From 5d77c0dc0c05c2c65aee16149fae06831a118730 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@sandeen.net>
Date: Thu, 19 Nov 2009 15:52:00 +0000
Subject: xfs: make several more functions static

Just minor housekeeping, a lot more functions can be trivially made
static; others could if we reordered things a bit...

Signed-off-by: Eric Sandeen <sandeen@sandeen.net>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 1f5e4bb5e97..0f90bfe2815 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -351,7 +351,7 @@ xfs_commit_dummy_trans(
 	return error;
 }
 
-int
+STATIC int
 xfs_sync_fsdata(
 	struct xfs_mount	*mp,
 	int			flags)
-- 
cgit v1.2.3-70-g09d2


From 5017e97d52628fb8ae56e434e86ac2e72ddaac2b Mon Sep 17 00:00:00 2001
From: Dave Chinner <david@fromorbit.com>
Date: Mon, 11 Jan 2010 11:47:40 +0000
Subject: xfs: rename xfs_get_perag

xfs_get_perag is really getting the perag that an inode belongs to
based on it's inode number. Convert the use of this function to just
get the perag from a provided ag number.  Use this new function to
obtain the per-ag structure when traversing the per AG inode trees
for sync and reclaim.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c | 22 +++++++++++++---------
 fs/xfs/xfs_iget.c           | 10 +++++-----
 fs/xfs/xfs_inode.c          |  8 +++++---
 fs/xfs/xfs_mount.h          |  8 ++++----
 4 files changed, 27 insertions(+), 21 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 0f90bfe2815..cc964faf12e 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -90,14 +90,13 @@ xfs_inode_ag_lookup(
 STATIC int
 xfs_inode_ag_walk(
 	struct xfs_mount	*mp,
-	xfs_agnumber_t		ag,
+	struct xfs_perag	*pag,
 	int			(*execute)(struct xfs_inode *ip,
 					   struct xfs_perag *pag, int flags),
 	int			flags,
 	int			tag,
 	int			exclusive)
 {
-	struct xfs_perag	*pag = &mp->m_perag[ag];
 	uint32_t		first_index;
 	int			last_error = 0;
 	int			skipped;
@@ -141,8 +140,6 @@ restart:
 		delay(1);
 		goto restart;
 	}
-
-	xfs_put_perag(mp, pag);
 	return last_error;
 }
 
@@ -160,10 +157,16 @@ xfs_inode_ag_iterator(
 	xfs_agnumber_t		ag;
 
 	for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
-		if (!mp->m_perag[ag].pag_ici_init)
+		struct xfs_perag	*pag;
+
+		pag = xfs_perag_get(mp, ag);
+		if (!pag->pag_ici_init) {
+			xfs_perag_put(pag);
 			continue;
-		error = xfs_inode_ag_walk(mp, ag, execute, flags, tag,
+		}
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
 						exclusive);
+		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
 			if (error == EFSCORRUPTED)
@@ -690,16 +693,17 @@ void
 xfs_inode_set_reclaim_tag(
 	xfs_inode_t	*ip)
 {
-	xfs_mount_t	*mp = ip->i_mount;
-	xfs_perag_t	*pag = xfs_get_perag(mp, ip->i_ino);
+	struct xfs_mount *mp = ip->i_mount;
+	struct xfs_perag *pag;
 
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
 	read_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);
-	xfs_put_perag(mp, pag);
+	xfs_perag_put(pag);
 }
 
 void
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 155e798f30a..e281eb4a1c4 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -374,7 +374,7 @@ xfs_iget(
 		return EINVAL;
 
 	/* get the perag structure and ensure that it's inode capable */
-	pag = xfs_get_perag(mp, ino);
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
 	if (!pag->pagi_inodeok)
 		return EINVAL;
 	ASSERT(pag->pag_ici_init);
@@ -398,7 +398,7 @@ again:
 		if (error)
 			goto out_error_or_again;
 	}
-	xfs_put_perag(mp, pag);
+	xfs_perag_put(pag);
 
 	*ipp = ip;
 
@@ -417,7 +417,7 @@ out_error_or_again:
 		delay(1);
 		goto again;
 	}
-	xfs_put_perag(mp, pag);
+	xfs_perag_put(pag);
 	return error;
 }
 
@@ -488,12 +488,12 @@ xfs_ireclaim(
 	 * added to the tree assert that it's been there before to catch
 	 * problems with the inode life time early on.
 	 */
-	pag = xfs_get_perag(mp, ip->i_ino);
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
 	write_lock(&pag->pag_ici_lock);
 	if (!radix_tree_delete(&pag->pag_ici_root, agino))
 		ASSERT(0);
 	write_unlock(&pag->pag_ici_lock);
-	xfs_put_perag(mp, pag);
+	xfs_perag_put(pag);
 
 	/*
 	 * Here we do an (almost) spurious inode lock in order to coordinate
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ef77fd88c8e..bd3d81636d5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1946,8 +1946,9 @@ xfs_ifree_cluster(
 	xfs_inode_t		*ip, **ip_found;
 	xfs_inode_log_item_t	*iip;
 	xfs_log_item_t		*lip;
-	xfs_perag_t		*pag = xfs_get_perag(mp, inum);
+	struct xfs_perag	*pag;
 
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
 	if (mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp)) {
 		blks_per_cluster = 1;
 		ninodes = mp->m_sb.sb_inopblock;
@@ -2088,7 +2089,7 @@ xfs_ifree_cluster(
 	}
 
 	kmem_free(ip_found);
-	xfs_put_perag(mp, pag);
+	xfs_perag_put(pag);
 }
 
 /*
@@ -2675,7 +2676,7 @@ xfs_iflush_cluster(
 	xfs_buf_t	*bp)
 {
 	xfs_mount_t		*mp = ip->i_mount;
-	xfs_perag_t		*pag = xfs_get_perag(mp, ip->i_ino);
+	struct xfs_perag	*pag;
 	unsigned long		first_index, mask;
 	unsigned long		inodes_per_cluster;
 	int			ilist_size;
@@ -2686,6 +2687,7 @@ xfs_iflush_cluster(
 	int			bufwasdelwri;
 	int			i;
 
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
 	ASSERT(pag->pagi_inodeok);
 	ASSERT(pag->pag_ici_init);
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1df7e450296..f8a68a2319b 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -386,14 +386,14 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 /*
  * perag get/put wrappers for eventual ref counting
  */
-static inline xfs_perag_t *
-xfs_get_perag(struct xfs_mount *mp, xfs_ino_t ino)
+static inline struct xfs_perag *
+xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
 {
-	return &mp->m_perag[XFS_INO_TO_AGNO(mp, ino)];
+	return &mp->m_perag[agno];
 }
 
 static inline void
-xfs_put_perag(struct xfs_mount *mp, xfs_perag_t *pag)
+xfs_perag_put(struct xfs_perag *pag)
 {
 	/* nothing to see here, move along */
 }
-- 
cgit v1.2.3-70-g09d2


From b657fc82a3ca6d7ad16a59e81765f0fb0e86cdbb Mon Sep 17 00:00:00 2001
From: Dave Chinner <david@fromorbit.com>
Date: Mon, 11 Jan 2010 11:47:47 +0000
Subject: xfs: Kill filestreams cache flush

The filestreams cache flush is not needed in the sync code as it
does not affect data writeback, and it is now not used by the growfs
code, either, so kill it.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c |  3 ---
 fs/xfs/xfs_filestream.c     | 14 --------------
 fs/xfs/xfs_filestream.h     |  1 -
 fs/xfs/xfs_mru_cache.c      |  2 +-
 fs/xfs/xfs_mru_cache.h      |  1 -
 5 files changed, 1 insertion(+), 20 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index cc964faf12e..b58f8412dfe 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -451,9 +451,6 @@ xfs_quiesce_data(
 	xfs_sync_data(mp, SYNC_WAIT);
 	xfs_qm_sync(mp, SYNC_WAIT);
 
-	/* drop inode references pinned by filestreams */
-	xfs_filestream_flush(mp);
-
 	/* write superblock and hoover up shutdown errors */
 	error = xfs_sync_fsdata(mp, SYNC_WAIT);
 
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 914d00d0f11..390850ee660 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -454,20 +454,6 @@ xfs_filestream_unmount(
 	xfs_mru_cache_destroy(mp->m_filestream);
 }
 
-/*
- * If the mount point's m_perag tree is going to be modified, all
- * outstanding cache entries must be flushed to avoid accessing reference count
- * addresses that have been freed.  The call to xfs_filestream_flush() must be
- * made inside the block that holds the m_perag_lock in write mode to do the
- * reallocation.
- */
-void
-xfs_filestream_flush(
-	xfs_mount_t	*mp)
-{
-	xfs_mru_cache_flush(mp->m_filestream);
-}
-
 /*
  * Return the AG of the filestream the file or directory belongs to, or
  * NULLAGNUMBER otherwise.
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 58378b2ea03..260f757bbc5 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -135,7 +135,6 @@ int xfs_filestream_init(void);
 void xfs_filestream_uninit(void);
 int xfs_filestream_mount(struct xfs_mount *mp);
 void xfs_filestream_unmount(struct xfs_mount *mp);
-void xfs_filestream_flush(struct xfs_mount *mp);
 xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
 int xfs_filestream_associate(struct xfs_inode *dip, struct xfs_inode *ip);
 void xfs_filestream_deassociate(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 4b0613d99fa..45ce15dc5b2 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -398,7 +398,7 @@ exit:
  * guaranteed that all the free functions for all the elements have finished
  * executing and the reaper is not running.
  */
-void
+static void
 xfs_mru_cache_flush(
 	xfs_mru_cache_t		*mru)
 {
diff --git a/fs/xfs/xfs_mru_cache.h b/fs/xfs/xfs_mru_cache.h
index 5d439f34b0c..36dd3ec8b4e 100644
--- a/fs/xfs/xfs_mru_cache.h
+++ b/fs/xfs/xfs_mru_cache.h
@@ -42,7 +42,6 @@ void xfs_mru_cache_uninit(void);
 int xfs_mru_cache_create(struct xfs_mru_cache **mrup, unsigned int lifetime_ms,
 			     unsigned int grp_count,
 			     xfs_mru_cache_free_func_t free_func);
-void xfs_mru_cache_flush(xfs_mru_cache_t *mru);
 void xfs_mru_cache_destroy(struct xfs_mru_cache *mru);
 int xfs_mru_cache_insert(struct xfs_mru_cache *mru, unsigned long key,
 				void *value);
-- 
cgit v1.2.3-70-g09d2


From 0cadda1c5f194f98a05d252ff4385d86d2ed0862 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Tue, 19 Jan 2010 09:56:44 +0000
Subject: xfs: remove duplicate buffer flags

Currently we define aliases for the buffer flags in various
namespaces, which only adds confusion.  Remove all but the XBF_
flags to clean this up a bit.

