft = schedule_timeout_interruptible(timeleft);
+		if (list_empty(&mp->m_sync_list))
+			timeleft = schedule_timeout_interruptible(timeleft);
 		/* swsusp */
 		try_to_freeze();
 		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
@@ -627,8 +628,7 @@ xfssyncd(
 			list_add_tail(&mp->m_sync_work.w_list,
 					&mp->m_sync_list);
 		}
-		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
-			list_move(&work->w_list, &tmp);
+		list_splice_init(&mp->m_sync_list, &tmp);
 		spin_unlock(&mp->m_sync_lock);
 
 		list_for_each_entry_safe(work, n, &tmp, w_list) {
@@ -688,12 +688,12 @@ xfs_inode_set_reclaim_tag(
 	struct xfs_perag *pag;
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-	read_lock(&pag->pag_ici_lock);
+	write_lock(&pag->pag_ici_lock);
 	spin_lock(&ip->i_flags_lock);
 	__xfs_inode_set_reclaim_tag(pag, ip);
 	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
 	spin_unlock(&ip->i_flags_lock);
-	read_unlock(&pag->pag_ici_lock);
+	write_unlock(&pag->pag_ici_lock);
 	xfs_perag_put(pag);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/linux-2.6/xfs_trace.c
index 856eb3c8d60..5a107601e96 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/linux-2.6/xfs_trace.c
@@ -52,22 +52,6 @@
 #include "quota/xfs_dquot.h"
 
 /*
- * Format fsblock number into a static buffer & return it.
- */
-STATIC char *xfs_fmtfsblock(xfs_fsblock_t bno)
-{
-	static char rval[50];
-
-	if (bno == NULLFSBLOCK)
-		sprintf(rval, "NULLFSBLOCK");
-	else if (isnullstartblock(bno))
-		sprintf(rval, "NULLSTARTBLOCK(%lld)", startblockval(bno));
-	else
-		sprintf(rval, "%lld", (xfs_dfsbno_t)bno);
-	return rval;
-}
-
-/*
  * We include this last to have the helpers above available for the trace
  * event implementations.
  */
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index a4574dcf506..fcaa62f0799 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -197,13 +197,13 @@ TRACE_EVENT(xfs_iext_insert,
 		__entry->caller_ip = caller_ip;
 	),
 	TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
-		  "offset %lld block %s count %lld flag %d caller %pf",
+		  "offset %lld block %lld count %lld flag %d caller %pf",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  xfs_fmtfsblock(__entry->startblock),
+		  (__int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -241,13 +241,13 @@ DECLARE_EVENT_CLASS(xfs_bmap_class,
 		__entry->caller_ip = caller_ip;
 	),
 	TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
-		  "offset %lld block %s count %lld flag %d caller %pf",
+		  "offset %lld block %lld count %lld flag %d caller %pf",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  xfs_fmtfsblock(__entry->startblock),
+		  (__int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -593,7 +593,7 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
 	TP_ARGS(dqp),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(__be32, id)
+		__field(u32, id)
 		__field(unsigned, flags)
 		__field(unsigned, nrefs)
 		__field(unsigned long long, res_bcount)
@@ -606,7 +606,7 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
 	), \
 	TP_fast_assign(
 		__entry->dev = dqp->q_mount->m_super->s_dev;
-		__entry->id = dqp->q_core.d_id;
+		__entry->id = be32_to_cpu(dqp->q_core.d_id);
 		__entry->flags = dqp->dq_flags;
 		__entry->nrefs = dqp->q_nrefs;
 		__entry->res_bcount = dqp->q_res_bcount;
@@ -622,10 +622,10 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
 			be64_to_cpu(dqp->q_core.d_ino_softlimit);
 	),
 	TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx "
-		  "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] "
-		  "icnt 0x%llx [hard 0x%llx | soft 0x%llx]",
+		  "bcnt 0x%llx bhardlimit 0x%llx bsoftlimit 0x%llx "
+		  "icnt 0x%llx ihardlimit 0x%llx isoftlimit 0x%llx]",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  be32_to_cpu(__entry->id),
+		  __entry->id,
 		  __print_flags(__entry->flags, "|", XFS_DQ_FLAGS),
 		  __entry->nrefs,
 		  __entry->res_bcount,
@@ -881,7 +881,7 @@ TRACE_EVENT(name, \
 	), \
 	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
 		  "offset 0x%llx count %zd flags %s " \
-		  "startoff 0x%llx startblock %s blockcount 0x%llx", \
+		  "startoff 0x%llx startblock %lld blockcount 0x%llx", \
 		  MAJOR(__entry->dev), MINOR(__entry->dev), \
 		  __entry->ino, \
 		  __entry->size, \
@@ -890,7 +890,7 @@ TRACE_EVENT(name, \
 		  __entry->count, \
 		  __print_flags(__entry->flags, "|", BMAPI_FLAGS), \
 		  __entry->startoff, \
-		  xfs_fmtfsblock(__entry->startblock), \
+		  (__int64_t)__entry->startblock, \
 		  __entry->blockcount) \
 )
 DEFINE_IOMAP_EVENT(xfs_iomap_enter);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 1869fb97381..5c11e4d1701 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2550,22 +2550,134 @@ xfs_bmap_rtalloc(
 }
 
