[PATCH 0/9, V2] xfs; discontiguous buffer support

[PATCH 0/9, V2] xfs; discontiguous buffer support

[Dave Chinner]

This is the latest version of the native xfs_buf discontiguous
buffer support series.

The series introduces the concept of buffer block maps, then
adds APIs for using them, converts the internal xfs_buf method
implementation to use them exclusively, adds support for
discontiguous buffer log items in transactions, converts
the directory code to use them and finally removes the xfs_dabuf
from the picture.

This greatly simplifies the directory buffer code and avoids
copy-up/copy-down for discontiguous buffers. It also avoids needing
to create and destroy a xfs-dabuf for every directory block that is
read or written, greatly reducing buffer setup and teardown
overhead and memory footprint.

Version 2:
- addressed Christoph's comments
- reordered to bring the xfs_buf_log_format changes up front
- rebased on a current 3.5-rc + xfs-oss/master tree

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 1/9] xfs: struct xfs_buf_log_format isn't variable sized.

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

The struct xfs_buf_log_format wants to think the dirty bitmap is
variable sized.  In fact, it is variable size on disk simply due to
the way we map it from the in-memory structure, but we still just
use a fixed size memory allocation for the in-memory structure.

Hence it makes no sense to set the function up as a variable sized
structure when we already know it's maximum size, and we always
allocate it as such. Simplify the structure by making the dirty
bitmap a fixed sized array and just using the size of the structure
for the allocation size.

This will make it much simpler to allocate and manipulate an array
of format structures for discontiguous buffer support.

The previous struct xfs_buf_log_item size according to
/proc/slabinfo was 224 bytes. pahole doesn't give the same size
because of the variable size definition. With this modification,
pahole reports the same as /proc/slabinfo:

	/* size: 224, cachelines: 4, members: 6 */

Because the xfs_buf_log_item size is now determined by the maximum
supported block size we introduce a dependency on xfs_alloc_btree.h.
Avoid this dependency by moving the idefines for the maximum block
sizes supported to xfs_types.h with all the other max/min type
defines to avoid any new dependencies.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_alloc_btree.h |   14 --------------
 fs/xfs/xfs_buf_item.c    |   14 ++++++--------
 fs/xfs/xfs_buf_item.h    |   36 ++++++++++++++++++------------------
 fs/xfs/xfs_super.c       |    5 ++---
 fs/xfs/xfs_types.h       |   14 ++++++++++++++
 5 files changed, 40 insertions(+), 43 deletions(-)

diff --git a/fs/xfs/xfs_alloc_btree.h b/fs/xfs/xfs_alloc_btree.h
index a6caa00..359fb86 100644
--- a/fs/xfs/xfs_alloc_btree.h
+++ b/fs/xfs/xfs_alloc_btree.h
@@ -51,20 +51,6 @@ typedef struct xfs_alloc_rec_incore {
 typedef __be32 xfs_alloc_ptr_t;
 
 /*
- * Minimum and maximum blocksize and sectorsize.
- * The blocksize upper limit is pretty much arbitrary.
- * The sectorsize upper limit is due to sizeof(sb_sectsize).
- */
-#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
-#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
-#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
-#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
-#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
-#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
-
-/*
  * Block numbers in the AG:
  * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
  */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 45df2b8..52cd8f8 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -240,15 +240,13 @@ xfs_buf_item_format(
 	       (bip->bli_flags & XFS_BLI_STALE));
 
 	/*
-	 * The size of the base structure is the size of the
-	 * declared structure plus the space for the extra words
-	 * of the bitmap.  We subtract one from the map size, because
-	 * the first element of the bitmap is accounted for in the
-	 * size of the base structure.
+	 * Base size is the actual size of the ondisk structure - it reflects
+	 * the actual size of the dirty bitmap rather than the size of the in
+	 * memory structure.
 	 */
-	base_size =
-		(uint)(sizeof(xfs_buf_log_format_t) +
-		       ((bip->bli_format.blf_map_size - 1) * sizeof(uint)));
+	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
+			(bip->bli_format.blf_map_size *
+				sizeof(bip->bli_format.blf_data_map[0]));
 	vecp->i_addr = &bip->bli_format;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index b6ecd20..ff26867 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -21,23 +21,6 @@
 extern kmem_zone_t	*xfs_buf_item_zone;
 
 /*
- * This is the structure used to lay out a buf log item in the
- * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.
- * For 6.2 and beyond, this is XFS_LI_BUF.  We use this to log everything.
- */
-typedef struct xfs_buf_log_format {
-	unsigned short	blf_type;	/* buf log item type indicator */
-	unsigned short	blf_size;	/* size of this item */
-	ushort		blf_flags;	/* misc state */
-	ushort		blf_len;	/* number of blocks in this buf */
-	__int64_t	blf_blkno;	/* starting blkno of this buf */
-	unsigned int	blf_map_size;	/* size of data bitmap in words */
-	unsigned int	blf_data_map[1];/* variable size bitmap of */
-					/*   regions of buffer in this item */
-} xfs_buf_log_format_t;
-
-/*
  * This flag indicates that the buffer contains on disk inodes
  * and requires special recovery handling.
  */
@@ -61,6 +44,23 @@ typedef struct xfs_buf_log_format {
 #define	NBWORD			(NBBY * sizeof(unsigned int))
 
 /*
+ * This is the structure used to lay out a buf log item in the
+ * log.  The data map describes which 128 byte chunks of the buffer
+ * have been logged.
+ */
+#define XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+
+typedef struct xfs_buf_log_format {
+	unsigned short	blf_type;	/* buf log item type indicator */
+	unsigned short	blf_size;	/* size of this item */
+	ushort		blf_flags;	/* misc state */
+	ushort		blf_len;	/* number of blocks in this buf */
+	__int64_t	blf_blkno;	/* starting blkno of this buf */
+	unsigned int	blf_map_size;	/* used size of data bitmap in words */
+	unsigned int	blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */
+} xfs_buf_log_format_t;
+
+/*
  * buf log item flags
  */
 #define	XFS_BLI_HOLD		0x01
@@ -102,7 +102,7 @@ typedef struct xfs_buf_log_item {
 	char			*bli_orig;	/* original buffer copy */
 	char			*bli_logged;	/* bytes logged (bitmap) */
 #endif
-	xfs_buf_log_format_t	bli_format;	/* in-log header */
+	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
 void	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0d9de41..425f6e9 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1514,9 +1514,8 @@ xfs_init_zones(void)
 	 * size possible under XFS.  This wastes a little bit of memory,
 	 * but it is much faster.
 	 */
-	xfs_buf_item_zone = kmem_zone_init((sizeof(xfs_buf_log_item_t) +
-				(((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) /
-				  NBWORD) * sizeof(int))), "xfs_buf_item");
+	xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
+					   "xfs_buf_item");
 	if (!xfs_buf_item_zone)
 		goto out_destroy_log_item_desc_zone;
 
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 7e0639a..42e5216 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -122,6 +122,20 @@ typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 #define	MAXAEXTNUM	((xfs_aextnum_t)0x7fff)		/* signed short */
 
 /*
+ * Minimum and maximum blocksize and sectorsize.
+ * The blocksize upper limit is pretty much arbitrary.
+ * The sectorsize upper limit is due to sizeof(sb_sectsize).
+ */
+#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
+#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
+#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
+#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
+#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
+#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
+
+/*
  * Min numbers of data/attr fork btree root pointers.
  */
 #define MINDBTPTRS	3
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 1/9] xfs: struct xfs_buf_log_format isn't variable sized.