Note that we still abuse XFS_B_ASYNC/XBF_ASYNC for some non-buffer
uses, but I'll clean that up later.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_buf.c     |  2 +-
 fs/xfs/linux-2.6/xfs_buf.h     | 22 ++++------------------
 fs/xfs/linux-2.6/xfs_fs_subr.c |  2 +-
 fs/xfs/linux-2.6/xfs_sync.c    |  4 ++--
 fs/xfs/quota/xfs_dquot.c       |  3 +--
 fs/xfs/quota/xfs_dquot_item.c  |  3 +--
 fs/xfs/xfs_alloc.c             |  2 +-
 fs/xfs/xfs_attr.c              | 12 +++++-------
 fs/xfs/xfs_attr_leaf.c         |  2 +-
 fs/xfs/xfs_btree.c             |  4 ++--
 fs/xfs/xfs_ialloc.c            |  2 +-
 fs/xfs/xfs_inode.c             | 20 ++++++++++----------
 fs/xfs/xfs_inode_item.c        |  2 +-
 fs/xfs/xfs_log_recover.c       |  8 ++++----
 fs/xfs/xfs_mount.c             |  4 ++--
 fs/xfs/xfs_trans_buf.c         | 27 ++++++++++++++-------------
 fs/xfs/xfs_vnodeops.c          |  4 ++--
 17 files changed, 53 insertions(+), 70 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index efd745bb888..730eff1e71a 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1169,7 +1169,7 @@ xfs_bioerror_relse(
 	XFS_BUF_STALE(bp);
 	XFS_BUF_CLR_IODONE_FUNC(bp);
 	XFS_BUF_CLR_BDSTRAT_FUNC(bp);
-	if (!(fl & XFS_B_ASYNC)) {
+	if (!(fl & XBF_ASYNC)) {
 		/*
 		 * Mark b_error and B_ERROR _both_.
 		 * Lot's of chunkcache code assumes that.
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 4f2ad66edb7..ea8c198f0c3 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -275,33 +275,19 @@ extern void xfs_buf_terminate(void);
 	({ char __b[BDEVNAME_SIZE]; bdevname((target)->bt_bdev, __b); __b; })
 
 
-#define XFS_B_ASYNC		XBF_ASYNC
-#define XFS_B_DELWRI		XBF_DELWRI
-#define XFS_B_READ		XBF_READ
-#define XFS_B_WRITE		XBF_WRITE
-#define XFS_B_STALE		XBF_STALE
-
-#define XFS_BUF_TRYLOCK		XBF_TRYLOCK
-#define XFS_INCORE_TRYLOCK	XBF_TRYLOCK
-#define XFS_BUF_LOCK		XBF_LOCK
-#define XFS_BUF_MAPPED		XBF_MAPPED
-
-#define BUF_BUSY		XBF_DONT_BLOCK
-
 #define XFS_BUF_BFLAGS(bp)	((bp)->b_flags)
 #define XFS_BUF_ZEROFLAGS(bp)	((bp)->b_flags &= \
 		~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI|XBF_ORDERED))
 
-#define XFS_BUF_STALE(bp)	((bp)->b_flags |= XFS_B_STALE)
-#define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XFS_B_STALE)
-#define XFS_BUF_ISSTALE(bp)	((bp)->b_flags & XFS_B_STALE)
+#define XFS_BUF_STALE(bp)	((bp)->b_flags |= XBF_STALE)
+#define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
+#define XFS_BUF_ISSTALE(bp)	((bp)->b_flags & XBF_STALE)
 #define XFS_BUF_SUPER_STALE(bp)	do {				\
 					XFS_BUF_STALE(bp);	\
 					xfs_buf_delwri_dequeue(bp);	\
 					XFS_BUF_DONE(bp);	\
 				} while (0)
 
-#define XFS_BUF_MANAGE		XBF_FS_MANAGED
 #define XFS_BUF_UNMANAGE(bp)	((bp)->b_flags &= ~XBF_FS_MANAGED)
 
 #define XFS_BUF_DELAYWRITE(bp)		((bp)->b_flags |= XBF_DELWRI)
@@ -390,7 +376,7 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
 
 #define xfs_biomove(bp, off, len, data, rw) \
 	    xfs_buf_iomove((bp), (off), (len), (data), \
-		((rw) == XFS_B_WRITE) ? XBRW_WRITE : XBRW_READ)
+		((rw) == XBF_WRITE) ? XBRW_WRITE : XBRW_READ)
 
 #define xfs_biozero(bp, off, len) \
 	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index 7501b85fd86..b6918d76bc7 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -79,7 +79,7 @@ xfs_flush_pages(
 		xfs_iflags_clear(ip, XFS_ITRUNCATED);
 		ret = -filemap_fdatawrite(mapping);
 	}
-	if (flags & XFS_B_ASYNC)
+	if (flags & XBF_ASYNC)
 		return ret;
 	ret2 = xfs_wait_on_pages(ip, first, last);
 	if (!ret)
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index b58f8412dfe..58c24be72c6 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -234,7 +234,7 @@ xfs_sync_inode_data(
 	}
 
 	error = xfs_flush_pages(ip, 0, -1, (flags & SYNC_WAIT) ?
-				0 : XFS_B_ASYNC, FI_NONE);
+				0 : XBF_ASYNC, FI_NONE);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
  out_wait:
@@ -370,7 +370,7 @@ xfs_sync_fsdata(
 	if (flags & SYNC_TRYLOCK) {
 		ASSERT(!(flags & SYNC_WAIT));
 
-		bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
+		bp = xfs_getsb(mp, XBF_TRYLOCK);
 		if (!bp)
 			goto out;
 
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index a447493690e..5756392ffde 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -1527,8 +1527,7 @@ xfs_qm_dqflock_pushbuf_wait(
 	 * the flush lock when the I/O completes.
 	 */
 	bp = xfs_incore(dqp->q_mount->m_ddev_targp, dqp->q_blkno,
-		    XFS_QI_DQCHUNKLEN(dqp->q_mount),
-		    XFS_INCORE_TRYLOCK);
+		    XFS_QI_DQCHUNKLEN(dqp->q_mount), XBF_TRYLOCK);
 	if (bp != NULL) {
 		if (XFS_BUF_ISDELAYWRITE(bp)) {
 			int	error;
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index d0d4a9a0bbd..37929d19ef4 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -237,8 +237,7 @@ xfs_qm_dquot_logitem_pushbuf(
 	}
 	mp = dqp->q_mount;
 	bp = xfs_incore(mp->m_ddev_targp, qip->qli_format.qlf_blkno,
-		    XFS_QI_DQCHUNKLEN(mp),
-		    XFS_INCORE_TRYLOCK);
+		    XFS_QI_DQCHUNKLEN(mp), XBF_TRYLOCK);
 	if (bp != NULL) {
 		if (XFS_BUF_ISDELAYWRITE(bp)) {
 			dopush = ((qip->qli_item.li_flags & XFS_LI_IN_AIL) &&
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 8aa181d6dd7..a27aeb7d9e7 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2180,7 +2180,7 @@ xfs_alloc_read_agf(
 	ASSERT(agno != NULLAGNUMBER);
 
 	error = xfs_read_agf(mp, tp, agno,
-			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XFS_BUF_TRYLOCK : 0,
+			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
 			bpp);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index f7b426a1b6e..b9c196a53c4 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -2015,15 +2015,14 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno,
-					     blkcnt,
-					     XFS_BUF_LOCK | XBF_DONT_BLOCK,
+					     blkcnt, XBF_LOCK | XBF_DONT_BLOCK,
 					     &bp);
 			if (error)
 				return(error);
 
 			tmp = (valuelen < XFS_BUF_SIZE(bp))
 				? valuelen : XFS_BUF_SIZE(bp);
-			xfs_biomove(bp, 0, tmp, dst, XFS_B_READ);
+			xfs_biomove(bp, 0, tmp, dst, XBF_READ);
 			xfs_buf_relse(bp);
 			dst += tmp;
 			valuelen -= tmp;
@@ -2149,13 +2148,13 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 		blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
 
 		bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt,
-				 XFS_BUF_LOCK | XBF_DONT_BLOCK);
+				 XBF_LOCK | XBF_DONT_BLOCK);
 		ASSERT(bp);
 		ASSERT(!XFS_BUF_GETERROR(bp));
 
 		tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen :
 							XFS_BUF_SIZE(bp);
-		xfs_biomove(bp, 0, tmp, src, XFS_B_WRITE);
+		xfs_biomove(bp, 0, tmp, src, XBF_WRITE);
 		if (tmp < XFS_BUF_SIZE(bp))
 			xfs_biozero(bp, tmp, XFS_BUF_SIZE(bp) - tmp);
 		if ((error = xfs_bwrite(mp, bp))) {/* GROT: NOTE: synchronous write */
@@ -2216,8 +2215,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args)
 		/*
 		 * If the "remote" value is in the cache, remove it.
 		 */
-		bp = xfs_incore(mp->m_ddev_targp, dblkno, blkcnt,
-				XFS_INCORE_TRYLOCK);
+		bp = xfs_incore(mp->m_ddev_targp, dblkno, blkcnt, XBF_TRYLOCK);
 		if (bp) {
 			XFS_BUF_STALE(bp);
 			XFS_BUF_UNDELAYWRITE(bp);
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 52519a20184..a90ce74fc25 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -2950,7 +2950,7 @@ xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
 						map.br_blockcount);
 			bp = xfs_trans_get_buf(*trans,
 					dp->i_mount->m_ddev_targp,
-					dblkno, dblkcnt, XFS_BUF_LOCK);
+					dblkno, dblkcnt, XBF_LOCK);
 			xfs_trans_binval(*trans, bp);
 			/*
 			 * Roll to next transaction.
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index 36a0992dd66..96be4b0f249 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -977,7 +977,7 @@ xfs_btree_get_buf_block(
 	xfs_daddr_t		d;
 