 STATIC int
+xfs_bmap_btalloc_nullfb(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		*blen)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		ag, startag;
+	int			notinit = 0;
+	int			error;
+
+	if (ap->userdata && xfs_inode_is_filestream(ap->ip))
+		args->type = XFS_ALLOCTYPE_NEAR_BNO;
+	else
+		args->type = XFS_ALLOCTYPE_START_BNO;
+	args->total = ap->total;
+
+	/*
+	 * Search for an allocation group with a single extent large enough
+	 * for the request.  If one isn't found, then adjust the minimum
+	 * allocation size to the largest space found.
+	 */
+	startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
+	if (startag == NULLAGNUMBER)
+		startag = ag = 0;
+
+	pag = xfs_perag_get(mp, ag);
+	while (*blen < ap->alen) {
+		if (!pag->pagf_init) {
+			error = xfs_alloc_pagf_init(mp, args->tp, ag,
+						    XFS_ALLOC_FLAG_TRYLOCK);
+			if (error) {
+				xfs_perag_put(pag);
+				return error;
+			}
+		}
+
+		/*
+		 * See xfs_alloc_fix_freelist...
+		 */
+		if (pag->pagf_init) {
+			xfs_extlen_t	longest;
+			longest = xfs_alloc_longest_free_extent(mp, pag);
+			if (*blen < longest)
+				*blen = longest;
+		} else
+			notinit = 1;
+
+		if (xfs_inode_is_filestream(ap->ip)) {
+			if (*blen >= ap->alen)
+				break;
+
+			if (ap->userdata) {
+				/*
+				 * If startag is an invalid AG, we've
+				 * come here once before and
+				 * xfs_filestream_new_ag picked the
+				 * best currently available.
+				 *
+				 * Don't continue looping, since we
+				 * could loop forever.
+				 */
+				if (startag == NULLAGNUMBER)
+					break;
+
+				error = xfs_filestream_new_ag(ap, &ag);
+				xfs_perag_put(pag);
+				if (error)
+					return error;
+
+				/* loop again to set 'blen'*/
+				startag = NULLAGNUMBER;
+				pag = xfs_perag_get(mp, ag);
+				continue;
+			}
+		}
+		if (++ag == mp->m_sb.sb_agcount)
+			ag = 0;
+		if (ag == startag)
+			break;
+		xfs_perag_put(pag);
+		pag = xfs_perag_get(mp, ag);
+	}
+	xfs_perag_put(pag);
+
+	/*
+	 * Since the above loop did a BUF_TRYLOCK, it is
+	 * possible that there is space for this request.
+	 */
+	if (notinit || *blen < ap->minlen)
+		args->minlen = ap->minlen;
+	/*
+	 * If the best seen length is less than the request
+	 * length, use the best as the minimum.
+	 */
+	else if (*blen < ap->alen)
+		args->minlen = *blen;
+	/*
+	 * Otherwise we've seen an extent as big as alen,
+	 * use that as the minimum.
+	 */
+	else
+		args->minlen = ap->alen;
+
+	/*
+	 * set the failure fallback case to look in the selected
+	 * AG as the stream may have moved.
+	 */
+	if (xfs_inode_is_filestream(ap->ip))
+		ap->rval = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
+
+	return 0;
+}
+
+STATIC int
 xfs_bmap_btalloc(
 	xfs_bmalloca_t	*ap)		/* bmap alloc argument struct */
 {
 	xfs_mount_t	*mp;		/* mount point structure */
 	xfs_alloctype_t	atype = 0;	/* type for allocation routines */
 	xfs_extlen_t	align;		/* minimum allocation alignment */
-	xfs_agnumber_t	ag;
 	xfs_agnumber_t	fb_agno;	/* ag number of ap->firstblock */
-	xfs_agnumber_t	startag;
+	xfs_agnumber_t	ag;
 	xfs_alloc_arg_t	args;
 	xfs_extlen_t	blen;
 	xfs_extlen_t	nextminlen = 0;
-	xfs_perag_t	*pag;
 	int		nullfb;		/* true if ap->firstblock isn't set */
 	int		isaligned;
-	int		notinit;
 	int		tryagain;
 	int		error;
 
@@ -2612,103 +2724,9 @@ xfs_bmap_btalloc(
 	args.firstblock = ap->firstblock;
 	blen = 0;
 	if (nullfb) {
-		if (ap->userdata && xfs_inode_is_filestream(ap->ip))
-			args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		else
-			args.type = XFS_ALLOCTYPE_START_BNO;
-		args.total = ap->total;
-
-		/*
-		 * Search for an allocation group with a single extent
-		 * large enough for the request.
-		 *
-		 * If one isn't found, then adjust the minimum allocation
-		 * size to the largest space found.
-		 */
-		startag = ag = XFS_FSB_TO_AGNO(mp, args.fsbno);
-		if (startag == NULLAGNUMBER)
-			startag = ag = 0;
-		notinit = 0;
-		pag = xfs_perag_get(mp, ag);
-		while (blen < ap->alen) {
-			if (!pag->pagf_init &&
-			    (error = xfs_alloc_pagf_init(mp, args.tp,
-				    ag, XFS_ALLOC_FLAG_TRYLOCK))) {
-				xfs_perag_put(pag);
-				return error;
-			}
-			/*
-			 * See xfs_alloc_fix_freelist...
-			 */
-			if (pag->pagf_init) {
-				xfs_extlen_t	longest;
-				longest = xfs_alloc_longest_free_extent(mp, pag);
-				if (blen < longest)
-					blen = longest;
-			} else
-				notinit = 1;
-
-			if (xfs_inode_is_filestream(ap->ip)) {
-				if (blen >= ap->alen)
-					break;
-
-				if (ap->userdata) {
-					/*
-					 * If startag is an invalid AG, we've
-					 * come here once before and
-					 * xfs_filestream_new_ag picked the
-					 * best currently available.
-					 *
-					 * Don't continue looping, since we
-					 * could loop forever.
-					 */
-					if (startag == NULLAGNUMBER)
-						break;
-
-					error = xfs_filestream_new_ag(ap, &ag);
-					xfs_perag_put(pag);
-					if (error)
-						return error;
-
-					/* loop again to set 'blen'*/
-					startag = NULLAGNUMBER;
-					pag = xfs_perag_get(mp, ag);
-					continue;
-				}
-			}
-			if (++ag == mp->m_sb.sb_agcount)
-				ag = 0;
-			if (ag == startag)
-				break;
-			xfs_perag_put(pag);
-			pag = xfs_perag_get(mp, ag);
-		}
-		xfs_perag_put(pag);
-		/*
-		 * Since the above loop did a BUF_TRYLOCK, it is
-		 * possible that there is space for this request.
-		 */
-		if (notinit || blen < ap->minlen)
-			args.minlen = ap->minlen;
-		/*
-		 * If the best seen length is less than the request
-		 * length, use the best as the minimum.
-		 */
-		else if (blen < ap->alen)
-			args.minlen = blen;
-		/*
-		 * Otherwise we've seen an extent as big as alen,
-		 * use that as the minimum.
-		 */
-		else
-			args.minlen = ap->alen;
-
-		/*
-		 * set the failure fallback case to look in the selected
-		 * AG as the stream may have moved.
-		 */
-		if (xfs_inode_is_filestream(ap->ip))
-			ap->rval = args.fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
+		error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
+		if (error)
+			return error;
 	} else if (ap->low) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index f52ac276277..7cf7220e7d5 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -292,7 +292,8 @@ typedef struct xfs_bstat {
 	__s32		bs_extents;	/* number of extents		*/
 	__u32		bs_gen;		/* generation count		*/
 	__u16		bs_projid;	/* project id			*/
-	unsigned char	bs_pad[14];	/* pad space, unused		*/
+	__u16		bs_forkoff;	/* inode fork offset in bytes	*/
+	unsigned char	bs_pad[12];	/* pad space, unused		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index e281eb4a1c4..6845db90818 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -190,13 +190,12 @@ xfs_iget_cache_hit(
 		trace_xfs_iget_reclaim(ip);
 