[Christoph Hellwig]

On Fri, Jun 22, 2012 at 06:50:07PM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> The struct xfs_buf_log_format wants to think the dirty bitmap is
> variable sized.  In fact, it is variable size on disk simply due to
> the way we map it from the in-memory structure, but we still just
> use a fixed size memory allocation for the in-memory structure.
> 
> Hence it makes no sense to set the function up as a variable sized
> structure when we already know it's maximum size, and we always
> allocate it as such. Simplify the structure by making the dirty
> bitmap a fixed sized array and just using the size of the structure
> for the allocation size.
> 
> This will make it much simpler to allocate and manipulate an array
> of format structures for discontiguous buffer support.
> 
> The previous struct xfs_buf_log_item size according to
> /proc/slabinfo was 224 bytes. pahole doesn't give the same size
> because of the variable size definition. With this modification,
> pahole reports the same as /proc/slabinfo:
> 
> 	/* size: 224, cachelines: 4, members: 6 */
> 
> Because the xfs_buf_log_item size is now determined by the maximum
> supported block size we introduce a dependency on xfs_alloc_btree.h.
> Avoid this dependency by moving the idefines for the maximum block
> sizes supported to xfs_types.h with all the other max/min type
> defines to avoid any new dependencies.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 2/9] xfs: separate buffer indexing from block map

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

To support discontiguous buffers in the buffer cache, we need to
separate the cache index variables from the I/O map. While this is
currently a 1:1 mapping, discontiguous buffer support will break
this relationship.

However, for caching purposes, we can still treat them the same as a
contiguous buffer - the block number of the first block and the
length of the buffer - as that is still a unique representation.
Also, the only way we will ever access the discontiguous regions of
buffers is via bulding the complete buffer in the first place, so
using the initial block number and entire buffer length is a sane
way to index the buffers.

Add a block mapping vector construct to the xfs_buf and use it in
the places where we are doing IO instead of the current
b_bn/b_length variables.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_buf.c |   21 ++++++++++++---------
 fs/xfs/xfs_buf.h |   27 +++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a4beb42..a843873 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -202,6 +202,8 @@ xfs_buf_alloc(
 	bp->b_io_length = numblks;
 	bp->b_flags = flags;
 	bp->b_bn = blkno;
+	bp->b_map.bm_bn = blkno;
+	bp->b_map.bm_len = numblks;
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
 
@@ -327,8 +329,9 @@ xfs_buf_allocate_memory(
 	}
 
 use_alloc_page:
-	start = BBTOB(bp->b_bn) >> PAGE_SHIFT;
-	end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	start = BBTOB(bp->b_map.bm_bn) >> PAGE_SHIFT;
+	end = (BBTOB(bp->b_map.bm_bn + bp->b_length) + PAGE_SIZE - 1)
+								>> PAGE_SHIFT;
 	page_count = end - start;
 	error = _xfs_buf_get_pages(bp, page_count, flags);
 	if (unlikely(error))
@@ -560,8 +563,6 @@ xfs_buf_get(
 	if (bp != new_bp)
 		xfs_buf_free(new_bp);
 
-	bp->b_io_length = bp->b_length;
-
 found:
 	if (!bp->b_addr) {
 		error = _xfs_buf_map_pages(bp, flags);
@@ -584,7 +585,7 @@ _xfs_buf_read(
 	xfs_buf_flags_t		flags)
 {
 	ASSERT(!(flags & XBF_WRITE));
-	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+	ASSERT(bp->b_map.bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
@@ -665,8 +666,8 @@ xfs_buf_read_uncached(
 		return NULL;
 
 	/* set up the buffer for a read IO */
-	XFS_BUF_SET_ADDR(bp, daddr);
-	XFS_BUF_READ(bp);
+	bp->b_map.bm_bn = daddr;
+	bp->b_flags |= XBF_READ;
 
 	xfsbdstrat(target->bt_mount, bp);
 	error = xfs_buf_iowait(bp);
@@ -695,6 +696,8 @@ xfs_buf_set_empty(
 	bp->b_length = numblks;
 	bp->b_io_length = numblks;
 	bp->b_bn = XFS_BUF_DADDR_NULL;
+	bp->b_map.bm_bn = XFS_BUF_DADDR_NULL;
+	bp->b_map.bm_len = bp->b_length;
 }
 
 static inline struct page *
@@ -1159,7 +1162,7 @@ _xfs_buf_ioapply(
 	struct bio		*bio;
 	int			offset = bp->b_offset;
 	int			size = BBTOB(bp->b_io_length);
-	sector_t		sector = bp->b_bn;
+	sector_t		sector = bp->b_map.bm_bn;
 
 	total_nr_pages = bp->b_page_count;
 	map_i = 0;
@@ -1564,7 +1567,7 @@ xfs_buf_cmp(
 	struct xfs_buf	*bp = container_of(b, struct xfs_buf, b_list);
 	xfs_daddr_t		diff;
 
-	diff = ap->b_bn - bp->b_bn;
+	diff = ap->b_map.bm_bn - bp->b_map.bm_bn;
 	if (diff < 0)
 		return -1;
 	if (diff > 0)
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 7f1d139..c9c2ba9 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -58,6 +58,7 @@ typedef enum {
 #define _XBF_PAGES	(1 << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	(1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	(1 << 22)/* buffer on a delwri queue */
+#define _XBF_COMPOUND	(1 << 23)/* compound buffer */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -75,7 +76,8 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
-	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
+	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
+	{ _XBF_COMPOUND,	"COMPOUND" }
 
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
@@ -98,6 +100,11 @@ typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
+struct xfs_buf_map {
+	xfs_daddr_t		bm_bn;	/* block number for I/O */
+	int			bm_len;	/* size of I/O */
+};
+
 typedef struct xfs_buf {
 	/*
 	 * first cacheline holds all the fields needed for an uncontended cache
@@ -107,7 +114,7 @@ typedef struct xfs_buf {
 	 * fast-path on locking.
 	 */
 	struct rb_node		b_rbnode;	/* rbtree node */
-	xfs_daddr_t		b_bn;		/* block number for I/O */
+	xfs_daddr_t		b_bn;		/* block number of buffer */
 	int			b_length;	/* size of buffer in BBs */
 	atomic_t		b_hold;		/* reference count */
 	atomic_t		b_lru_ref;	/* lru reclaim ref count */
@@ -127,12 +134,14 @@ typedef struct xfs_buf {
 	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
+	struct xfs_buf_map	b_map;		/* compound buffer map */
 	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
 	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
 	unsigned int		b_page_count;	/* size of page array */
 	unsigned int		b_offset;	/* page offset in first page */
 	unsigned short		b_error;	/* error code on I/O */
+
 #ifdef XFS_BUF_LOCK_TRACKING
 	int			b_last_holder;
 #endif
@@ -233,8 +242,18 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
 #define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
 
