xfs: xfs_sync_data is redundant.

We don't do any data writeback from XFS any more - the VFS is
completely responsible for that, including for freeze. We can
replace the remaining caller with a VFS level function that
achieves the same thing, but without conflicting with current
writeback work.

This means we can remove the flush_work and xfs_flush_inodes() - the
VFS functionality completely replaces the internal flush queue for
doing this writeback work in a separate context to avoid stack
overruns.

This does have one complication - it cannot be called with page
locks held.  Hence move the flushing of delalloc space when ENOSPC
occurs back up into xfs_file_aio_buffered_write when we don't hold
any locks that will stall writeback.

Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to
trigger delalloc conversion fast enough to prevent spurious ENOSPC
whent here are hundreds of writers, thousands of small files and GBs
of free RAM.  Hence we need to use sync_sb_inodes() to block callers
while we wait for writeback like the previous xfs_flush_inodes
implementation did.

That means we have to hold the s_umount lock here, but because this
call can nest inside i_mutex (the parent directory in the create
case, held by the VFS), we have to use down_read_trylock() to avoid
potential deadlocks. In practice, this trylock will succeed on
almost every attempt as unmount/remount type operations are
exceedingly rare.

Note: we always need to pass a count of zero to
generic_file_buffered_write() as the previously written byte count.
We only do this by accident before this patch by the virtue of ret
always being zero when there are no errors. Make this explicit
rather than needing to specifically zero ret in the ENOSPC retry
case.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Tested-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ben Myers <bpm@sgi.com>

1 files changed, 0 insertions, 78 deletions

diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 2174555aebb2..6a2ada379166 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -217,51 +217,6 @@ xfs_inode_ag_iterator(
 }
 
 STATIC int
-xfs_sync_inode_data(
-	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	int			flags)
-{
-	struct inode		*inode = VFS_I(ip);
-	struct address_space *mapping = inode->i_mapping;
-	int			error = 0;
-
-	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-		return 0;
-
-	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
-		if (flags & SYNC_TRYLOCK)
-			return 0;
-		xfs_ilock(ip, XFS_IOLOCK_SHARED);
-	}
-
-	error = xfs_flush_pages(ip, 0, -1, (flags & SYNC_WAIT) ?
-				0 : XBF_ASYNC, FI_NONE);
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-	return error;
-}
-
-/*
- * Write out pagecache data for the whole filesystem.
- */
-STATIC int
-xfs_sync_data(
-	struct xfs_mount	*mp,
-	int			flags)
-{
-	int			error;
-
-	ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
-
-	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags);
-	if (error)
-		return XFS_ERROR(error);
-
-	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
-	return 0;
-}
-
-STATIC int
 xfs_sync_fsdata(
 	struct xfs_mount	*mp)
 {
@@ -415,39 +370,6 @@ xfs_reclaim_worker(
 	xfs_syncd_queue_reclaim(mp);
 }
 
-/*
- * Flush delayed allocate data, attempting to free up reserved space
- * from existing allocations.  At this point a new allocation attempt
- * has failed with ENOSPC and we are in the process of scratching our
- * heads, looking about for more room.
- *
- * Queue a new data flush if there isn't one already in progress and
- * wait for completion of the flush. This means that we only ever have one
- * inode flush in progress no matter how many ENOSPC events are occurring and
- * so will prevent the system from bogging down due to every concurrent
- * ENOSPC event scanning all the active inodes in the system for writeback.
- */
-void
-xfs_flush_inodes(
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-
-	queue_work(xfs_syncd_wq, &mp->m_flush_work);
-	flush_work(&mp->m_flush_work);
-}
-
-void
-xfs_flush_worker(
-	struct work_struct *work)
-{
-	struct xfs_mount *mp = container_of(work,
-					struct xfs_mount, m_flush_work);
-
-	xfs_sync_data(mp, SYNC_TRYLOCK);
-	xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT);
-}
-
 void
 __xfs_inode_set_reclaim_tag(
 	struct xfs_perag	*pag,