 		/*
-		 * We need to set XFS_INEW atomically with clearing the
-		 * reclaimable tag so that we do have an indicator of the
-		 * inode still being initialized.
+		 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
+		 * from stomping over us while we recycle the inode.  We can't
+		 * clear the radix tree reclaimable tag yet as it requires
+		 * pag_ici_lock to be held exclusive.
 		 */
-		ip->i_flags |= XFS_INEW;
-		ip->i_flags &= ~XFS_IRECLAIMABLE;
-		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
+		ip->i_flags |= XFS_IRECLAIM;
 
 		spin_unlock(&ip->i_flags_lock);
 		read_unlock(&pag->pag_ici_lock);
@@ -216,7 +215,15 @@ xfs_iget_cache_hit(
 			trace_xfs_iget_reclaim(ip);
 			goto out_error;
 		}
+
+		write_lock(&pag->pag_ici_lock);
+		spin_lock(&ip->i_flags_lock);
+		ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
+		ip->i_flags |= XFS_INEW;
+		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
 		inode->i_state = I_NEW;
+		spin_unlock(&ip->i_flags_lock);
+		write_unlock(&pag->pag_ici_lock);
 	} else {
 		/* If the VFS inode is being torn down, pause and try again. */
 		if (!igrab(inode)) {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index fa31360046d..0ffd5644704 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2439,75 +2439,31 @@ xfs_idestroy_fork(
 }
 
 /*
- * Increment the pin count of the given buffer.
- * This value is protected by ipinlock spinlock in the mount structure.
+ * This is called to unpin an inode.  The caller must have the inode locked
+ * in at least shared mode so that the buffer cannot be subsequently pinned
+ * once someone is waiting for it to be unpinned.
  */
-void
-xfs_ipin(
-	xfs_inode_t	*ip)
-{
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	atomic_inc(&ip->i_pincount);
-}
-
-/*
- * Decrement the pin count of the given inode, and wake up
- * anyone in xfs_iwait_unpin() if the count goes to 0.  The
- * inode must have been previously pinned with a call to xfs_ipin().
- */
-void
-xfs_iunpin(
-	xfs_inode_t	*ip)
-{
-	ASSERT(atomic_read(&ip->i_pincount) > 0);
-
-	if (atomic_dec_and_test(&ip->i_pincount))
-		wake_up(&ip->i_ipin_wait);
-}
-
-/*
- * This is called to unpin an inode. It can be directed to wait or to return
- * immediately without waiting for the inode to be unpinned.  The caller must
- * have the inode locked in at least shared mode so that the buffer cannot be
- * subsequently pinned once someone is waiting for it to be unpinned.
- */
-STATIC void
-__xfs_iunpin_wait(
-	xfs_inode_t	*ip,
-	int		wait)
+static void
+xfs_iunpin_nowait(
+	struct xfs_inode	*ip)
 {
-	xfs_inode_log_item_t	*iip = ip->i_itemp;
-
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	if (atomic_read(&ip->i_pincount) == 0)
-		return;
 
 	/* Give the log a push to start the unpinning I/O */
-	if (iip && iip->ili_last_lsn)
-		xfs_log_force_lsn(ip->i_mount, iip->ili_last_lsn, 0);
-	else
-		xfs_log_force(ip->i_mount, 0);
+	xfs_log_force_lsn(ip->i_mount, ip->i_itemp->ili_last_lsn, 0);
 
-	if (wait)
-		wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
 }
 
 void
 xfs_iunpin_wait(
-	xfs_inode_t	*ip)
+	struct xfs_inode	*ip)
 {
-	__xfs_iunpin_wait(ip, 1);
-}
-
-static inline void
-xfs_iunpin_nowait(
-	xfs_inode_t	*ip)
-{
-	__xfs_iunpin_wait(ip, 0);
+	if (xfs_ipincount(ip)) {
+		xfs_iunpin_nowait(ip);
+		wait_event(ip->i_ipin_wait, (xfs_ipincount(ip) == 0));
+	}
 }
 
-
 /*
  * xfs_iextents_copy()
  *
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 6c912b02759..9965e40a461 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -471,8 +471,6 @@ int		xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
 int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
-void		xfs_ipin(xfs_inode_t *);
-void		xfs_iunpin(xfs_inode_t *);
 void		xfs_iunpin_wait(xfs_inode_t *);
 int		xfs_iflush(xfs_inode_t *, uint);
 void		xfs_ichgtime(xfs_inode_t *, int);
@@ -480,6 +478,7 @@ void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
 void		xfs_synchronize_times(xfs_inode_t *);
+void		xfs_mark_inode_dirty(xfs_inode_t *);
 void		xfs_mark_inode_dirty_sync(xfs_inode_t *);
 
 #define IHOLD(ip) \
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d4dc063111f..7bfea854015 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -535,23 +535,23 @@ xfs_inode_item_format(
 