-#define XFS_BUF_ADDR(bp)		((bp)->b_bn)
-#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_bn = (xfs_daddr_t)(bno))
+/*
+ * These macros use the IO block map rather than b_bn. b_bn is now really
+ * just for the buffer cache index for cached buffers. As IO does not use b_bn
+ * anymore, uncached buffers do not use b_bn at all and hence must modify the IO
+ * map directly. Uncached buffers are not allowed to be discontiguous, so this
+ * is safe to do.
+ *
+ * In future, uncached buffers will pass the block number directly to the io
+ * request function and hence these macros will go away at that point.
+ */
+#define XFS_BUF_ADDR(bp)		((bp)->b_map.bm_bn)
+#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_map.bm_bn = (xfs_daddr_t)(bno))
 
 static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 2/9] xfs: separate buffer indexing from block map

[Christoph Hellwig]

On Fri, Jun 22, 2012 at 06:50:08PM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> To support discontiguous buffers in the buffer cache, we need to
> separate the cache index variables from the I/O map. While this is
> currently a 1:1 mapping, discontiguous buffer support will break
> this relationship.
> 
> However, for caching purposes, we can still treat them the same as a
> contiguous buffer - the block number of the first block and the
> length of the buffer - as that is still a unique representation.
> Also, the only way we will ever access the discontiguous regions of
> buffers is via bulding the complete buffer in the first place, so
> using the initial block number and entire buffer length is a sane
> way to index the buffers.
> 
> Add a block mapping vector construct to the xfs_buf and use it in
> the places where we are doing IO instead of the current
> b_bn/b_length variables.

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 3/9] xfs: convert internal buffer functions to pass maps

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

While the external interface currently uses separate blockno/length
variables, we need to move internal interfaces to passing and
parsing vector maps. This will then allow us to add external
interfaces to support discontiguous buffer maps as the internal code
will already support them.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_buf.c |  202 +++++++++++++++++++++++++++++++++++++++++-------------
 fs/xfs/xfs_buf.h |   43 +++++++++---
 2 files changed, 191 insertions(+), 54 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a843873..82bb812 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -164,14 +164,49 @@ xfs_buf_stale(
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
 }
 
+static int
+xfs_buf_get_maps(
+	struct xfs_buf		*bp,
+	int			map_count)
+{
+	ASSERT(bp->b_maps == NULL);
+	bp->b_map_count = map_count;
+
+	if (map_count == 1) {
+		bp->b_maps = &bp->b_map;
+		return 0;
+	}
+
+	bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map),
+				KM_NOFS);
+	if (!bp->b_maps)
+		return ENOMEM;
+	return 0;
+}
+
+/*
+ *	Frees b_pages if it was allocated.
+ */
+static void
+xfs_buf_free_maps(
+	struct xfs_buf	*bp)
+{
+	if (bp->b_maps != &bp->b_map) {
+		kmem_free(bp->b_maps);
+		bp->b_maps = NULL;
+	}
+}
+
 struct xfs_buf *
-xfs_buf_alloc(
+_xfs_buf_alloc(
 	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
+	int			error;
+	int			i;
 
 	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
 	if (unlikely(!bp))
@@ -192,18 +227,28 @@ xfs_buf_alloc(
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	XB_SET_OWNER(bp);
 	bp->b_target = target;
+	bp->b_flags = flags;
 
 	/*
 	 * Set length and io_length to the same value initially.
 	 * I/O routines should use io_length, which will be the same in
 	 * most cases but may be reset (e.g. XFS recovery).
 	 */
-	bp->b_length = numblks;
-	bp->b_io_length = numblks;
-	bp->b_flags = flags;
-	bp->b_bn = blkno;
-	bp->b_map.bm_bn = blkno;
-	bp->b_map.bm_len = numblks;
+	error = xfs_buf_get_maps(bp, nmaps);
+	if (error)  {
+		kmem_zone_free(xfs_buf_zone, bp);
+		return NULL;
+	}
+
+	bp->b_bn = map[0].bm_bn;
+	bp->b_length = 0;
+	for (i = 0; i < nmaps; i++) {
+		bp->b_maps[i].bm_bn = map[i].bm_bn;
+		bp->b_maps[i].bm_len = map[i].bm_len;
+		bp->b_length += map[i].bm_len;
+	}
+	bp->b_io_length = bp->b_length;
+
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
 
@@ -282,6 +327,7 @@ xfs_buf_free(
 	} else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
 	_xfs_buf_free_pages(bp);
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
 }
 
@@ -428,8 +474,8 @@ _xfs_buf_map_pages(
 xfs_buf_t *
 _xfs_buf_find(
 	struct xfs_buftarg	*btp,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags,
 	xfs_buf_t		*new_bp)
 {
@@ -438,7 +484,12 @@ _xfs_buf_find(
 	struct rb_node		**rbp;
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
+	xfs_daddr_t		blkno = map[0].bm_bn;
+	int			numblks = 0;
+	int			i;
 
+	for (i = 0; i < nmaps; i++)
+		numblks += map[i].bm_len;
 	numbytes = BBTOB(numblks);
 
 	/* Check for IOs smaller than the sector size / not sector aligned */
@@ -539,22 +590,23 @@ xfs_buf_get(
 	struct xfs_buf		*bp;
 	struct xfs_buf		*new_bp;
 	int			error = 0;
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, NULL);
+	bp = _xfs_buf_find(target, &map, 1, flags, NULL);
 	if (likely(bp))
 		goto found;
 
-	new_bp = xfs_buf_alloc(target, blkno, numblks, flags);
+	new_bp = _xfs_buf_alloc(target, &map, 1, flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
 	error = xfs_buf_allocate_memory(new_bp, flags);
 	if (error) {
-		kmem_zone_free(xfs_buf_zone, new_bp);
+		xfs_buf_free(new_bp);
 		return NULL;
 	}
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp);
+	bp = _xfs_buf_find(target, &map, 1, flags, new_bp);
 	if (!bp) {
 		xfs_buf_free(new_bp);
 		return NULL;
@@ -666,7 +718,9 @@ xfs_buf_read_uncached(
 		return NULL;
 