 	/* need to sort out how callers deal with failures first */
-	ASSERT(!(flags & XFS_BUF_TRYLOCK));
+	ASSERT(!(flags & XBF_TRYLOCK));
 
 	d = xfs_btree_ptr_to_daddr(cur, ptr);
 	*bpp = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d,
@@ -1008,7 +1008,7 @@ xfs_btree_read_buf_block(
 	int			error;
 
 	/* need to sort out how callers deal with failures first */
-	ASSERT(!(flags & XFS_BUF_TRYLOCK));
+	ASSERT(!(flags & XBF_TRYLOCK));
 
 	d = xfs_btree_ptr_to_daddr(cur, ptr);
 	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 52c9d006c0e..9d884c127bb 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -205,7 +205,7 @@ xfs_ialloc_inode_init(
 		d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * blks_per_cluster));
 		fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
 					 mp->m_bsize * blks_per_cluster,
-					 XFS_BUF_LOCK);
+					 XBF_LOCK);
 		ASSERT(fbuf);
 		ASSERT(!XFS_BUF_GETERROR(fbuf));
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0317b000ab4..bbb3bee8e93 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -151,7 +151,7 @@ xfs_imap_to_bp(
 				"an error %d on %s.  Returning error.",
 				error, mp->m_fsname);
 		} else {
-			ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+			ASSERT(buf_flags & XBF_TRYLOCK);
 		}
 		return error;
 	}
@@ -239,7 +239,7 @@ xfs_inotobp(
 	if (error)
 		return error;
 
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, imap_flags);
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XBF_LOCK, imap_flags);
 	if (error)
 		return error;
 
@@ -285,7 +285,7 @@ xfs_itobp(
 		return error;
 
 	if (!bp) {
-		ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+		ASSERT(buf_flags & XBF_TRYLOCK);
 		ASSERT(tp == NULL);
 		*bpp = NULL;
 		return EAGAIN;
@@ -807,7 +807,7 @@ xfs_iread(
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
 	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp,
-			       XFS_BUF_LOCK, iget_flags);
+			       XBF_LOCK, iget_flags);
 	if (error)
 		return error;
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -1751,7 +1751,7 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
 		if (error)
 			return error;
 
@@ -1833,7 +1833,7 @@ xfs_iunlink_remove(
 		 * of dealing with the buffer when there is no need to
 		 * change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -1895,7 +1895,7 @@ xfs_iunlink_remove(
 		 * Now last_ibp points to the buffer previous to us on
 		 * the unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -2040,7 +2040,7 @@ xfs_ifree_cluster(
 
 		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, 
 					mp->m_bsize * blks_per_cluster,
-					XFS_BUF_LOCK);
+					XBF_LOCK);
 
 		pre_flushed = 0;
 		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
@@ -2151,7 +2151,7 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
+	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XBF_LOCK);
 	if (error)
 		return error;
 
@@ -2952,7 +2952,7 @@ xfs_iflush(
 	 * Get the buffer containing the on-disk inode.
 	 */
 	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				noblock ? XFS_BUF_TRYLOCK : XFS_BUF_LOCK);
+				noblock ? XBF_TRYLOCK : XBF_LOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index f38855d21ea..6194fb5d377 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -785,7 +785,7 @@ xfs_inode_item_pushbuf(
 
 	mp = ip->i_mount;
 	bp = xfs_incore(mp->m_ddev_targp, iip->ili_format.ilf_blkno,
-		    iip->ili_format.ilf_len, XFS_INCORE_TRYLOCK);
+		    iip->ili_format.ilf_len, XBF_TRYLOCK);
 
 	if (bp != NULL) {
 		if (XFS_BUF_ISDELAYWRITE(bp)) {
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 65f1f137d78..97148f0c4bd 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2184,9 +2184,9 @@ xlog_recover_do_buffer_trans(
 	}
 
 	mp = log->l_mp;
-	buf_flags = XFS_BUF_LOCK;
+	buf_flags = XBF_LOCK;
 	if (!(flags & XFS_BLI_INODE_BUF))
-		buf_flags |= XFS_BUF_MAPPED;
+		buf_flags |= XBF_MAPPED;
 
 	bp = xfs_buf_read(mp->m_ddev_targp, blkno, len, buf_flags);
 	if (XFS_BUF_ISERROR(bp)) {
@@ -2288,7 +2288,7 @@ xlog_recover_do_inode_trans(
 	}
 
 	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len,
-			  XFS_BUF_LOCK);
+			  XBF_LOCK);
 	if (XFS_BUF_ISERROR(bp)) {
 		xfs_ioerror_alert("xlog_recover_do..(read#2)", mp,
 				  bp, in_f->ilf_blkno);
@@ -3146,7 +3146,7 @@ xlog_recover_process_one_iunlink(
 	/*
 	 * Get the on disk inode to find the next inode in the bucket.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XFS_BUF_LOCK);
+	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XBF_LOCK);
 	if (error)
 		goto fail_iput;
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d95bd1809f3..bb0154047e8 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -665,7 +665,7 @@ xfs_readsb(xfs_mount_t *mp, int flags)
 	 * access to the superblock.
 	 */
 	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-	extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;
+	extra_flags = XBF_LOCK | XBF_FS_MANAGED | XBF_MAPPED;
 
 	bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size),
 			  extra_flags);
@@ -1969,7 +1969,7 @@ xfs_getsb(
 
 	ASSERT(mp->m_sb_bp != NULL);
 	bp = mp->m_sb_bp;
-	if (flags & XFS_BUF_TRYLOCK) {
+	if (flags & XBF_TRYLOCK) {
 		if (!XFS_BUF_CPSEMA(bp)) {
 			return NULL;
 		}
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 49130628d5e..5ffd544434e 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -75,13 +75,14 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 	xfs_buf_log_item_t	*bip;
 
 	if (flags == 0)
-		flags = XFS_BUF_LOCK | XFS_BUF_MAPPED;
+		flags = XBF_LOCK | XBF_MAPPED;
 
 	/*
 	 * Default to a normal get_buf() call if the tp is NULL.
 	 */
 	if (tp == NULL)
-		return xfs_buf_get(target_dev, blkno, len, flags | BUF_BUSY);
+		return xfs_buf_get(target_dev, blkno, len,
+				   flags | XBF_DONT_BLOCK);
 
 	/*
 	 * If we find the buffer in the cache with this transaction
@@ -117,14 +118,14 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 	}
 
 	/*
-	 * We always specify the BUF_BUSY flag within a transaction so
-	 * that get_buf does not try to push out a delayed write buffer
+	 * We always specify the XBF_DONT_BLOCK flag within a transaction
+	 * so that get_buf does not try to push out a delayed write buffer
 	 * which might cause another transaction to take place (if the
 	 * buffer was delayed alloc).  Such recursive transactions can
 	 * easily deadlock with our current transaction as well as cause
 	 * us to run out of stack space.
 	 */
-	bp = xfs_buf_get(target_dev, blkno, len, flags | BUF_BUSY);
+	bp = xfs_buf_get(target_dev, blkno, len, flags | XBF_DONT_BLOCK);
 	if (bp == NULL) {
 		return NULL;
 	}
@@ -290,15 +291,15 @@ xfs_trans_read_buf(
 	int			error;
 
 	if (flags == 0)
-		flags = XFS_BUF_LOCK | XFS_BUF_MAPPED;
+		flags = XBF_LOCK | XBF_MAPPED;
 
 	/*
 	 * Default to a normal get_buf() call if the tp is NULL.
 	 */
 	if (tp == NULL) {
-		bp = xfs_buf_read(target, blkno, len, flags | BUF_BUSY);
+		bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
 		if (!bp)
-			return (flags & XFS_BUF_TRYLOCK) ?
+			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);
 
 		if (XFS_BUF_GETERROR(bp) != 0) {
@@ -385,14 +386,14 @@ xfs_trans_read_buf(
 	}
 
 	/*
-	 * We always specify the BUF_BUSY flag within a transaction so
-	 * that get_buf does not try to push out a delayed write buffer
+	 * We always specify the XBF_DONT_BLOCK flag within a transaction
+	 * so that get_buf does not try to push out a delayed write buffer
 	 * which might cause another transaction to take place (if the
 	 * buffer was delayed alloc).  Such recursive transactions can
 	 * easily deadlock with our current transaction as well as cause
 	 * us to run out of stack space.
 	 */
-	bp = xfs_buf_read(target, blkno, len, flags | BUF_BUSY);
+	bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
 	if (bp == NULL) {
 		*bpp = NULL;
 		return 0;
@@ -472,8 +473,8 @@ shutdown_abort:
 	if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
 		cmn_err(CE_NOTE, "about to pop assert, bp == 0x%p", bp);
 #endif
-	ASSERT((XFS_BUF_BFLAGS(bp) & (XFS_B_STALE|XFS_B_DELWRI)) !=
-						(XFS_B_STALE|XFS_B_DELWRI));
+	ASSERT((XFS_BUF_BFLAGS(bp) & (XBF_STALE|XBF_DELWRI)) !=
+				     (XBF_STALE|XBF_DELWRI));
 
 	trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
 	xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 9f7c001ef46..4da96cdffb7 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -256,7 +256,7 @@ xfs_setattr(
 		    iattr->ia_size > ip->i_d.di_size) {
 			code = xfs_flush_pages(ip,
 					ip->i_d.di_size, iattr->ia_size,
-					XFS_B_ASYNC, FI_NONE);
+					XBF_ASYNC, FI_NONE);
 		}
 
 		/* wait for all I/O to complete */
@@ -1096,7 +1096,7 @@ xfs_release(
 		 */
 		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
 		if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
-			xfs_flush_pages(ip, 0, -1, XFS_B_ASYNC, FI_NONE);
+			xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
 	}
 
 	if (ip->i_d.di_nlink != 0) {
-- 
cgit v1.2.3-70-g09d2


From a14a348bff2f99471a28e5928eb6801224c053d8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Tue, 19 Jan 2010 09:56:46 +0000
Subject: xfs: cleanup up xfs_log_force calling conventions

Remove the XFS_LOG_FORCE argument which was always set, and the
XFS_LOG_URGE define, which was never used.