 /*
  * This is called to pin the inode associated with the inode log
- * item in memory so it cannot be written out.  Do this by calling
- * xfs_ipin() to bump the pin count in the inode while holding the
- * inode pin lock.
+ * item in memory so it cannot be written out.
  */
 STATIC void
 xfs_inode_item_pin(
 	xfs_inode_log_item_t	*iip)
 {
 	ASSERT(xfs_isilocked(iip->ili_inode, XFS_ILOCK_EXCL));
-	xfs_ipin(iip->ili_inode);
+
+	atomic_inc(&iip->ili_inode->i_pincount);
 }
 
 
 /*
  * This is called to unpin the inode associated with the inode log
  * item which was previously pinned with a call to xfs_inode_item_pin().
- * Just call xfs_iunpin() on the inode to do this.
+ *
+ * Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
  */
 /* ARGSUSED */
 STATIC void
@@ -559,7 +559,11 @@ xfs_inode_item_unpin(
 	xfs_inode_log_item_t	*iip,
 	int			stale)
 {
-	xfs_iunpin(iip->ili_inode);
+	struct xfs_inode	*ip = iip->ili_inode;
+
+	ASSERT(atomic_read(&ip->i_pincount) > 0);
+	if (atomic_dec_and_test(&ip->i_pincount))
+		wake_up(&ip->i_ipin_wait);
 }
 
 /* ARGSUSED */
@@ -568,7 +572,7 @@ xfs_inode_item_unpin_remove(
 	xfs_inode_log_item_t	*iip,
 	xfs_trans_t		*tp)
 {
-	xfs_iunpin(iip->ili_inode);
+	xfs_inode_item_unpin(iip, 0);
 }
 
 /*
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 3af02314c60..b1b801e4a28 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -106,6 +106,7 @@ xfs_bulkstat_one_iget(
 	buf->bs_dmevmask = dic->di_dmevmask;
 	buf->bs_dmstate = dic->di_dmstate;
 	buf->bs_aextents = dic->di_anextents;
+	buf->bs_forkoff = XFS_IFORK_BOFF(ip);
 
 	switch (dic->di_format) {
 	case XFS_DINODE_FMT_DEV:
@@ -176,6 +177,7 @@ xfs_bulkstat_one_dinode(
 	buf->bs_dmevmask = be32_to_cpu(dic->di_dmevmask);
 	buf->bs_dmstate = be16_to_cpu(dic->di_dmstate);
 	buf->bs_aextents = be16_to_cpu(dic->di_anextents);
+	buf->bs_forkoff = XFS_DFORK_BOFF(dic);
 
 	switch (dic->di_format) {
 	case XFS_DINODE_FMT_DEV:
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 4f16be4b6ee..e8fba92d7cd 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -60,7 +60,7 @@ STATIC int	 xlog_space_left(xlog_t *log, int cycle, int bytes);
 STATIC int	 xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
 STATIC void	 xlog_dealloc_log(xlog_t *log);
 STATIC int	 xlog_write(xfs_mount_t *mp, xfs_log_iovec_t region[],
-			    int nentries, xfs_log_ticket_t tic,
+			    int nentries, struct xlog_ticket *tic,
 			    xfs_lsn_t *start_lsn,
 			    xlog_in_core_t **commit_iclog,
 			    uint flags);
@@ -243,14 +243,14 @@ xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type)
  * out when the next write occurs.
  */
 xfs_lsn_t
-xfs_log_done(xfs_mount_t	*mp,
-	     xfs_log_ticket_t	xtic,
-	     void		**iclog,
-	     uint		flags)
+xfs_log_done(
+	struct xfs_mount	*mp,
+	struct xlog_ticket	*ticket,
+	struct xlog_in_core	**iclog,
+	uint			flags)
 {
-	xlog_t		*log    = mp->m_log;
-	xlog_ticket_t	*ticket = (xfs_log_ticket_t) xtic;
-	xfs_lsn_t	lsn	= 0;
+	struct log		*log = mp->m_log;
+	xfs_lsn_t		lsn = 0;
 
 	if (XLOG_FORCED_SHUTDOWN(log) ||
 	    /*
@@ -258,8 +258,7 @@ xfs_log_done(xfs_mount_t	*mp,
 	     * If we get an error, just continue and give back the log ticket.
 	     */
 	    (((ticket->t_flags & XLOG_TIC_INITED) == 0) &&
-	     (xlog_commit_record(mp, ticket,
-				 (xlog_in_core_t **)iclog, &lsn)))) {
+	     (xlog_commit_record(mp, ticket, iclog, &lsn)))) {
 		lsn = (xfs_lsn_t) -1;
 		if (ticket->t_flags & XLOG_TIC_PERM_RESERV) {
 			flags |= XFS_LOG_REL_PERM_RESERV;
@@ -289,7 +288,7 @@ xfs_log_done(xfs_mount_t	*mp,
 	}
 
 	return lsn;
-}	/* xfs_log_done */
+}
 
 /*
  * Attaches a new iclog I/O completion callback routine during
@@ -298,11 +297,11 @@ xfs_log_done(xfs_mount_t	*mp,
  * executing the callback at an appropriate time.
  */
 int
-xfs_log_notify(xfs_mount_t	  *mp,		/* mount of partition */
-	       void		  *iclog_hndl,	/* iclog to hang callback off */
-	       xfs_log_callback_t *cb)
+xfs_log_notify(
+	struct xfs_mount	*mp,
+	struct xlog_in_core	*iclog,
+	xfs_log_callback_t	*cb)
 {
-	xlog_in_core_t	  *iclog = (xlog_in_core_t *)iclog_hndl;
 	int	abortflg;
 
 	spin_lock(&iclog->ic_callback_lock);
@@ -316,16 +315,14 @@ xfs_log_notify(xfs_mount_t	  *mp,		/* mount of partition */
 	}
 	spin_unlock(&iclog->ic_callback_lock);
 	return abortflg;
-}	/* xfs_log_notify */
+}
 