 	/* set up the buffer for a read IO */
-	bp->b_map.bm_bn = daddr;
+	ASSERT(bp->b_map_count == 1);
+	bp->b_bn = daddr;
+	bp->b_maps[0].bm_bn = daddr;
 	bp->b_flags |= XBF_READ;
 
 	xfsbdstrat(target->bt_mount, bp);
@@ -695,9 +749,11 @@ xfs_buf_set_empty(
 	bp->b_addr = NULL;
 	bp->b_length = numblks;
 	bp->b_io_length = numblks;
+
+	ASSERT(bp->b_map_count == 1);
 	bp->b_bn = XFS_BUF_DADDR_NULL;
-	bp->b_map.bm_bn = XFS_BUF_DADDR_NULL;
-	bp->b_map.bm_len = bp->b_length;
+	bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL;
+	bp->b_maps[0].bm_len = bp->b_length;
 }
 
 static inline struct page *
@@ -761,9 +817,10 @@ xfs_buf_get_uncached(
 {
 	unsigned long		page_count;
 	int			error, i;
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
+	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
-	bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0);
+	bp = _xfs_buf_alloc(target, &map, 1, 0);
 	if (unlikely(bp == NULL))
 		goto fail;
 
@@ -794,6 +851,7 @@ xfs_buf_get_uncached(
 		__free_page(bp->b_pages[i]);
 	_xfs_buf_free_pages(bp);
  fail_free_buf:
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
  fail:
 	return NULL;
@@ -1154,36 +1212,39 @@ xfs_buf_bio_end_io(
 	bio_put(bio);
 }
 
-STATIC void
-_xfs_buf_ioapply(
-	xfs_buf_t		*bp)
+static void
+xfs_buf_ioapply_map(
+	struct xfs_buf	*bp,
+	int		map,
+	int		*buf_offset,
+	int		*count,
+	int		rw)
 {
-	int			rw, map_i, total_nr_pages, nr_pages;
-	struct bio		*bio;
-	int			offset = bp->b_offset;
-	int			size = BBTOB(bp->b_io_length);
-	sector_t		sector = bp->b_map.bm_bn;
+	int		page_index;
+	int		total_nr_pages = bp->b_page_count;
+	int		nr_pages;
+	struct bio	*bio;
+	sector_t	sector =  bp->b_maps[map].bm_bn;
+	int		size;
+	int		offset;
 
 	total_nr_pages = bp->b_page_count;
-	map_i = 0;
 
-	if (bp->b_flags & XBF_WRITE) {
-		if (bp->b_flags & XBF_SYNCIO)
-			rw = WRITE_SYNC;
-		else
-			rw = WRITE;
-		if (bp->b_flags & XBF_FUA)
-			rw |= REQ_FUA;
-		if (bp->b_flags & XBF_FLUSH)
-			rw |= REQ_FLUSH;
-	} else if (bp->b_flags & XBF_READ_AHEAD) {
-		rw = READA;
-	} else {
-		rw = READ;
+	/* skip the pages in the buffer before the start offset */
+	page_index = 0;
+	offset = *buf_offset;
+	while (offset >= PAGE_SIZE) {
+		page_index++;
+		offset -= PAGE_SIZE;
 	}
 
-	/* we only use the buffer cache for meta-data */
-	rw |= REQ_META;
+	/*
+	 * Limit the IO size to the length of the current vector, and update the
+	 * remaining IO count for the next time around.
+	 */
+	size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count);
+	*count -= size;
+	*buf_offset += size;
 
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
@@ -1198,13 +1259,14 @@ next_chunk:
 	bio->bi_private = bp;
 
 
-	for (; size && nr_pages; nr_pages--, map_i++) {
+	for (; size && nr_pages; nr_pages--, page_index++) {
 		int	rbytes, nbytes = PAGE_SIZE - offset;
 
 		if (nbytes > size)
 			nbytes = size;
 
-		rbytes = bio_add_page(bio, bp->b_pages[map_i], nbytes, offset);
+		rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes,
+				      offset);
 		if (rbytes < nbytes)
 			break;
 
@@ -1226,6 +1288,54 @@ next_chunk:
 		xfs_buf_ioerror(bp, EIO);
 		bio_put(bio);
 	}
+
+}
+
+STATIC void
+_xfs_buf_ioapply(
+	struct xfs_buf	*bp)
+{
+	struct blk_plug	plug;
+	int		rw;
+	int		offset;
+	int		size;
+	int		i;
+
+	if (bp->b_flags & XBF_WRITE) {
+		if (bp->b_flags & XBF_SYNCIO)
+			rw = WRITE_SYNC;
+		else
+			rw = WRITE;
+		if (bp->b_flags & XBF_FUA)
+			rw |= REQ_FUA;
+		if (bp->b_flags & XBF_FLUSH)
+			rw |= REQ_FLUSH;
+	} else if (bp->b_flags & XBF_READ_AHEAD) {
+		rw = READA;
+	} else {
+		rw = READ;
+	}
+
+	/* we only use the buffer cache for meta-data */
+	rw |= REQ_META;
+
+	/*
+	 * Walk all the vectors issuing IO on them. Set up the initial offset
+	 * into the buffer and the desired IO size before we start -
+	 * _xfs_buf_ioapply_vec() will modify them appropriately for each
+	 * subsequent call.
+	 */
+	offset = bp->b_offset;
+	size = BBTOB(bp->b_io_length);
+	blk_start_plug(&plug);
+	for (i = 0; i < bp->b_map_count; i++) {
+		xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+		if (bp->b_error)
+			break;
+		if (size <= 0)
+			break;	/* all done */
+	}
+	blk_finish_plug(&plug);
 }
 
 void
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c9c2ba9..67d1349 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -105,6 +105,9 @@ struct xfs_buf_map {
 	int			bm_len;	/* size of I/O */
 };
 
+#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \
+	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
+
 typedef struct xfs_buf {
 	/*
 	 * first cacheline holds all the fields needed for an uncontended cache
@@ -134,7 +137,9 @@ typedef struct xfs_buf {
 	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
-	struct xfs_buf_map	b_map;		/* compound buffer map */
+	struct xfs_buf_map	*b_maps;	/* compound buffer map */
+	struct xfs_buf_map	b_map;		/* inline compound buffer map */
+	int			b_map_count;
 	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
 	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
@@ -149,11 +154,35 @@ typedef struct xfs_buf {
 
 
 /* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags,
-				struct xfs_buf *new_bp);
-#define xfs_incore(buftarg,blkno,len,lockit) \
-	_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
+struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
+			      struct xfs_buf_map *map, int nmaps,
+			      xfs_buf_flags_t flags, struct xfs_buf *new_bp);
+
+static inline struct xfs_buf *
+xfs_incore(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_find(target, &map, 1, flags, NULL);
+}
+
+struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+
+static inline struct xfs_buf *
+xfs_buf_alloc(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_alloc(target, &map, 1, flags);
+}
 
 struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
 				size_t numblks, xfs_buf_flags_t flags);
@@ -163,8 +192,6 @@ void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
 				size_t numblks);
 
 struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
-struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
 void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
 int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 3/9] xfs: convert internal buffer functions to pass maps