Split xfs_log_force into a two helpers - xfs_log_force which forces
the whole log, and xfs_log_force_lsn which forces up to the
specified LSN.  The underlying implementations already were entirely
separate, as were the users.

Also re-indent the new _xfs_log_force/_xfs_log_force which
previously had a weird coding style.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c    |  17 +--
 fs/xfs/quota/xfs_dquot.c       |  10 +-
 fs/xfs/quota/xfs_dquot_item.c  |   9 +-
 fs/xfs/quota/xfs_qm_syscalls.c |   4 +-
 fs/xfs/xfs_alloc.c             |   2 +-
 fs/xfs/xfs_inode.c             |   9 +-
 fs/xfs/xfs_inode_item.c        |   7 +-
 fs/xfs/xfs_log.c               | 312 ++++++++++++++++++++---------------------
 fs/xfs/xfs_log.h               |  15 +-
 fs/xfs/xfs_log_recover.c       |   3 +-
 fs/xfs/xfs_mount.c             |   4 +-
 fs/xfs/xfs_trans.c             |   5 +-
 fs/xfs/xfs_trans_ail.c         |   2 +-
 fs/xfs/xfs_vnodeops.c          |   5 +-
 14 files changed, 193 insertions(+), 211 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 58c24be72c6..c9b863eacab 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -296,10 +296,7 @@ xfs_sync_data(
 	if (error)
 		return XFS_ERROR(error);
 
-	xfs_log_force(mp, 0,
-		      (flags & SYNC_WAIT) ?
-		       XFS_LOG_FORCE | XFS_LOG_SYNC :
-		       XFS_LOG_FORCE);
+	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
 	return 0;
 }
 
@@ -325,10 +322,6 @@ xfs_commit_dummy_trans(
 	struct xfs_inode	*ip = mp->m_rootip;
 	struct xfs_trans	*tp;
 	int			error;
-	int			log_flags = XFS_LOG_FORCE;
-
-	if (flags & SYNC_WAIT)
-		log_flags |= XFS_LOG_SYNC;
 
 	/*
 	 * Put a dummy transaction in the log to tell recovery
@@ -350,7 +343,7 @@ xfs_commit_dummy_trans(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	/* the log force ensures this transaction is pushed to disk */
-	xfs_log_force(mp, 0, log_flags);
+	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
 	return error;
 }
 
@@ -390,7 +383,7 @@ xfs_sync_fsdata(
 		 * become pinned in between there and here.
 		 */
 		if (XFS_BUF_ISPINNED(bp))
-			xfs_log_force(mp, 0, XFS_LOG_FORCE);
+			xfs_log_force(mp, 0);
 	}
 
 
@@ -575,7 +568,7 @@ xfs_flush_inodes(
 	igrab(inode);
 	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
 	wait_for_completion(&completion);
-	xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
+	xfs_log_force(ip->i_mount, XFS_LOG_SYNC);
 }
 
 /*
@@ -591,7 +584,7 @@ xfs_sync_worker(
 	int		error;
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+		xfs_log_force(mp, 0);
 		xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
 		/* dgc: errors ignored here */
 		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index 5756392ffde..f9baeedbfdf 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -1248,7 +1248,7 @@ xfs_qm_dqflush(
 	 */
 	if (XFS_BUF_ISPINNED(bp)) {
 		trace_xfs_dqflush_force(dqp);
-		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+		xfs_log_force(mp, 0);
 	}
 
 	if (flags & XFS_QMOPT_DELWRI) {
@@ -1531,11 +1531,9 @@ xfs_qm_dqflock_pushbuf_wait(
 	if (bp != NULL) {
 		if (XFS_BUF_ISDELAYWRITE(bp)) {
 			int	error;
-			if (XFS_BUF_ISPINNED(bp)) {
-				xfs_log_force(dqp->q_mount,
-					      (xfs_lsn_t)0,
-					      XFS_LOG_FORCE);
-			}
+
+			if (XFS_BUF_ISPINNED(bp))
+				xfs_log_force(dqp->q_mount, 0);
 			error = xfs_bawrite(dqp->q_mount, bp);
 			if (error)
 				xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index 116580d52fa..1b564376d50 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -190,7 +190,7 @@ xfs_qm_dqunpin_wait(
 	/*
 	 * Give the log a push so we don't wait here too long.
 	 */
-	xfs_log_force(dqp->q_mount, (xfs_lsn_t)0, XFS_LOG_FORCE);
+	xfs_log_force(dqp->q_mount, 0);
 	wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
 }
 
@@ -245,10 +245,9 @@ xfs_qm_dquot_logitem_pushbuf(
 			qip->qli_pushbuf_flag = 0;
 			xfs_dqunlock(dqp);
 
-			if (XFS_BUF_ISPINNED(bp)) {
-				xfs_log_force(mp, (xfs_lsn_t)0,
-					      XFS_LOG_FORCE);
-			}
+			if (XFS_BUF_ISPINNED(bp))
+				xfs_log_force(mp, 0);
+
 			if (dopush) {
 				int	error;
 #ifdef XFSRACEDEBUG
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 873e07e2907..5d0ee8d492d 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -1192,9 +1192,9 @@ xfs_qm_internalqcheck(
 	if (! XFS_IS_QUOTA_ON(mp))
 		return XFS_ERROR(ESRCH);
 
-	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
+	xfs_log_force(mp, XFS_LOG_SYNC);
 	XFS_bflush(mp->m_ddev_targp);
-	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
+	xfs_log_force(mp, XFS_LOG_SYNC);
 	XFS_bflush(mp->m_ddev_targp);
 
 	mutex_lock(&qcheck_lock);
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index a27aeb7d9e7..94cddbfb256 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2601,5 +2601,5 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 	 * transaction that freed the block
 	 */
 	if (lsn)
-		xfs_log_force(tp->t_mountp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC);
+		xfs_log_force_lsn(tp->t_mountp, lsn, XFS_LOG_SYNC);
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index bbb3bee8e93..d0d1b5a0518 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2484,8 +2484,11 @@ __xfs_iunpin_wait(
 		return;
 
 	/* Give the log a push to start the unpinning I/O */
-	xfs_log_force(ip->i_mount, (iip && iip->ili_last_lsn) ?
-				iip->ili_last_lsn : 0, XFS_LOG_FORCE);
+	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);
+
 	if (wait)
 		wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
 }
@@ -2970,7 +2973,7 @@ xfs_iflush(
 	 * get stuck waiting in the write for too long.
 	 */
 	if (XFS_BUF_ISPINNED(bp))
-		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+		xfs_log_force(mp, 0);
 
 	/*
 	 * inode clustering:
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index da4cac67bda..48ec1c0b23c 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -804,10 +804,9 @@ xfs_inode_item_pushbuf(
 
 			trace_xfs_inode_item_push(bp, _RET_IP_);
 
-			if (XFS_BUF_ISPINNED(bp)) {
-				xfs_log_force(mp, (xfs_lsn_t)0,
-					      XFS_LOG_FORCE);
-			}
+			if (XFS_BUF_ISPINNED(bp))
+				xfs_log_force(mp, 0);
+
 			if (dopush) {
 				int	error;
 				error = xfs_bawrite(mp, bp);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 20118ddadef..4f16be4b6ee 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -79,11 +79,6 @@ STATIC int  xlog_state_release_iclog(xlog_t		*log,
 STATIC void xlog_state_switch_iclogs(xlog_t		*log,
 				     xlog_in_core_t *iclog,
 				     int		eventual_size);
-STATIC int  xlog_state_sync(xlog_t			*log,
-			    xfs_lsn_t 			lsn,
-			    uint			flags,
-			    int				*log_flushed);
-STATIC int  xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed);
 STATIC void xlog_state_want_sync(xlog_t	*log, xlog_in_core_t *iclog);
 
 /* local functions to manipulate grant head */
@@ -296,65 +291,6 @@ xfs_log_done(xfs_mount_t	*mp,
 	return lsn;
 }	/* xfs_log_done */
 