 int
-xfs_log_release_iclog(xfs_mount_t *mp,
-		      void	  *iclog_hndl)
+xfs_log_release_iclog(
+	struct xfs_mount	*mp,
+	struct xlog_in_core	*iclog)
 {
-	xlog_t *log = mp->m_log;
-	xlog_in_core_t	  *iclog = (xlog_in_core_t *)iclog_hndl;
-
-	if (xlog_state_release_iclog(log, iclog)) {
+	if (xlog_state_release_iclog(mp->m_log, iclog)) {
 		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
 		return EIO;
 	}
@@ -344,17 +341,18 @@ xfs_log_release_iclog(xfs_mount_t *mp,
  * reservation, we prevent over allocation problems.
  */
 int
-xfs_log_reserve(xfs_mount_t	 *mp,
-		int		 unit_bytes,
-		int		 cnt,
-		xfs_log_ticket_t *ticket,
-		__uint8_t	 client,
-		uint		 flags,
-		uint		 t_type)
+xfs_log_reserve(
+	struct xfs_mount	*mp,
+	int		 	unit_bytes,
+	int		 	cnt,
+	struct xlog_ticket	**ticket,
+	__uint8_t	 	client,
+	uint		 	flags,
+	uint		 	t_type)
 {
-	xlog_t		*log = mp->m_log;
-	xlog_ticket_t	*internal_ticket;
-	int		retval = 0;
+	struct log		*log = mp->m_log;
+	struct xlog_ticket	*internal_ticket;
+	int			retval = 0;
 
 	ASSERT(client == XFS_TRANSACTION || client == XFS_LOG);
 	ASSERT((flags & XFS_LOG_NOSLEEP) == 0);
@@ -367,7 +365,7 @@ xfs_log_reserve(xfs_mount_t	 *mp,
 
 	if (*ticket != NULL) {
 		ASSERT(flags & XFS_LOG_PERM_RESERV);
-		internal_ticket = (xlog_ticket_t *)*ticket;
+		internal_ticket = *ticket;
 
 		trace_xfs_log_reserve(log, internal_ticket);
 
@@ -519,7 +517,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	xlog_in_core_t	 *first_iclog;
 #endif
 	xfs_log_iovec_t  reg[1];
-	xfs_log_ticket_t tic = NULL;
+	xlog_ticket_t	*tic = NULL;
 	xfs_lsn_t	 lsn;
 	int		 error;
 
@@ -656,24 +654,24 @@ xfs_log_unmount(xfs_mount_t *mp)
  * transaction occur with one call to xfs_log_write().
  */
 int
-xfs_log_write(xfs_mount_t *	mp,
-	      xfs_log_iovec_t	reg[],
-	      int		nentries,
-	      xfs_log_ticket_t	tic,
-	      xfs_lsn_t		*start_lsn)
+xfs_log_write(
+	struct xfs_mount	*mp,
+	struct xfs_log_iovec	reg[],
+	int			nentries,
+	struct xlog_ticket	*tic,
+	xfs_lsn_t		*start_lsn)
 {
-	int	error;
-	xlog_t *log = mp->m_log;
+	struct log		*log = mp->m_log;
+	int			error;
 
 	if (XLOG_FORCED_SHUTDOWN(log))
 		return XFS_ERROR(EIO);
 
-	if ((error = xlog_write(mp, reg, nentries, tic, start_lsn, NULL, 0))) {
+	error = xlog_write(mp, reg, nentries, tic, start_lsn, NULL, 0);
+	if (error)
 		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
-	}
 	return error;
-}	/* xfs_log_write */
-
+}
 
 void
 xfs_log_move_tail(xfs_mount_t	*mp,
@@ -1642,16 +1640,16 @@ xlog_print_tic_res(xfs_mount_t *mp, xlog_ticket_t *ticket)
  *	bytes have been written out.
  */
 STATIC int
-xlog_write(xfs_mount_t *	mp,
-	   xfs_log_iovec_t	reg[],
-	   int			nentries,
-	   xfs_log_ticket_t	tic,
-	   xfs_lsn_t		*start_lsn,
-	   xlog_in_core_t	**commit_iclog,
-	   uint			flags)
+xlog_write(
+	struct xfs_mount	*mp,
+	struct xfs_log_iovec	reg[],
+	int			nentries,
+	struct xlog_ticket	*ticket,
+	xfs_lsn_t		*start_lsn,
+	struct xlog_in_core	**commit_iclog,
+	uint			flags)
 {
     xlog_t	     *log = mp->m_log;
-    xlog_ticket_t    *ticket = (xlog_ticket_t *)tic;
     xlog_in_core_t   *iclog = NULL;  /* ptr to current in-core log */
     xlog_op_header_t *logop_head;    /* ptr to log operation header */
     __psint_t	     ptr;	     /* copy address into data region */
@@ -1765,7 +1763,7 @@ xlog_write(xfs_mount_t *	mp,
 	    default:
 		xfs_fs_cmn_err(CE_WARN, mp,
 		    "Bad XFS transaction clientid 0x%x in ticket 0x%p",
-		    logop_head->oh_clientid, tic);
+		    logop_head->oh_clientid, ticket);
 		return XFS_ERROR(EIO);
 	    }
 
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 7074be9d13e..97a24c7795a 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -110,8 +110,6 @@ typedef struct xfs_log_iovec {
 	uint		i_type;		/* type of region */
 } xfs_log_iovec_t;
 