[Christoph Hellwig]

On Fri, Jun 22, 2012 at 06:50:09PM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> While the external interface currently uses separate blockno/length
> variables, we need to move internal interfaces to passing and
> parsing vector maps. This will then allow us to add external
> interfaces to support discontiguous buffer maps as the internal code
> will already support them.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 4/9] xfs: add discontiguous buffer map interface

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

With the internal interfaces supporting discontiguous buffer maps,
add external lookup, read and get interfaces so they can start to be
used.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_buf.c |   37 ++++++++++++++++++-------------------
 fs/xfs/xfs_buf.h |   46 ++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 58 insertions(+), 25 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 82bb812..39c5d76 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -581,22 +581,21 @@ found:
  * more hits than misses.
  */
 struct xfs_buf *
-xfs_buf_get(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_get_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
 	struct xfs_buf		*new_bp;
 	int			error = 0;
-	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
 
-	bp = _xfs_buf_find(target, &map, 1, flags, NULL);
+	bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
 	if (likely(bp))
 		goto found;
 
-	new_bp = _xfs_buf_alloc(target, &map, 1, flags);
+	new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
@@ -606,7 +605,7 @@ xfs_buf_get(
 		return NULL;
 	}
 
-	bp = _xfs_buf_find(target, &map, 1, flags, new_bp);
+	bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
 	if (!bp) {
 		xfs_buf_free(new_bp);
 		return NULL;
@@ -649,17 +648,17 @@ _xfs_buf_read(
 }
 
 xfs_buf_t *
-xfs_buf_read(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_read_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
 
 	flags |= XBF_READ;
 
-	bp = xfs_buf_get(target, blkno, numblks, flags);
+	bp = xfs_buf_get_map(target, map, nmaps, flags);
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
@@ -687,15 +686,15 @@ xfs_buf_read(
  *	safe manner.
  */
 void
-xfs_buf_readahead(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks)
+xfs_buf_readahead_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps)
 {
 	if (bdi_read_congested(target->bt_bdi))
 		return;
 
-	xfs_buf_read(target, blkno, numblks,
+	xfs_buf_read_map(target, map, nmaps,
 		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
 }
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 67d1349..aa96bd4 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -184,12 +184,46 @@ xfs_buf_alloc(
 	return _xfs_buf_alloc(target, &map, 1, flags);
 }
 
-struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks);
+struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+void xfs_buf_readahead_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps);
+
+static inline struct xfs_buf *
+xfs_buf_get(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_get_map(target, &map, 1, flags);
+}
+
+static inline struct xfs_buf *
+xfs_buf_read(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_read_map(target, &map, 1, flags);
+}
+
+static inline void
+xfs_buf_readahead(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_readahead_map(target, &map, 1);
+}
 
 struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
 void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 5/9] xfs: add discontiguous buffer support to transactions

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

Now that the buffer cache supports discontiguous buffers, add
support to the transaction buffer interface for getting and reading
buffers.

Note that this patch does not convert the buffer item logging to
support discontiguous buffers. That will be done as a separate
commit.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_trans.h     |   50 +++++++++++++++++++++++++++++++----
 fs/xfs/xfs_trans_buf.c |   68 ++++++++++++++++++++++++------------------------
 2 files changed, 79 insertions(+), 39 deletions(-)

diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7c37b53..bc2afd5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -448,11 +448,51 @@ xfs_trans_t	*xfs_trans_dup(xfs_trans_t *);
 int		xfs_trans_reserve(xfs_trans_t *, uint, uint, uint,
 				  uint, uint);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
-struct xfs_buf	*xfs_trans_get_buf(xfs_trans_t *, struct xfs_buftarg *, xfs_daddr_t,
-				   int, uint);
-int		xfs_trans_read_buf(struct xfs_mount *, xfs_trans_t *,
-				   struct xfs_buftarg *, xfs_daddr_t, int, uint,
-				   struct xfs_buf **);
+
+struct xfs_buf	*xfs_trans_get_buf_map(struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       uint flags);
+
+static inline struct xfs_buf *
+xfs_trans_get_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	uint			flags)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_get_buf_map(tp, target, &map, 1, flags);
+}
+
+int		xfs_trans_read_buf_map(struct xfs_mount *mp,
+				       struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       xfs_buf_flags_t flags,
+				       struct xfs_buf **bpp);
+
+static inline int
+xfs_trans_read_buf(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	xfs_buf_flags_t		flags,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_read_buf_map(mp, tp, target, &map, 1, flags, bpp);
+}
+
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 21c5a5e..6311b99 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -41,20 +41,26 @@ STATIC struct xfs_buf *
 xfs_trans_buf_item_match(
 	struct xfs_trans	*tp,
 	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	int			len)
+	struct xfs_buf_map	*map,
+	int			nmaps)
 {
 	struct xfs_log_item_desc *lidp;
 	struct xfs_buf_log_item	*blip;
+	int			len = 0;
+	int			i;
+
+	for (i = 0; i < nmaps; i++)
+		len += map[i].bm_len;
 
-	len = BBTOB(len);
 	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
 		blip = (struct xfs_buf_log_item *)lidp->lid_item;
 		if (blip->bli_item.li_type == XFS_LI_BUF &&
 		    blip->bli_buf->b_target == target &&
-		    XFS_BUF_ADDR(blip->bli_buf) == blkno &&
-		    BBTOB(blip->bli_buf->b_length) == len)
+		    XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
+		    blip->bli_buf->b_length == len) {
+			ASSERT(blip->bli_buf->b_map_count == nmaps);
 			return blip->bli_buf;
+		}
 	}
 
 	return NULL;
@@ -128,21 +134,19 @@ xfs_trans_bjoin(
  * If the transaction pointer is NULL, make this just a normal
  * get_buf() call.
  */
-xfs_buf_t *
-xfs_trans_get_buf(xfs_trans_t	*tp,
-		  xfs_buftarg_t	*target_dev,
-		  xfs_daddr_t	blkno,
-		  int		len,
-		  uint		flags)
+struct xfs_buf *
+xfs_trans_get_buf_map(
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
+	xfs_buf_flags_t		flags)
 {
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;
 
-	/*
-	 * Default to a normal get_buf() call if the tp is NULL.
-	 */
-	if (tp == NULL)
-		return xfs_buf_get(target_dev, blkno, len, flags);
+	if (!tp)
+		return xfs_buf_get_map(target, map, nmaps, flags);
 
 	/*
 	 * If we find the buffer in the cache with this transaction
@@ -150,7 +154,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 	 * have it locked.  In this case we just increment the lock
 	 * recursion count and return the buffer to the caller.
 	 */
-	bp = xfs_trans_buf_item_match(tp, target_dev, blkno, len);
+	bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
 	if (bp != NULL) {
 		ASSERT(xfs_buf_islocked(bp));
 		if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
@@ -167,7 +171,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 		return (bp);
 	}
 