-
-/*
- * Force the in-core log to disk.  If flags == XFS_LOG_SYNC,
- *	the force is done synchronously.
- *
- * Asynchronous forces are implemented by setting the WANT_SYNC
- * bit in the appropriate in-core log and then returning.
- *
- * Synchronous forces are implemented with a signal variable. All callers
- * to force a given lsn to disk will wait on a the sv attached to the
- * specific in-core log.  When given in-core log finally completes its
- * write to disk, that thread will wake up all threads waiting on the
- * sv.
- */
-int
-_xfs_log_force(
-	xfs_mount_t	*mp,
-	xfs_lsn_t	lsn,
-	uint		flags,
-	int		*log_flushed)
-{
-	xlog_t		*log = mp->m_log;
-	int		dummy;
-
-	if (!log_flushed)
-		log_flushed = &dummy;
-
-	ASSERT(flags & XFS_LOG_FORCE);
-
-	XFS_STATS_INC(xs_log_force);
-
-	if (log->l_flags & XLOG_IO_ERROR)
-		return XFS_ERROR(EIO);
-	if (lsn == 0)
-		return xlog_state_sync_all(log, flags, log_flushed);
-	else
-		return xlog_state_sync(log, lsn, flags, log_flushed);
-}	/* _xfs_log_force */
-
-/*
- * Wrapper for _xfs_log_force(), to be used when caller doesn't care
- * about errors or whether the log was flushed or not. This is the normal
- * interface to use when trying to unpin items or move the log forward.
- */
-void
-xfs_log_force(
-	xfs_mount_t	*mp,
-	xfs_lsn_t	lsn,
-	uint		flags)
-{
-	int	error;
-	error = _xfs_log_force(mp, lsn, flags, NULL);
-	if (error) {
-		xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
-			"error %d returned.", error);
-	}
-}
-
-
 /*
  * Attaches a new iclog I/O completion callback routine during
  * transaction commit.  If the log is in error state, a non-zero
@@ -601,7 +537,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return 0;
 
-	error = _xfs_log_force(mp, 0, XFS_LOG_FORCE|XFS_LOG_SYNC, NULL);
+	error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
 	ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log)));
 
 #ifdef DEBUG
@@ -2853,7 +2789,6 @@ xlog_state_switch_iclogs(xlog_t		*log,
 	log->l_iclog = iclog->ic_next;
 }	/* xlog_state_switch_iclogs */
 
-
 /*
  * Write out all data in the in-core log as of this exact moment in time.
  *
@@ -2881,11 +2816,17 @@ xlog_state_switch_iclogs(xlog_t		*log,
  *	   b) when we return from flushing out this iclog, it is still
  *		not in the active nor dirty state.
  */
-STATIC int
-xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed)
+int
+_xfs_log_force(
+	struct xfs_mount	*mp,
+	uint			flags,
+	int			*log_flushed)
 {
-	xlog_in_core_t	*iclog;
-	xfs_lsn_t	lsn;
+	struct log		*log = mp->m_log;
+	struct xlog_in_core	*iclog;
+	xfs_lsn_t		lsn;
+
+	XFS_STATS_INC(xs_log_force);
 
 	spin_lock(&log->l_icloglock);
 
@@ -2931,7 +2872,9 @@ xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed)
 
 				if (xlog_state_release_iclog(log, iclog))
 					return XFS_ERROR(EIO);
-				*log_flushed = 1;
+
+				if (log_flushed)
+					*log_flushed = 1;
 				spin_lock(&log->l_icloglock);
 				if (be64_to_cpu(iclog->ic_header.h_lsn) == lsn &&
 				    iclog->ic_state != XLOG_STATE_DIRTY)
@@ -2975,19 +2918,37 @@ maybe_sleep:
 		 */
 		if (iclog->ic_state & XLOG_STATE_IOERROR)
 			return XFS_ERROR(EIO);
-		*log_flushed = 1;
-
+		if (log_flushed)
+			*log_flushed = 1;
 	} else {
 
 no_sleep:
 		spin_unlock(&log->l_icloglock);
 	}
 	return 0;
-}	/* xlog_state_sync_all */
+}
 
+/*
+ * Wrapper for _xfs_log_force(), to be used when caller doesn't care
+ * about errors or whether the log was flushed or not. This is the normal
+ * interface to use when trying to unpin items or move the log forward.
+ */
+void
+xfs_log_force(
+	xfs_mount_t	*mp,
+	uint		flags)
+{
+	int	error;
+
+	error = _xfs_log_force(mp, flags, NULL);
+	if (error) {
+		xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
+			"error %d returned.", error);
+	}
+}
 
 /*
- * Used by code which implements synchronous log forces.
+ * Force the in-core log to disk for a specific LSN.
  *
  * Find in-core log with lsn.
  *	If it is in the DIRTY state, just return.
@@ -2995,109 +2956,142 @@ no_sleep:
  *		state and go to sleep or return.
  *	If it is in any other state, go to sleep or return.
  *
- * If filesystem activity goes to zero, the iclog will get flushed only by
- * bdflush().
+ * Synchronous forces are implemented with a signal variable. All callers
+ * to force a given lsn to disk will wait on a the sv attached to the
+ * specific in-core log.  When given in-core log finally completes its
+ * write to disk, that thread will wake up all threads waiting on the
+ * sv.
  */
-STATIC int
-xlog_state_sync(xlog_t	  *log,
-		xfs_lsn_t lsn,
-		uint	  flags,
-		int	  *log_flushed)
+int
+_xfs_log_force_lsn(
+	struct xfs_mount	*mp,
+	xfs_lsn_t		lsn,
+	uint			flags,
+	int			*log_flushed)
 {
-    xlog_in_core_t	*iclog;
-    int			already_slept = 0;
-
-try_again:
-    spin_lock(&log->l_icloglock);
-    iclog = log->l_iclog;
+	struct log		*log = mp->m_log;
+	struct xlog_in_core	*iclog;
+	int			already_slept = 0;
 
-    if (iclog->ic_state & XLOG_STATE_IOERROR) {
-	    spin_unlock(&log->l_icloglock);
-	    return XFS_ERROR(EIO);
-    }
+	ASSERT(lsn != 0);
 
-    do {
-	if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) {
-		iclog = iclog->ic_next;
-		continue;
-	}
+	XFS_STATS_INC(xs_log_force);
 
-	if (iclog->ic_state == XLOG_STATE_DIRTY) {
+try_again:
+	spin_lock(&log->l_icloglock);
+	iclog = log->l_iclog;
+	if (iclog->ic_state & XLOG_STATE_IOERROR) {
 		spin_unlock(&log->l_icloglock);
-		return 0;
+		return XFS_ERROR(EIO);
 	}
 
-	if (iclog->ic_state == XLOG_STATE_ACTIVE) {
-		/*
-		 * We sleep here if we haven't already slept (e.g.
-		 * this is the first time we've looked at the correct
-		 * iclog buf) and the buffer before us is going to
-		 * be sync'ed. The reason for this is that if we
-		 * are doing sync transactions here, by waiting for
-		 * the previous I/O to complete, we can allow a few
-		 * more transactions into this iclog before we close
-		 * it down.
-		 *
-		 * Otherwise, we mark the buffer WANT_SYNC, and bump
-		 * up the refcnt so we can release the log (which drops
-		 * the ref count).  The state switch keeps new transaction
-		 * commits from using this buffer.  When the current commits
-		 * finish writing into the buffer, the refcount will drop to
-		 * zero and the buffer will go out then.
-		 */
-		if (!already_slept &&
-		    (iclog->ic_prev->ic_state & (XLOG_STATE_WANT_SYNC |
-						 XLOG_STATE_SYNCING))) {
-			ASSERT(!(iclog->ic_state & XLOG_STATE_IOERROR));
-			XFS_STATS_INC(xs_log_force_sleep);
-			sv_wait(&iclog->ic_prev->ic_write_wait, PSWP,
-				&log->l_icloglock, s);
-			*log_flushed = 1;
-			already_slept = 1;
-			goto try_again;
-		} else {
+	do {
+		if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) {
+			iclog = iclog->ic_next;
+			continue;
+		}
+
+		if (iclog->ic_state == XLOG_STATE_DIRTY) {
+			spin_unlock(&log->l_icloglock);
+			return 0;
+		}
+
+		if (iclog->ic_state == XLOG_STATE_ACTIVE) {
+			/*
+			 * We sleep here if we haven't already slept (e.g.
+			 * this is the first time we've looked at the correct
+			 * iclog buf) and the buffer before us is going to
+			 * be sync'ed. The reason for this is that if we
+			 * are doing sync transactions here, by waiting for
+			 * the previous I/O to complete, we can allow a few
+			 * more transactions into this iclog before we close
+			 * it down.
+			 *
+			 * Otherwise, we mark the buffer WANT_SYNC, and bump
+			 * up the refcnt so we can release the log (which
+			 * drops the ref count).  The state switch keeps new
+			 * transaction commits from using this buffer.  When
+			 * the current commits finish writing into the buffer,
+			 * the refcount will drop to zero and the buffer will
+			 * go out then.
+			 */
+			if (!already_slept &&
+			    (iclog->ic_prev->ic_state &
+			     (XLOG_STATE_WANT_SYNC | XLOG_STATE_SYNCING))) {
+				ASSERT(!(iclog->ic_state & XLOG_STATE_IOERROR));
+
+				XFS_STATS_INC(xs_log_force_sleep);
+
+				sv_wait(&iclog->ic_prev->ic_write_wait,
+					PSWP, &log->l_icloglock, s);
+				if (log_flushed)
+					*log_flushed = 1;
+				already_slept = 1;
+				goto try_again;
+			}
 			atomic_inc(&iclog->ic_refcnt);
 			xlog_state_switch_iclogs(log, iclog, 0);
 			spin_unlock(&log->l_icloglock);
 			if (xlog_state_release_iclog(log, iclog))
 				return XFS_ERROR(EIO);
-			*log_flushed = 1;
+			if (log_flushed)
+				*log_flushed = 1;
 			spin_lock(&log->l_icloglock);
 		}
-	}
 