-typedef void* xfs_log_ticket_t;
-
 /*
  * Structure used to pass callback function and the function's argument
  * to the log manager.
@@ -126,10 +124,12 @@ typedef struct xfs_log_callback {
 #ifdef __KERNEL__
 /* Log manager interfaces */
 struct xfs_mount;
+struct xlog_in_core;
 struct xlog_ticket;
+
 xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
-		       xfs_log_ticket_t ticket,
-		       void		**iclog,
+		       struct xlog_ticket *ticket,
+		       struct xlog_in_core **iclog,
 		       uint		flags);
 int	  _xfs_log_force(struct xfs_mount *mp,
 			 uint		flags,
@@ -151,21 +151,21 @@ int	  xfs_log_mount_finish(struct xfs_mount *mp);
 void	  xfs_log_move_tail(struct xfs_mount	*mp,
 			    xfs_lsn_t		tail_lsn);
 int	  xfs_log_notify(struct xfs_mount	*mp,
-			 void			*iclog,
+			 struct xlog_in_core	*iclog,
 			 xfs_log_callback_t	*callback_entry);
 int	  xfs_log_release_iclog(struct xfs_mount *mp,
-			 void			 *iclog_hndl);
+			 struct xlog_in_core	 *iclog);
 int	  xfs_log_reserve(struct xfs_mount *mp,
 			  int		   length,
 			  int		   count,
-			  xfs_log_ticket_t *ticket,
+			  struct xlog_ticket **ticket,
 			  __uint8_t	   clientid,
 			  uint		   flags,
 			  uint		   t_type);
 int	  xfs_log_write(struct xfs_mount *mp,
 			xfs_log_iovec_t  region[],
 			int		 nentries,
-			xfs_log_ticket_t ticket,
+			struct xlog_ticket *ticket,
 			xfs_lsn_t	 *start_lsn);
 int	  xfs_log_unmount_write(struct xfs_mount *mp);
 void      xfs_log_unmount(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 6afaaeb2950..e79b56b4bca 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1097,13 +1097,15 @@ xfs_default_resblks(xfs_mount_t *mp)
 	__uint64_t resblks;
 
 	/*
-	 * We default to 5% or 1024 fsbs of space reserved, whichever is smaller.
-	 * This may drive us straight to ENOSPC on mount, but that implies
-	 * we were already there on the last unmount. Warn if this occurs.
+	 * We default to 5% or 8192 fsbs of space reserved, whichever is
+	 * smaller.  This is intended to cover concurrent allocation
+	 * transactions when we initially hit enospc. These each require a 4
+	 * block reservation. Hence by default we cover roughly 2000 concurrent
+	 * allocation reservations.
 	 */
 	resblks = mp->m_sb.sb_dblocks;
 	do_div(resblks, 20);
-	resblks = min_t(__uint64_t, resblks, 1024);
+	resblks = min_t(__uint64_t, resblks, 8192);
 	return resblks;
 }
 
@@ -1417,6 +1419,9 @@ xfs_mountfs(
 	 * when at ENOSPC. This is needed for operations like create with
 	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
 	 * are not allowed to use this reserved space.
+	 *
+	 * This may drive us straight to ENOSPC on mount, but that implies
+	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		resblks = xfs_default_resblks(mp);
@@ -1725,26 +1730,30 @@ xfs_mod_incore_sb_unlocked(
 				lcounter += rem;
 			}
 		} else {				/* Taking blocks away */
-
 			lcounter += delta;
+			if (lcounter >= 0) {
+				mp->m_sb.sb_fdblocks = lcounter +
+							XFS_ALLOC_SET_ASIDE(mp);
+				return 0;
+			}
 
-		/*
-		 * If were out of blocks, use any available reserved blocks if
-		 * were allowed to.
-		 */
+			/*
+			 * We are out of blocks, use any available reserved
+			 * blocks if were allowed to.
+			 */
+			if (!rsvd)
+				return XFS_ERROR(ENOSPC);
 
-			if (lcounter < 0) {
-				if (rsvd) {
-					lcounter = (long long)mp->m_resblks_avail + delta;
-					if (lcounter < 0) {
-						return XFS_ERROR(ENOSPC);
-					}
-					mp->m_resblks_avail = lcounter;
-					return 0;
-				} else {	/* not reserved */
-					return XFS_ERROR(ENOSPC);
-				}
+			lcounter = (long long)mp->m_resblks_avail + delta;
+			if (lcounter >= 0) {
+				mp->m_resblks_avail = lcounter;
+				return 0;
 			}
+			printk_once(KERN_WARNING
+				"Filesystem \"%s\": reserve blocks depleted! "
+				"Consider increasing reserve pool size.",
+				mp->m_fsname);
+			return XFS_ERROR(ENOSPC);
 		}
 
 		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
@@ -2052,6 +2061,26 @@ xfs_mount_log_sb(
 	return error;
 }
 
+/*
+ * If the underlying (data/log/rt) device is readonly, there are some
+ * operations that cannot proceed.
+ */
+int
+xfs_dev_is_read_only(
+	struct xfs_mount	*mp,
+	char			*message)
+{
+	if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
+	    xfs_readonly_buftarg(mp->m_logdev_targp) ||
+	    (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
+		cmn_err(CE_NOTE,
+			"XFS: %s required on read-only device.", message);
+		cmn_err(CE_NOTE,
+			"XFS: write access unavailable, cannot proceed.");
+		return EROFS;
+	}
+	return 0;
+}
 
 #ifdef HAVE_PERCPU_SB
 /*
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 14dafd60823..4fa0bc7b983 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -436,6 +436,8 @@ extern void	xfs_freesb(xfs_mount_t *);
 extern int	xfs_fs_writable(xfs_mount_t *);
 extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t);
 
+extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
+
 extern int	xfs_dmops_get(struct xfs_mount *);
 extern void	xfs_dmops_put(struct xfs_mount *);
 
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index be942d4e332..f73e358bae8 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -796,7 +796,7 @@ _xfs_trans_commit(
 	int			sync;
 #define	XFS_TRANS_LOGVEC_COUNT	16
 	xfs_log_iovec_t		log_vector_fast[XFS_TRANS_LOGVEC_COUNT];
-	void			*commit_iclog;
+	struct xlog_in_core	*commit_iclog;
 	int			shutdown;
 
 	commit_lsn = -1;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index c93e3a10285..79c8bab9dff 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -910,7 +910,7 @@ typedef struct xfs_trans {
 	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
-	xfs_log_ticket_t	t_ticket;	/* log mgr ticket */
+	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	xfs_lsn_t		t_lsn;		/* log seq num of start of
 						 * transaction. */
 	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 5ffd544434e..fb586360d1c 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -46,6 +46,65 @@ STATIC xfs_buf_t *xfs_trans_buf_item_match(xfs_trans_t *, xfs_buftarg_t *,
 STATIC xfs_buf_t *xfs_trans_buf_item_match_all(xfs_trans_t *, xfs_buftarg_t *,
 		xfs_daddr_t, int);
 