-	bp = xfs_buf_get(target_dev, blkno, len, flags);
+	bp = xfs_buf_get_map(target, map, nmaps, flags);
 	if (bp == NULL) {
 		return NULL;
 	}
@@ -246,26 +250,22 @@ int	xfs_error_mod = 33;
  * read_buf() call.
  */
 int
-xfs_trans_read_buf(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_buftarg_t	*target,
-	xfs_daddr_t	blkno,
-	int		len,
-	uint		flags,
-	xfs_buf_t	**bpp)
+xfs_trans_read_buf_map(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
+	xfs_buf_flags_t		flags,
+	struct xfs_buf		**bpp)
 {
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;
 	int			error;
 
 	*bpp = NULL;
-
-	/*
-	 * Default to a normal get_buf() call if the tp is NULL.
-	 */
-	if (tp == NULL) {
-		bp = xfs_buf_read(target, blkno, len, flags);
+	if (!tp) {
+		bp = xfs_buf_read_map(target, map, nmaps, flags);
 		if (!bp)
 			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);
@@ -303,7 +303,7 @@ xfs_trans_read_buf(
 	 * If the buffer is not yet read in, then we read it in, increment
 	 * the lock recursion count, and return it to the caller.
 	 */
-	bp = xfs_trans_buf_item_match(tp, target, blkno, len);
+	bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
 	if (bp != NULL) {
 		ASSERT(xfs_buf_islocked(bp));
 		ASSERT(bp->b_transp == tp);
@@ -349,7 +349,7 @@ xfs_trans_read_buf(
 		return 0;
 	}
 
-	bp = xfs_buf_read(target, blkno, len, flags);
+	bp = xfs_buf_read_map(target, map, nmaps, flags);
 	if (bp == NULL) {
 		*bpp = NULL;
 		return (flags & XBF_TRYLOCK) ?
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 6/9] xfs: support discontiguous buffers in the xfs_buf_log_item

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

>From the perspective of the log, we need to keep each segment of a
discontigous buffer in separate buffer format structures. This means log
recovery will recover all the changes on a per segment basis without
requiring any knowledge of the fact that it was logged from a
compound buffer.

To do this, we need to be able to determine what buffer segment any
given offset into the compound buffer sits over. This enables us to
translate the dirty bitmap in the number of separate buffer format
structures required.

We also need to be able to determine the number of bitmap elements
that a given buffer segment has, as this determines the size of the
buffer format structure. Hence we need to be able to determine the
both the start offset into the buffer and the length of a given
segment to be able to calculate this.

With this information, we can preallocate, build and format the
correct log vector array for each segment in a compound buffer to
appear exactly the same as individually logged buffers in the log.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_buf_item.c |  335 +++++++++++++++++++++++++++++++++++--------------
 fs/xfs/xfs_buf_item.h |    2 +
 2 files changed, 244 insertions(+), 93 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 52cd8f8..e4a6e4b 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -153,33 +153,25 @@ STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
  * If the XFS_BLI_STALE flag has been set, then log nothing.
  */
 STATIC uint
-xfs_buf_item_size(
-	struct xfs_log_item	*lip)
+xfs_buf_item_size_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_buf_log_format *blfp)
 {
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			nvecs;
 	int			next_bit;
 	int			last_bit;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	if (bip->bli_flags & XFS_BLI_STALE) {
-		/*
-		 * The buffer is stale, so all we need to log
-		 * is the buf log format structure with the
-		 * cancel flag in it.
-		 */
-		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		return 1;
-	}
+	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (last_bit == -1)
+		return 0;
+
+	/*
+	 * initial count for a dirty buffer is 2 vectors - the format structure
+	 * and the first dirty region.
+	 */
+	nvecs = 2;
 
-	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
-	nvecs = 1;
-	last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
-	ASSERT(last_bit != -1);
-	nvecs++;
 	while (last_bit != -1) {
 		/*
 		 * This takes the bit number to start looking from and
@@ -187,16 +179,15 @@ xfs_buf_item_size(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					last_bit + 1);
 		/*
 		 * If we run out of bits, leave the loop,
 		 * else if we find a new set of bits bump the number of vecs,
 		 * else keep scanning the current set of bits.
 		 */
 		if (next_bit == -1) {
-			last_bit = -1;
+			break;
 		} else if (next_bit != last_bit + 1) {
 			last_bit = next_bit;
 			nvecs++;
@@ -210,22 +201,73 @@ xfs_buf_item_size(
 		}
 	}
 
-	trace_xfs_buf_item_size(bip);
 	return nvecs;
 }
 
 /*
- * This is called to fill in the vector of log iovecs for the
- * given log buf item.  It fills the first entry with a buf log
- * format structure, and the rest point to contiguous chunks
- * within the buffer.
+ * This returns the number of log iovecs needed to log the given buf log item.
+ *
+ * It calculates this as 1 iovec for the buf log format structure and 1 for each
+ * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
+ * in a single iovec.
+ *
+ * Discontiguous buffers need a format structure per region that that is being
+ * logged. This makes the changes in the buffer appear to log recovery as though
+ * they came from separate buffers, just like would occur if multiple buffers
+ * were used instead of a single discontiguous buffer. This enables
+ * discontiguous buffers to be in-memory constructs, completely transparent to
+ * what ends up on disk.
+ *
+ * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
+ * format structures.
  */
-STATIC void
-xfs_buf_item_format(
-	struct xfs_log_item	*lip,
-	struct xfs_log_iovec	*vecp)
+STATIC uint
+xfs_buf_item_size(
+	struct xfs_log_item	*lip)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	uint			nvecs;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	if (bip->bli_flags & XFS_BLI_STALE) {
+		/*
+		 * The buffer is stale, so all we need to log
+		 * is the buf log format structure with the
+		 * cancel flag in it.
+		 */
+		trace_xfs_buf_item_size_stale(bip);
+		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		return bip->bli_format_count;
+	}
+
+	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
+
+	/*
+	 * the vector count is based on the number of buffer vectors we have
+	 * dirty bits in. This will only be greater than one when we have a
+	 * compound buffer with more than one segment dirty. Hence for compound
+	 * buffers we need to track which segment the dirty bits correspond to,
+	 * and when we move from one segment to the next increment the vector
+	 * count for the extra buf log format structure that will need to be
+	 * written.
+	 */
+	nvecs = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		nvecs += xfs_buf_item_size_segment(bip, &bip->bli_formats[i]);
+	}
+
+	trace_xfs_buf_item_size(bip);
+	return nvecs;
+}
+
+static struct xfs_log_iovec *
+xfs_buf_item_format_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_log_iovec	*vecp,
+	uint			offset,
+	struct xfs_buf_log_format *blfp)
+{
 	struct xfs_buf	*bp = bip->bli_buf;
 	uint		base_size;
 	uint		nvecs;
@@ -235,9 +277,8 @@ xfs_buf_item_format(
 	uint		nbits;
 	uint		buffer_offset;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
-	       (bip->bli_flags & XFS_BLI_STALE));
+	/* copy the flags across from the base format item */
+	blfp->blf_flags = bip->bli_format.blf_flags;
 