-	if ((flags & XFS_LOG_SYNC) && /* sleep */
-	    !(iclog->ic_state & (XLOG_STATE_ACTIVE | XLOG_STATE_DIRTY))) {
+		if ((flags & XFS_LOG_SYNC) && /* sleep */
+		    !(iclog->ic_state &
+		      (XLOG_STATE_ACTIVE | XLOG_STATE_DIRTY))) {
+			/*
+			 * Don't wait on completion if we know that we've
+			 * gotten a log write error.
+			 */
+			if (iclog->ic_state & XLOG_STATE_IOERROR) {
+				spin_unlock(&log->l_icloglock);
+				return XFS_ERROR(EIO);
+			}
+			XFS_STATS_INC(xs_log_force_sleep);
+			sv_wait(&iclog->ic_force_wait, PSWP, &log->l_icloglock, s);
+			/*
+			 * No need to grab the log lock here since we're
+			 * only deciding whether or not to return EIO
+			 * and the memory read should be atomic.
+			 */
+			if (iclog->ic_state & XLOG_STATE_IOERROR)
+				return XFS_ERROR(EIO);
 
-		/*
-		 * Don't wait on completion if we know that we've
-		 * gotten a log write error.
-		 */
-		if (iclog->ic_state & XLOG_STATE_IOERROR) {
+			if (log_flushed)
+				*log_flushed = 1;
+		} else {		/* just return */
 			spin_unlock(&log->l_icloglock);
-			return XFS_ERROR(EIO);
 		}
-		XFS_STATS_INC(xs_log_force_sleep);
-		sv_wait(&iclog->ic_force_wait, PSWP, &log->l_icloglock, s);
-		/*
-		 * No need to grab the log lock here since we're
-		 * only deciding whether or not to return EIO
-		 * and the memory read should be atomic.
-		 */
-		if (iclog->ic_state & XLOG_STATE_IOERROR)
-			return XFS_ERROR(EIO);
-		*log_flushed = 1;
-	} else {		/* just return */
-		spin_unlock(&log->l_icloglock);
-	}
-	return 0;
 
-    } while (iclog != log->l_iclog);
+		return 0;
+	} while (iclog != log->l_iclog);
 
-    spin_unlock(&log->l_icloglock);
-    return 0;
-}	/* xlog_state_sync */
+	spin_unlock(&log->l_icloglock);
+	return 0;
+}
+
+/*
+ * Wrapper for _xfs_log_force_lsn(), to be used when caller doesn't care
+ * about errors or whether the log was flushed or not. This is the normal
+ * interface to use when trying to unpin items or move the log forward.
+ */
+void
+xfs_log_force_lsn(
+	xfs_mount_t	*mp,
+	xfs_lsn_t	lsn,
+	uint		flags)
+{
+	int	error;
 
+	error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
+	if (error) {
+		xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
+			"error %d returned.", error);
+	}
+}
 
 /*
  * Called when we want to mark the current iclog as being ready to sync to
@@ -3462,7 +3456,6 @@ xfs_log_force_umount(
 	xlog_ticket_t	*tic;
 	xlog_t		*log;
 	int		retval;
-	int		dummy;
 
 	log = mp->m_log;
 
@@ -3536,13 +3529,14 @@ xfs_log_force_umount(
 	}
 	spin_unlock(&log->l_grant_lock);
 
-	if (! (log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
+	if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
 		ASSERT(!logerror);
 		/*
 		 * Force the incore logs to disk before shutting the
 		 * log down completely.
 		 */
-		xlog_state_sync_all(log, XFS_LOG_FORCE|XFS_LOG_SYNC, &dummy);
+		_xfs_log_force(mp, XFS_LOG_SYNC, NULL);
+
 		spin_lock(&log->l_icloglock);
 		retval = xlog_state_ioerror(log);
 		spin_unlock(&log->l_icloglock);
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 811ccf4d8b3..7074be9d13e 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -70,14 +70,8 @@ static inline xfs_lsn_t	_lsn_cmp(xfs_lsn_t lsn1, xfs_lsn_t lsn2)
  * Flags to xfs_log_force()
  *
  *	XFS_LOG_SYNC:	Synchronous force in-core log to disk
- *	XFS_LOG_FORCE:	Start in-core log write now.
- *	XFS_LOG_URGE:	Start write within some window of time.
- *
- * Note: Either XFS_LOG_FORCE or XFS_LOG_URGE must be set.
  */
 #define XFS_LOG_SYNC		0x1
-#define XFS_LOG_FORCE		0x2
-#define XFS_LOG_URGE		0x4
 
 #endif	/* __KERNEL__ */
 
@@ -138,12 +132,17 @@ xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
 		       void		**iclog,
 		       uint		flags);
 int	  _xfs_log_force(struct xfs_mount *mp,
-			 xfs_lsn_t	lsn,
 			 uint		flags,
 			 int		*log_forced);
 void	  xfs_log_force(struct xfs_mount	*mp,
-			xfs_lsn_t		lsn,
 			uint			flags);
+int	  _xfs_log_force_lsn(struct xfs_mount *mp,
+			     xfs_lsn_t		lsn,
+			     uint		flags,
+			     int		*log_forced);
+void	  xfs_log_force_lsn(struct xfs_mount	*mp,
+			    xfs_lsn_t		lsn,
+			    uint		flags);
 int	  xfs_log_mount(struct xfs_mount	*mp,
 			struct xfs_buftarg	*log_target,
 			xfs_daddr_t		start_block,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 97148f0c4bd..22e6efdc17e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3913,8 +3913,7 @@ xlog_recover_finish(
 		 * case the unlink transactions would have problems
 		 * pushing the EFIs out of the way.
 		 */
-		xfs_log_force(log->l_mp, (xfs_lsn_t)0,
-			      (XFS_LOG_FORCE | XFS_LOG_SYNC));
+		xfs_log_force(log->l_mp, XFS_LOG_SYNC);
 
 		xlog_recover_process_iunlinks(log);
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index bb0154047e8..7f81ed72c87 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1455,7 +1455,7 @@ xfs_unmountfs(
 	 * push out the iclog we will never get that unlocked. hence we
 	 * need to force the log first.
 	 */
-	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
+	xfs_log_force(mp, XFS_LOG_SYNC);
 	xfs_reclaim_inodes(mp, XFS_IFLUSH_ASYNC);
 
 	xfs_qm_unmount(mp);
@@ -1465,7 +1465,7 @@ xfs_unmountfs(
 	 * that nothing is pinned.  This is important because bflush()
 	 * will skip pinned buffers.
 	 */
-	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
+	xfs_log_force(mp, XFS_LOG_SYNC);
 
 	xfs_binval(mp->m_ddev_targp);
 	if (mp->m_rtdev_targp) {
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 7dbe3c3051d..be942d4e332 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -981,9 +981,8 @@ shut_us_down:
 	 */
 	if (sync) {
 		if (!error) {
-			error = _xfs_log_force(mp, commit_lsn,
-				      XFS_LOG_FORCE | XFS_LOG_SYNC,
-				      log_flushed);
+			error = _xfs_log_force_lsn(mp, commit_lsn,
+				      XFS_LOG_SYNC, log_flushed);
 		}
 		XFS_STATS_INC(xs_trans_sync);
 	} else {
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 063dfbdca94..d7b1af8a832 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -371,7 +371,7 @@ xfsaild_push(
 		 * move forward in the AIL.
 		 */
 		XFS_STATS_INC(xs_push_ail_flush);
-		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+		xfs_log_force(mp, 0);
 	}
 
 	if (!count) {
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 4da96cdffb7..fd108b73855 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -631,9 +631,8 @@ xfs_fsync(
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 		if (xfs_ipincount(ip)) {
-			error = _xfs_log_force(ip->i_mount, (xfs_lsn_t)0,
-				      XFS_LOG_FORCE | XFS_LOG_SYNC,
-				      &log_flushed);
+			error = _xfs_log_force(ip->i_mount, XFS_LOG_SYNC,
+					       &log_flushed);
 		} else {
 			/*
 			 * If the inode is not pinned and nothing has changed
-- 
cgit v1.2.3-70-g09d2


From 777df5afdb26c71634edd60582be620ff94e87a0 Mon Sep 17 00:00:00 2001
From: Dave Chinner <david@fromorbit.com>
Date: Sat, 6 Feb 2010 12:37:26 +1100
Subject: xfs: Make inode reclaim states explicit

A.K.A.: don't rely on xfs_iflush() return value in reclaim

We have gradually been moving checks out of the reclaim code because
they are duplicated in xfs_iflush(). We've had a history of problems
in this area, and many of them stem from the overloading of the
return values from xfs_iflush() and interaction with inode flush
locking to determine if the inode is safe to reclaim.

With the desire to move to delayed write flushing of inodes and
non-blocking inode tree reclaim walks, the overloading of the
return value of xfs_iflush makes it very difficult to determine
the correct thing to do next.

This patch explicitly re-adds the checks to the inode reclaim code,
removing the reliance on the return value of xfs_iflush() to
determine what to do next. It also means that we can clearly
document all the inode states that reclaim must handle and hence
we can easily see that we handled all the necessary cases.

This also removes the need for the xfs_inode_clean() check in
xfs_iflush() as all callers now check this first (safely).