+/*
+ * Add the locked buffer to the transaction.
+ *
+ * The buffer must be locked, and it cannot be associated with any
+ * transaction.
+ *
+ * If the buffer does not yet have a buf log item associated with it,
+ * then allocate one for it.  Then add the buf item to the transaction.
+ */
+STATIC void
+_xfs_trans_bjoin(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
+	int			reset_recur)
+{
+	struct xfs_buf_log_item	*bip;
+
+	ASSERT(XFS_BUF_ISBUSY(bp));
+	ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL);
+
+	/*
+	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
+	 * it doesn't have one yet, then allocate one and initialize it.
+	 * The checks to see if one is there are in xfs_buf_item_init().
+	 */
+	xfs_buf_item_init(bp, tp->t_mountp);
+	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
+	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
+	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
+	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
+	if (reset_recur)
+		bip->bli_recur = 0;
+
+	/*
+	 * Take a reference for this transaction on the buf item.
+	 */
+	atomic_inc(&bip->bli_refcount);
+
+	/*
+	 * Get a log_item_desc to point at the new item.
+	 */
+	(void) xfs_trans_add_item(tp, (xfs_log_item_t *)bip);
+
+	/*
+	 * Initialize b_fsprivate2 so we can find it with incore_match()
+	 * in xfs_trans_get_buf() and friends above.
+	 */
+	XFS_BUF_SET_FSPRIVATE2(bp, tp);
+
+}
+
+void
+xfs_trans_bjoin(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	_xfs_trans_bjoin(tp, bp, 0);
+	trace_xfs_trans_bjoin(bp->b_fspriv);
+}
 
 /*
  * Get and lock the buffer for the caller if it is not already
@@ -132,40 +191,8 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 
 	ASSERT(!XFS_BUF_GETERROR(bp));
 
-	/*
-	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
-	 * it doesn't have one yet, then allocate one and initialize it.
-	 * The checks to see if one is there are in xfs_buf_item_init().
-	 */
-	xfs_buf_item_init(bp, tp->t_mountp);
-
-	/*
-	 * Set the recursion count for the buffer within this transaction
-	 * to 0.
-	 */
-	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*);
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
-	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-	bip->bli_recur = 0;
-
-	/*
-	 * Take a reference for this transaction on the buf item.
-	 */
-	atomic_inc(&bip->bli_refcount);
-
-	/*
-	 * Get a log_item_desc to point at the new item.
-	 */
-	(void) xfs_trans_add_item(tp, (xfs_log_item_t*)bip);
-
-	/*
-	 * Initialize b_fsprivate2 so we can find it with incore_match()
-	 * above.
-	 */
-	XFS_BUF_SET_FSPRIVATE2(bp, tp);
-
-	trace_xfs_trans_get_buf(bip);
+	_xfs_trans_bjoin(tp, bp, 1);
+	trace_xfs_trans_get_buf(bp->b_fspriv);
 	return (bp);
 }
 
@@ -210,44 +237,11 @@ xfs_trans_getsb(xfs_trans_t	*tp,
 	}
 
 	bp = xfs_getsb(mp, flags);
-	if (bp == NULL) {
+	if (bp == NULL)
 		return NULL;
-	}
-
-	/*
-	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
-	 * it doesn't have one yet, then allocate one and initialize it.
-	 * The checks to see if one is there are in xfs_buf_item_init().
-	 */
-	xfs_buf_item_init(bp, mp);
-
-	/*
-	 * Set the recursion count for the buffer within this transaction
-	 * to 0.
-	 */
-	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*);
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
-	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-	bip->bli_recur = 0;
-
-	/*
-	 * Take a reference for this transaction on the buf item.
-	 */
-	atomic_inc(&bip->bli_refcount);
-
-	/*
-	 * Get a log_item_desc to point at the new item.
-	 */
-	(void) xfs_trans_add_item(tp, (xfs_log_item_t*)bip);
-
-	/*
-	 * Initialize b_fsprivate2 so we can find it with incore_match()
-	 * above.
-	 */
-	XFS_BUF_SET_FSPRIVATE2(bp, tp);
 
-	trace_xfs_trans_getsb(bip);
+	_xfs_trans_bjoin(tp, bp, 1);
+	trace_xfs_trans_getsb(bp->b_fspriv);
 	return (bp);
 }
 
@@ -425,40 +419,9 @@ xfs_trans_read_buf(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		goto shutdown_abort;
 
-	/*
-	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
-	 * it doesn't have one yet, then allocate one and initialize it.
-	 * The checks to see if one is there are in xfs_buf_item_init().
-	 */
-	xfs_buf_item_init(bp, tp->t_mountp);
+	_xfs_trans_bjoin(tp, bp, 1);
+	trace_xfs_trans_read_buf(bp->b_fspriv);
 
-	/*
-	 * Set the recursion count for the buffer within this transaction
-	 * to 0.
-	 */
-	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*);
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
-	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-	bip->bli_recur = 0;
-
-	/*
-	 * Take a reference for this transaction on the buf item.
-	 */
-	atomic_inc(&bip->bli_refcount);
-
-	/*
-	 * Get a log_item_desc to point at the new item.
-	 */
-	(void) xfs_trans_add_item(tp, (xfs_log_item_t*)bip);
-
-	/*
-	 * Initialize b_fsprivate2 so we can find it with incore_match()
-	 * above.
-	 */
-	XFS_BUF_SET_FSPRIVATE2(bp, tp);
-
-	trace_xfs_trans_read_buf(bip);
 	*bpp = bp;
 	return 0;
 