 	/*
 	 * Base size is the actual size of the ondisk structure - it reflects
@@ -245,28 +286,13 @@ xfs_buf_item_format(
 	 * memory structure.
 	 */
 	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
-			(bip->bli_format.blf_map_size *
-				sizeof(bip->bli_format.blf_data_map[0]));
-	vecp->i_addr = &bip->bli_format;
+			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
+	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
 	vecp++;
 	nvecs = 1;
 
-	/*
-	 * If it is an inode buffer, transfer the in-memory state to the
-	 * format flags and clear the in-memory state. We do not transfer
-	 * this state if the inode buffer allocation has not yet been committed
-	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
-	 * correct replay of the inode allocation.
-	 */
-	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
-		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
-		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
-		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
-	}
-
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		/*
 		 * The buffer is stale, so all we need to log
@@ -274,16 +300,15 @@ xfs_buf_item_format(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_format_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		bip->bli_format.blf_size = nvecs;
-		return;
+		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
+		blfp->blf_size = nvecs;
+		return vecp;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	ASSERT(first_bit != -1);
 	last_bit = first_bit;
 	nbits = 1;
@@ -294,9 +319,8 @@ xfs_buf_item_format(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 (uint)last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)last_bit + 1);
 		/*
 		 * If we run out of bits fill in the last iovec and get
 		 * out of the loop.
@@ -307,14 +331,14 @@ xfs_buf_item_format(
 		 * keep counting and scanning.
 		 */
 		if (next_bit == -1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
 			nvecs++;
 			break;
 		} else if (next_bit != last_bit + 1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
@@ -323,14 +347,17 @@ xfs_buf_item_format(
 			first_bit = next_bit;
 			last_bit = next_bit;
 			nbits = 1;
-		} else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
-			   (xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
+		} else if (xfs_buf_offset(bp, offset +
+					      (next_bit << XFS_BLF_SHIFT)) !=
+			   (xfs_buf_offset(bp, offset +
+					       (last_bit << XFS_BLF_SHIFT)) +
 			    XFS_BLF_CHUNK)) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/* You would think we need to bump the nvecs here too, but we do not
+/*
+ * You would think we need to bump the nvecs here too, but we do not
  * this number is used by recovery, and it gets confused by the boundary
  * split here
  *			nvecs++;
@@ -345,6 +372,48 @@ xfs_buf_item_format(
 		}
 	}
 	bip->bli_format.blf_size = nvecs;
+	return vecp;
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the
+ * given log buf item.  It fills the first entry with a buf log
+ * format structure, and the rest point to contiguous chunks
+ * within the buffer.
+ */
+STATIC void
+xfs_buf_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_iovec	*vecp)
+{
+	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	struct xfs_buf		*bp = bip->bli_buf;
+	uint			offset = 0;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+	       (bip->bli_flags & XFS_BLI_STALE));
+
+	/*
+	 * If it is an inode buffer, transfer the in-memory state to the
+	 * format flags and clear the in-memory state. We do not transfer
+	 * this state if the inode buffer allocation has not yet been committed
+	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
+	 * correct replay of the inode allocation.
+	 */
+	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
+		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+		      xfs_log_item_in_current_chkpt(lip)))
+			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+	}
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		vecp = xfs_buf_item_format_segment(bip, vecp, offset,
+						&bip->bli_formats[i]);
+		offset += bp->b_maps[i].bm_len;
+	}
 
 	/*
 	 * Check to make sure everything is consistent.
@@ -620,6 +689,35 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_committing = xfs_buf_item_committing
 };
 
+STATIC int
+xfs_buf_item_get_format(
+	struct xfs_buf_log_item	*bip,
+	int			count)
+{
+	ASSERT(bip->bli_formats == NULL);
+	bip->bli_format_count = count;
+
+	if (count == 1) {
+		bip->bli_formats = &bip->bli_format;
+		return 0;
+	}
+
+	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
+				KM_SLEEP);
+	if (!bip->bli_formats)
+		return ENOMEM;
+	return 0;
+}
+
+STATIC void
+xfs_buf_item_free_format(
+	struct xfs_buf_log_item	*bip)
+{
+	if (bip->bli_formats != &bip->bli_format) {
+		kmem_free(bip->bli_formats);
+		bip->bli_formats = NULL;
+	}
+}
 
 /*
  * Allocate a new buf log item to go with the given buffer.
@@ -637,6 +735,8 @@ xfs_buf_item_init(
 	xfs_buf_log_item_t	*bip;
 	int			chunks;
 	int			map_size;
+	int			error;
+	int			i;
 
 	/*
 	 * Check to see if there is already a buf log item for
@@ -648,25 +748,33 @@ xfs_buf_item_init(
 	if (lip != NULL && lip->li_type == XFS_LI_BUF)
 		return;
 
-	/*
-	 * chunks is the number of XFS_BLF_CHUNK size pieces
-	 * the buffer can be divided into. Make sure not to
-	 * truncate any pieces.  map_size is the size of the
-	 * bitmap needed to describe the chunks of the buffer.
-	 */
-	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
-								XFS_BLF_SHIFT);
-	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
-
-	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
-						    KM_SLEEP);
+	bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
 	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
 	bip->bli_buf = bp;
 	xfs_buf_hold(bp);
-	bip->bli_format.blf_type = XFS_LI_BUF;
-	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)bp->b_length;
-	bip->bli_format.blf_map_size = map_size;
+
+	/*
+	 * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
+	 * can be divided into. Make sure not to truncate any pieces.
+	 * map_size is the size of the bitmap needed to describe the
+	 * chunks of the buffer.
+	 *
+	 * Discontiguous buffer support follows the layout of the underlying
+	 * buffer. This makes the implementation as simple as possible.
+	 */
+	error = xfs_buf_item_get_format(bip, bp->b_map_count);
+	ASSERT(error == 0);
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+				      XFS_BLF_CHUNK);
+		map_size = DIV_ROUND_UP(chunks, NBWORD);
+
+		bip->bli_formats[i].blf_type = XFS_LI_BUF;
+		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
+		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
+		bip->bli_formats[i].blf_map_size = map_size;
+	}
 
 #ifdef XFS_TRANS_DEBUG
 	/*
@@ -697,10 +805,11 @@ xfs_buf_item_init(
  * item's bitmap.
  */
 void
-xfs_buf_item_log(
-	xfs_buf_log_item_t	*bip,
+xfs_buf_item_log_segment(
+	struct xfs_buf_log_item	*bip,
 	uint			first,
-	uint			last)
+	uint			last,
+	uint			*map)
 {
 	uint		first_bit;
 	uint		last_bit;
@@ -713,12 +822,6 @@ xfs_buf_item_log(
 	uint		mask;
 