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/linux-2.6/xfs_sync.c | 81 ++++++++++++++++++++++++++++++++++-----------
 fs/xfs/xfs_inode.c          | 11 +-----
 fs/xfs/xfs_inode.h          |  1 +
 3 files changed, 64 insertions(+), 29 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index c9b863eacab..525260c7617 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -706,12 +706,43 @@ __xfs_inode_clear_reclaim_tag(
 			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
 }
 
+/*
+ * Inodes in different states need to be treated differently, and the return
+ * value of xfs_iflush is not sufficient to get this right. The following table
+ * lists the inode states and the reclaim actions necessary for non-blocking
+ * reclaim:
+ *
+ *
+ *	inode state	     iflush ret		required action
+ *      ---------------      ----------         ---------------
+ *	bad			-		reclaim
+ *	shutdown		EIO		unpin and reclaim
+ *	clean, unpinned		0		reclaim
+ *	stale, unpinned		0		reclaim
+ *	clean, pinned(*)	0		unpin and reclaim
+ *	stale, pinned		0		unpin and reclaim
+ *	dirty, async		0		block on flush lock, reclaim
+ *	dirty, sync flush	0		block on flush lock, reclaim
+ *
+ * (*) dgc: I don't think the clean, pinned state is possible but it gets
+ * handled anyway given the order of checks implemented.
+ *
+ * Hence the order of actions after gaining the locks should be:
+ *	bad		=> reclaim
+ *	shutdown	=> unpin and reclaim
+ *	pinned		=> unpin
+ *	stale		=> reclaim
+ *	clean		=> reclaim
+ *	dirty		=> flush, wait and reclaim
+ */
 STATIC int
 xfs_reclaim_inode(
 	struct xfs_inode	*ip,
 	struct xfs_perag	*pag,
 	int			sync_mode)
 {
+	int	error;
+
 	/*
 	 * The radix tree lock here protects a thread in xfs_iget from racing
 	 * with us starting reclaim on the inode.  Once we have the
@@ -729,30 +760,42 @@ xfs_reclaim_inode(
 	spin_unlock(&ip->i_flags_lock);
 	write_unlock(&pag->pag_ici_lock);
 
-	/*
-	 * If the inode is still dirty, then flush it out.  If the inode
-	 * is not in the AIL, then it will be OK to flush it delwri as
-	 * long as xfs_iflush() does not keep any references to the inode.
-	 * We leave that decision up to xfs_iflush() since it has the
-	 * knowledge of whether it's OK to simply do a delwri flush of
-	 * the inode or whether we need to wait until the inode is
-	 * pulled from the AIL.
-	 * We get the flush lock regardless, though, just to make sure
-	 * we don't free it while it is being flushed.
-	 */
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_iflock(ip);
 
-	/*
-	 * In the case of a forced shutdown we rely on xfs_iflush() to
-	 * wait for the inode to be unpinned before returning an error.
-	 */
-	if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
-		/* synchronize with xfs_iflush_done */
-		xfs_iflock(ip);
-		xfs_ifunlock(ip);
+	if (is_bad_inode(VFS_I(ip)))
+		goto reclaim;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		xfs_iunpin_wait(ip);
+		goto reclaim;
+	}
+	if (xfs_ipincount(ip))
+		xfs_iunpin_wait(ip);
+	if (xfs_iflags_test(ip, XFS_ISTALE))
+		goto reclaim;
+	if (xfs_inode_clean(ip))
+		goto reclaim;
+
+	/* Now we have an inode that needs flushing */
+	error = xfs_iflush(ip, sync_mode);
+	if (!error) {
+		switch(sync_mode) {
+		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
+		case XFS_IFLUSH_DELWRI:
+		case XFS_IFLUSH_ASYNC:
+		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
+		case XFS_IFLUSH_SYNC:
+			/* IO issued, synchronise with IO completion */
+			xfs_iflock(ip);
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
 	}
 
+reclaim:
+	xfs_ifunlock(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_ireclaim(ip);
 	return 0;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d0d1b5a0518..8d0666dd170 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2493,7 +2493,7 @@ __xfs_iunpin_wait(
 		wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
 }
 
-static inline void
+void
 xfs_iunpin_wait(
 	xfs_inode_t	*ip)
 {
@@ -2848,15 +2848,6 @@ xfs_iflush(
 	iip = ip->i_itemp;
 	mp = ip->i_mount;
 
-	/*
-	 * If the inode isn't dirty, then just release the inode flush lock and
-	 * do nothing.
-	 */
-	if (xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
 	/*
 	 * We can't flush the inode until it is unpinned, so wait for it if we
 	 * are allowed to block.  We know noone new can pin it, because we are
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ec1f28c4fc4..8b618ea4d69 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -483,6 +483,7 @@ 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);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
-- 
cgit v1.2.3-70-g09d2


From c854363e80b49dd04a4de18ebc379eb8c8806674 Mon Sep 17 00:00:00 2001
From: Dave Chinner <david@fromorbit.com>
Date: Sat, 6 Feb 2010 12:39:36 +1100
Subject: xfs: Use delayed write for inodes rather than async V2

We currently do background inode flush asynchronously, resulting in
inodes being written in whatever order the background writeback
issues them. Not only that, there are also blocking and non-blocking
asynchronous inode flushes, depending on where the flush comes from.

This patch completely removes asynchronous inode writeback. It
removes all the strange writeback modes and replaces them with
either a synchronous flush or a non-blocking delayed write flush.
That is, inode flushes will only issue IO directly if they are
synchronous, and background flushing may do nothing if the operation
would block (e.g. on a pinned inode or buffer lock).

Delayed write flushes will now result in the inode buffer sitting in
the delwri queue of the buffer cache to be flushed by either an AIL
push or by the xfsbufd timing out the buffer. This will allow
accumulation of dirty inode buffers in memory and allow optimisation
of inode cluster writeback at the xfsbufd level where we have much
greater queue depths than the block layer elevators. We will also
get adjacent inode cluster buffer IO merging for free when a later
patch in the series allows sorting of the delayed write buffers
before dispatch.

This effectively means that any inode that is written back by
background writeback will be seen as flush locked during AIL
pushing, and will result in the buffers being pushed from there.
This writeback path is currently non-optimal, but the next patch
in the series will fix that problem.

A side effect of this delayed write mechanism is that background
inode reclaim will no longer directly flush inodes, nor can it wait
on the flush lock. The result is that inode reclaim must leave the
inode in the reclaimable state until it is clean. Hence attempts to
reclaim a dirty inode in the background will simply skip the inode
until it is clean and this allows other mechanisms (i.e. xfsbufd) to
do more optimal writeback of the dirty buffers. As a result, the
inode reclaim code has been rewritten so that it no longer relies on
the ambiguous return values of xfs_iflush() to determine whether it
is safe to reclaim an inode.

Portions of this patch are derived from patches by Christoph
Hellwig.

Version 2:
- cleanup reclaim code as suggested by Christoph
- log background reclaim inode flush errors
- just pass sync flags to xfs_iflush

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/linux-2.6/xfs_super.c |   4 +-
 fs/xfs/linux-2.6/xfs_sync.c  | 105 +++++++++++++++++++++++++++++++------------
 fs/xfs/xfs_inode.c           |  75 +++----------------------------
 fs/xfs/xfs_inode.h           |  10 -----
 fs/xfs/xfs_inode_item.c      |  10 +++--
 fs/xfs/xfs_mount.c           |  13 +++++-
 6 files changed, 102 insertions(+), 115 deletions(-)

(limited to 'fs/xfs/linux-2.6/xfs_sync.c')

diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 6ce828e0e17..3b5b46b8e3b 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1064,7 +1064,7 @@ xfs_fs_write_inode(
 		xfs_ilock(ip, XFS_ILOCK_SHARED);
 		xfs_iflock(ip);
 
-		error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+		error = xfs_iflush(ip, SYNC_WAIT);
 	} else {
 		error = EAGAIN;
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
@@ -1072,7 +1072,7 @@ xfs_fs_write_inode(
 		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
 			goto out_unlock;
 
-		error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK);
+		error = xfs_iflush(ip, 0);
 	}
 
  out_unlock:
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 525260c7617..a9f6d20aff4 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -270,8 +270,7 @@ xfs_sync_inode_attr(
 		goto out_unlock;
 	}
 
-	error = xfs_iflush(ip, (flags & SYNC_WAIT) ?
-			   XFS_IFLUSH_SYNC : XFS_IFLUSH_DELWRI);
+	error = xfs_iflush(ip, flags);
 
  out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -460,16 +459,18 @@ xfs_quiesce_fs(
 {
 	int	count = 0, pincount;
 
+	xfs_reclaim_inodes(mp, 0);
 	xfs_flush_buftarg(mp->m_ddev_targp, 0);
-	xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
 
 	/*
 	 * This loop must run at least twice.  The first instance of the loop
 	 * will flush most meta data but that will generate more meta data
 	 * (typically directory updates).  Which then must be flushed and
-	 * logged before we can write the unmount record.
+	 * logged before we can write the unmount record. We also so sync
+	 * reclaim of inodes to catch any that the above delwri flush skipped.
 	 */
 	do {
+		xfs_reclaim_inodes(mp, SYNC_WAIT);
 		xfs_sync_attr(mp, SYNC_WAIT);
 		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
 		if (!pincount) {
@@ -585,7 +586,7 @@ xfs_sync_worker(
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		xfs_log_force(mp, 0);
-		xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+		xfs_reclaim_inodes(mp, 0);
 		/* dgc: errors ignored here */
 		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 		error = xfs_sync_fsdata(mp, SYNC_TRYLOCK);
@@ -719,21 +720,42 @@ __xfs_inode_clear_reclaim_tag(
  *	shutdown		EIO		unpin and reclaim
  *	clean, unpinned		0		reclaim
  *	stale, unpinned		0		reclaim
- *	clean, pinned(*)	0		unpin and reclaim
- *	stale, pinned		0		unpin and reclaim
- *	dirty, async		0		block on flush lock, reclaim
- *	dirty, sync flush	0		block on flush lock, reclaim
+ *	clean, pinned(*)	0		requeue
+ *	stale, pinned		EAGAIN		requeue
+ *	dirty, delwri ok	0		requeue
+ *	dirty, delwri blocked	EAGAIN		requeue
+ *	dirty, sync flush	0		reclaim
  *
  * (*) dgc: I don't think the clean, pinned state is possible but it gets
  * handled anyway given the order of checks implemented.
  *
+ * As can be seen from the table, the return value of xfs_iflush() is not
+ * sufficient to correctly decide the reclaim action here. The checks in
+ * xfs_iflush() might look like duplicates, but they are not.
+ *
+ * Also, because we get the flush lock first, we know that any inode that has
+ * been flushed delwri has had the flush completed by the time we check that
+ * the inode is clean. The clean inode check needs to be done before flushing
+ * the inode delwri otherwise we would loop forever requeuing clean inodes as
+ * we cannot tell apart a successful delwri flush and a clean inode from the
+ * return value of xfs_iflush().
+ *
+ * Note that because the inode is flushed delayed write by background
+ * writeback, the flush lock may already be held here and waiting on it can
+ * result in very long latencies. Hence for sync reclaims, where we wait on the
+ * flush lock, the caller should push out delayed write inodes first before
+ * trying to reclaim them to minimise the amount of time spent waiting. For
+ * background relaim, we just requeue the inode for the next pass.
+ *
  * Hence the order of actions after gaining the locks should be:
  *	bad		=> reclaim
  *	shutdown	=> unpin and reclaim
- *	pinned		=> unpin
+ *	pinned, delwri	=> requeue
+ *	pinned, sync	=> unpin
  *	stale		=> reclaim
  *	clean		=> reclaim
- *	dirty		=> flush, wait and reclaim
+ *	dirty, delwri	=> flush and requeue
+ *	dirty, sync	=> flush, wait and reclaim
  */
 STATIC int
 xfs_reclaim_inode(
@@ -741,7 +763,7 @@ xfs_reclaim_inode(
 	struct xfs_perag	*pag,
 	int			sync_mode)
 {
-	int	error;
+	int	error = 0;
 