@@ -623,53 +586,6 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 }
 
 /*
- * Add the locked buffer to the transaction.
- * The buffer must be locked, and it cannot be associated with any
- * transaction.
- *
- * If the buffer does not yet have a buf log item associated with it,
- * then allocate one for it.  Then add the buf item to the transaction.
- */
-void
-xfs_trans_bjoin(xfs_trans_t	*tp,
-		xfs_buf_t	*bp)
-{
-	xfs_buf_log_item_t	*bip;
-
-	ASSERT(XFS_BUF_ISBUSY(bp));
-	ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL);
-
-	/*
-	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
-	 * it doesn't have one yet, then allocate one and initialize it.
-	 * The checks to see if one is there are in xfs_buf_item_init().
-	 */
-	xfs_buf_item_init(bp, tp->t_mountp);
-	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
-	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-
-	/*
-	 * Take a reference for this transaction on the buf item.
-	 */
-	atomic_inc(&bip->bli_refcount);
-
-	/*
-	 * Get a log_item_desc to point at the new item.
-	 */
-	(void) xfs_trans_add_item(tp, (xfs_log_item_t *)bip);
-
-	/*
-	 * Initialize b_fsprivate2 so we can find it with incore_match()
-	 * in xfs_trans_get_buf() and friends above.
-	 */
-	XFS_BUF_SET_FSPRIVATE2(bp, tp);
-
-	trace_xfs_trans_bjoin(bip);
-}
-
-/*
  * Mark the buffer as not needing to be unlocked when the buf item's
  * IOP_UNLOCK() routine is called.  The buffer must already be locked
  * and associated with the given transaction.
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index ddd2c5d1b85..9d376be0ea3 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -584,113 +584,6 @@ xfs_readlink(
 }
 
 /*
- * xfs_fsync
- *
- * This is called to sync the inode and its data out to disk.  We need to hold
- * the I/O lock while flushing the data, and the inode lock while flushing the
- * inode.  The inode lock CANNOT be held while flushing the data, so acquire
- * after we're done with that.
- */
-int
-xfs_fsync(
-	xfs_inode_t	*ip)
-{
-	xfs_trans_t	*tp;
-	int		error = 0;
-	int		log_flushed = 0;
-
-	xfs_itrace_entry(ip);
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return XFS_ERROR(EIO);
-
-	/*
-	 * We always need to make sure that the required inode state is safe on
-	 * disk.  The inode might be clean but we still might need to force the
-	 * log because of committed transactions that haven't hit the disk yet.
-	 * Likewise, there could be unflushed non-transactional changes to the
-	 * inode core that have to go to disk and this requires us to issue
-	 * a synchronous transaction to capture these changes correctly.
-	 *
-	 * This code relies on the assumption that if the update_* fields
-	 * of the inode are clear and the inode is unpinned then it is clean
-	 * and no action is required.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-
-	if (!ip->i_update_core) {
-		/*
-		 * Timestamps/size haven't changed since last inode flush or
-		 * inode transaction commit.  That means either nothing got
-		 * written or a transaction committed which caught the updates.
-		 * If the latter happened and the transaction hasn't hit the
-		 * disk yet, the inode will be still be pinned.  If it is,
-		 * force the log.
-		 */
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		if (xfs_ipincount(ip)) {
-			if (ip->i_itemp->ili_last_lsn) {
-				error = _xfs_log_force_lsn(ip->i_mount,
-						ip->i_itemp->ili_last_lsn,
-						XFS_LOG_SYNC, &log_flushed);
-			} else {
-				error = _xfs_log_force(ip->i_mount,
-						XFS_LOG_SYNC, &log_flushed);
-			}
-		}
-	} else	{
-		/*
-		 * Kick off a transaction to log the inode core to get the
-		 * updates.  The sync transaction will also force the log.
-		 */
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
-		error = xfs_trans_reserve(tp, 0,
-				XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			return error;
-		}
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-		/*
-		 * Note - it's possible that we might have pushed ourselves out
-		 * of the way during trans_reserve which would flush the inode.
-		 * But there's no guarantee that the inode buffer has actually
-		 * gone out yet (it's delwri).	Plus the buffer could be pinned
-		 * anyway if it's part of an inode in another recent
-		 * transaction.	 So we play it safe and fire off the
-		 * transaction anyway.
-		 */
-		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_trans_ihold(tp, ip);
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		xfs_trans_set_sync(tp);
-		error = _xfs_trans_commit(tp, 0, &log_flushed);
-
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-
-	if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
-		/*
-		 * If the log write didn't issue an ordered tag we need
-		 * to flush the disk cache for the data device now.
-		 */
-		if (!log_flushed)
-			xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
-
-		/*
-		 * If this inode is on the RT dev we need to flush that
-		 * cache as well.
-		 */
-		if (XFS_IS_REALTIME_INODE(ip))
-			xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
-	}
-
-	return error;
-}
-
-/*
  * Flags for xfs_free_eofblocks
  */
 #define XFS_FREE_EOF_TRYLOCK	(1<<0)
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index 774f40729ca..d8dfa8d0dad 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -21,7 +21,6 @@ int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags);
 #define XFS_ATTR_NOACL		0x08	/* Don't call xfs_acl_chmod */
 
 int xfs_readlink(struct xfs_inode *ip, char *link);
-int xfs_fsync(struct xfs_inode *ip);
 int xfs_release(struct xfs_inode *ip);
 int xfs_inactive(struct xfs_inode *ip);
 int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
@@ -50,18 +49,6 @@ int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
-ssize_t xfs_read(struct xfs_inode *ip, struct kiocb *iocb,
-		const struct iovec *iovp, unsigned int segs,
-		loff_t *offset, int ioflags);
-ssize_t xfs_splice_read(struct xfs_inode *ip, struct file *infilp,
-		loff_t *ppos, struct pipe_inode_info *pipe, size_t count,
-		int flags, int ioflags);
-ssize_t xfs_splice_write(struct xfs_inode *ip,
-		struct pipe_inode_info *pipe, struct file *outfilp,
-		loff_t *ppos, size_t count, int flags, int ioflags);
-ssize_t xfs_write(struct xfs_inode *xip, struct kiocb *iocb,
-		const struct iovec *iovp, unsigned int nsegs,
-		loff_t *offset, int ioflags);
 int xfs_bmap(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
 		int flags, struct xfs_iomap *iomapp, int *niomaps);
 void xfs_tosspages(struct xfs_inode *inode, xfs_off_t first,
@@ -72,4 +59,6 @@ int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, uint64_t flags, int fiopt);
 int xfs_wait_on_pages(struct xfs_inode *ip, xfs_off_t first, xfs_off_t last);
 
+int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
+
 #endif /* _XFS_VNODEOPS_H */