 	/*
 	 * The radix tree lock here protects a thread in xfs_iget from racing
@@ -761,7 +783,11 @@ xfs_reclaim_inode(
 	write_unlock(&pag->pag_ici_lock);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_iflock(ip);
+	if (!xfs_iflock_nowait(ip)) {
+		if (!(sync_mode & SYNC_WAIT))
+			goto out;
+		xfs_iflock(ip);
+	}
 
 	if (is_bad_inode(VFS_I(ip)))
 		goto reclaim;
@@ -769,8 +795,13 @@ xfs_reclaim_inode(
 		xfs_iunpin_wait(ip);
 		goto reclaim;
 	}
-	if (xfs_ipincount(ip))
+	if (xfs_ipincount(ip)) {
+		if (!(sync_mode & SYNC_WAIT)) {
+			xfs_ifunlock(ip);
+			goto out;
+		}
 		xfs_iunpin_wait(ip);
+	}
 	if (xfs_iflags_test(ip, XFS_ISTALE))
 		goto reclaim;
 	if (xfs_inode_clean(ip))
@@ -778,27 +809,43 @@ xfs_reclaim_inode(
 
 	/* Now we have an inode that needs flushing */
 	error = xfs_iflush(ip, sync_mode);
-	if (!error) {
-		switch(sync_mode) {
-		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
-		case XFS_IFLUSH_DELWRI:
-		case XFS_IFLUSH_ASYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
-		case XFS_IFLUSH_SYNC:
-			/* IO issued, synchronise with IO completion */
-			xfs_iflock(ip);
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+	if (sync_mode & SYNC_WAIT) {
+		xfs_iflock(ip);
+		goto reclaim;
 	}
 
+	/*
+	 * When we have to flush an inode but don't have SYNC_WAIT set, we
+	 * flush the inode out using a delwri buffer and wait for the next
+	 * call into reclaim to find it in a clean state instead of waiting for
+	 * it now. We also don't return errors here - if the error is transient
+	 * then the next reclaim pass will flush the inode, and if the error
+	 * is permanent then the next sync reclaim will relcaim the inode and
+	 * pass on the error.
+	 */
+	if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		xfs_fs_cmn_err(CE_WARN, ip->i_mount,
+			"inode 0x%llx background reclaim flush failed with %d",
+			(long long)ip->i_ino, error);
+	}
+out:
+	xfs_iflags_clear(ip, XFS_IRECLAIM);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	/*
+	 * We could return EAGAIN here to make reclaim rescan the inode tree in
+	 * a short while. However, this just burns CPU time scanning the tree
+	 * waiting for IO to complete and xfssyncd never goes back to the idle
+	 * state. Instead, return 0 to let the next scheduled background reclaim
+	 * attempt to reclaim the inode again.
+	 */
+	return 0;
+
 reclaim:
 	xfs_ifunlock(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_ireclaim(ip);
-	return 0;
+	return error;
+
 }
 
 int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8d0666dd170..fa31360046d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2835,8 +2835,6 @@ xfs_iflush(
 	xfs_dinode_t		*dip;
 	xfs_mount_t		*mp;
 	int			error;
-	int			noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK);
-	enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) };
 
 	XFS_STATS_INC(xs_iflush_count);
 
@@ -2859,7 +2857,7 @@ xfs_iflush(
 	 * in the same cluster are dirty, they will probably write the inode
 	 * out for us if they occur after the log force completes.
 	 */
-	if (noblock && xfs_ipincount(ip)) {
+	if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
 		xfs_iunpin_nowait(ip);
 		xfs_ifunlock(ip);
 		return EAGAIN;
@@ -2892,61 +2890,11 @@ xfs_iflush(
 		return XFS_ERROR(EIO);
 	}
 
-	/*
-	 * Decide how buffer will be flushed out.  This is done before
-	 * the call to xfs_iflush_int because this field is zeroed by it.
-	 */
-	if (iip != NULL && iip->ili_format.ilf_fields != 0) {
-		/*
-		 * Flush out the inode buffer according to the directions
-		 * of the caller.  In the cases where the caller has given
-		 * us a choice choose the non-delwri case.  This is because
-		 * the inode is in the AIL and we need to get it out soon.
-		 */
-		switch (flags) {
-		case XFS_IFLUSH_SYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
-			flags = 0;
-			break;
-		case XFS_IFLUSH_ASYNC_NOBLOCK:
-		case XFS_IFLUSH_ASYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
-			flags = INT_ASYNC;
-			break;
-		case XFS_IFLUSH_DELWRI:
-			flags = INT_DELWRI;
-			break;
-		default:
-			ASSERT(0);
-			flags = 0;
-			break;
-		}
-	} else {
-		switch (flags) {
-		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
-		case XFS_IFLUSH_DELWRI:
-			flags = INT_DELWRI;
-			break;
-		case XFS_IFLUSH_ASYNC_NOBLOCK:
-		case XFS_IFLUSH_ASYNC:
-			flags = INT_ASYNC;
-			break;
-		case XFS_IFLUSH_SYNC:
-			flags = 0;
-			break;
-		default:
-			ASSERT(0);
-			flags = 0;
-			break;
-		}
-	}
-
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
 	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				noblock ? XBF_TRYLOCK : XBF_LOCK);
+				(flags & SYNC_WAIT) ? XBF_LOCK : XBF_TRYLOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
@@ -2974,13 +2922,10 @@ xfs_iflush(
 	if (error)
 		goto cluster_corrupt_out;
 
-	if (flags & INT_DELWRI) {
-		xfs_bdwrite(mp, bp);
-	} else if (flags & INT_ASYNC) {
-		error = xfs_bawrite(mp, bp);
-	} else {
+	if (flags & SYNC_WAIT)
 		error = xfs_bwrite(mp, bp);
-	}
+	else
+		xfs_bdwrite(mp, bp);
 	return error;
 
 corrupt_out:
@@ -3015,16 +2960,6 @@ xfs_iflush_int(
 	iip = ip->i_itemp;
 	mp = ip->i_mount;
 
-
-	/*
-	 * If the inode isn't dirty, then just release the inode
-	 * flush lock and do nothing.
-	 */
-	if (xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
 	/* set *dip = inode's place in the buffer */
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8b618ea4d69..6c912b02759 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -419,16 +419,6 @@ static inline void xfs_ifunlock(xfs_inode_t *ip)
 #define XFS_IOLOCK_DEP(flags)	(((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT)
 #define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT)
 
-/*
- * Flags for xfs_iflush()
- */
-#define	XFS_IFLUSH_DELWRI_ELSE_SYNC	1
-#define	XFS_IFLUSH_DELWRI_ELSE_ASYNC	2
-#define	XFS_IFLUSH_SYNC			3
-#define	XFS_IFLUSH_ASYNC		4
-#define	XFS_IFLUSH_DELWRI		5
-#define	XFS_IFLUSH_ASYNC_NOBLOCK	6
-
 /*
  * Flags for xfs_itruncate_start().
  */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 48ec1c0b23c..207553e8295 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -866,10 +866,14 @@ xfs_inode_item_push(
 	       iip->ili_format.ilf_fields != 0);
 
 	/*
-	 * Write out the inode.  The completion routine ('iflush_done') will
-	 * pull it from the AIL, mark it clean, unlock the flush lock.
+	 * Push the inode to it's backing buffer. This will not remove the
+	 * inode from the AIL - a further push will be required to trigger a
+	 * buffer push. However, this allows all the dirty inodes to be pushed
+	 * to the buffer before it is pushed to disk. THe buffer IO completion
+	 * will pull th einode from the AIL, mark it clean and unlock the flush
+	 * lock.
 	 */
-	(void) xfs_iflush(ip, XFS_IFLUSH_ASYNC);
+	(void) xfs_iflush(ip, 0);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	return;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 5061149b2cc..6afaaeb2950 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1468,7 +1468,18 @@ xfs_unmountfs(
 	 * need to force the log first.
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
-	xfs_reclaim_inodes(mp, XFS_IFLUSH_ASYNC);
+
+	/*
+	 * Do a delwri reclaim pass first so that as many dirty inodes are
+	 * queued up for IO as possible. Then flush the buffers before making
+	 * a synchronous path to catch all the remaining inodes are reclaimed.
+	 * This makes the reclaim process as quick as possible by avoiding
+	 * synchronous writeout and blocking on inodes already in the delwri
+	 * state as much as possible.
+	 */
+	xfs_reclaim_inodes(mp, 0);
+	XFS_bflush(mp->m_ddev_targp);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
 
 	xfs_qm_unmount(mp);
 
-- 
cgit v1.2.3-70-g09d2