 	/*
-	 * Mark the item as having some dirty data for
-	 * quick reference in xfs_buf_item_dirty.
-	 */
-	bip->bli_flags |= XFS_BLI_DIRTY;
-
-	/*
 	 * Convert byte offsets to bit numbers.
 	 */
 	first_bit = first >> XFS_BLF_SHIFT;
@@ -734,7 +837,7 @@ xfs_buf_item_log(
 	 * to set a bit in.
 	 */
 	word_num = first_bit >> BIT_TO_WORD_SHIFT;
-	wordp = &(bip->bli_format.blf_data_map[word_num]);
+	wordp = &map[word_num];
 
 	/*
 	 * Calculate the starting bit in the first word.
@@ -781,6 +884,51 @@ xfs_buf_item_log(
 	xfs_buf_item_log_debug(bip, first, last);
 }
 
+/*
+ * Mark bytes first through last inclusive as dirty in the buf
+ * item's bitmap.
+ */
+void
+xfs_buf_item_log(
+	xfs_buf_log_item_t	*bip,
+	uint			first,
+	uint			last)
+{
+	int			i;
+	uint			start;
+	uint			end;
+	struct xfs_buf		*bp = bip->bli_buf;
+
+	/*
+	 * Mark the item as having some dirty data for
+	 * quick reference in xfs_buf_item_dirty.
+	 */
+	bip->bli_flags |= XFS_BLI_DIRTY;
+
+	/*
+	 * walk each buffer segment and mark them dirty appropriately.
+	 */
+	start = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (start > last)
+			break;
+		end = start + BBTOB(bp->b_maps[i].bm_len);
+		if (first > end) {
+			start += BBTOB(bp->b_maps[i].bm_len);
+			continue;
+		}
+		if (first < start)
+			first = start;
+		if (end > last)
+			end = last;
+
+		xfs_buf_item_log_segment(bip, first, end,
+					 &bip->bli_formats[i].blf_data_map[0]);
+
+		start += bp->b_maps[i].bm_len;
+	}
+}
+
 
 /*
  * Return 1 if the buffer has some data that has been logged (at any
@@ -802,6 +950,7 @@ xfs_buf_item_free(
 	kmem_free(bip->bli_logged);
 #endif /* XFS_TRANS_DEBUG */
 
+	xfs_buf_item_free_format(bip);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index ff26867..6850f49 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -102,6 +102,8 @@ typedef struct xfs_buf_log_item {
 	char			*bli_orig;	/* original buffer copy */
 	char			*bli_logged;	/* bytes logged (bitmap) */
 #endif
+	int			bli_format_count;	/* count of headers */
+	struct xfs_buf_log_format *bli_formats;	/* array of in-log header ptrs */
 	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 7/9] xfs: use discontiguous xfs_buf support in dabuf wrappers

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

First step in converting the directory code to use native
discontiguous buffers and replacing the dabuf construct.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_da_btree.c |  538 ++++++++++++++++++++++---------------------------
 fs/xfs/xfs_da_btree.h |    6 +-
 2 files changed, 239 insertions(+), 305 deletions(-)

diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 015b946..76e5dba 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -85,7 +85,7 @@ STATIC void xfs_da_node_unbalance(xfs_da_state_t *state,
  */
 STATIC uint	xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count);
 STATIC int	xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp);
-STATIC xfs_dabuf_t *xfs_da_buf_make(int nbuf, xfs_buf_t **bps);
+STATIC xfs_dabuf_t *xfs_da_buf_make(xfs_buf_t *bp);
 STATIC int	xfs_da_blk_unlink(xfs_da_state_t *state,
 				  xfs_da_state_blk_t *drop_blk,
 				  xfs_da_state_blk_t *save_blk);
@@ -1967,35 +1967,75 @@ xfs_da_map_covers_blocks(
 }
 
 /*
- * Make a dabuf.
- * Used for get_buf, read_buf, read_bufr, and reada_buf.
+ * Convert a struct xfs_bmbt_irec to a struct xfs_buf_map.
+ *
+ * For the single map case, it is assumed that the caller has provided a pointer
+ * to a valid xfs_buf_map.  For the multiple map case, this function will
+ * allocate the xfs_buf_map to hold all the maps and replace the caller's single
+ * map pointer with the allocated map.
  */
-STATIC int
-xfs_da_do_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t	*mappedbnop,
-	xfs_dabuf_t	**bpp,
-	int		whichfork,
-	int		caller)
+static int
+xfs_buf_map_from_irec(
+	struct xfs_mount	*mp,
+	struct xfs_buf_map	**mapp,
+	unsigned int		*nmaps,
+	struct xfs_bmbt_irec	*irecs,
+	unsigned int		nirecs)
 {
-	xfs_buf_t	*bp = NULL;
-	xfs_buf_t	**bplist;
-	int		error=0;
-	int		i;
-	xfs_bmbt_irec_t	map;
-	xfs_bmbt_irec_t	*mapp;
-	xfs_daddr_t	mappedbno;
-	xfs_mount_t	*mp;
-	int		nbplist=0;
-	int		nfsb;
-	int		nmap;
-	xfs_dabuf_t	*rbp;
+	struct xfs_buf_map	*map;
+	int			i;
+
+	ASSERT(*nmaps == 1);
+	ASSERT(nirecs >= 1);
+
+	if (nirecs > 1) {
+		map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), KM_SLEEP);
+		if (!map)
+			return ENOMEM;
+		*mapp = map;
+	}
+
+	*nmaps = nirecs;
+	map = *mapp;
+	for (i = 0; i < *nmaps; i++) {
+		ASSERT(irecs[i].br_startblock != DELAYSTARTBLOCK &&
+		       irecs[i].br_startblock != HOLESTARTBLOCK);
+		map[i].bm_bn = XFS_FSB_TO_DADDR(mp, irecs[i].br_startblock);
+		map[i].bm_len = XFS_FSB_TO_BB(mp, irecs[i].br_blockcount);
+	}
+	return 0;
+}
+
+/*
+ * Map the block we are given ready for reading. There are three possible return
+ * values:
+ *	-1 - will be returned if we land in a hole and mappedbno == -2 so the
+ *	     caller knows not to execute a subsequent read.
+ *	 0 - if we mapped the block successfully
+ *	>0 - positive error number if there was an error.
+ */
+static int
+xfs_dabuf_map(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	int			whichfork,
+	struct xfs_buf_map	**map,
+	int			*nmaps)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	int			nfsb;
+	int			error = 0;
+	struct xfs_bmbt_irec	irec;
+	struct xfs_bmbt_irec	*irecs = &irec;
+	int			nirecs;
+
+	ASSERT(map && *map);
+	ASSERT(*nmaps == 1);
 
-	mp = dp->i_mount;
 	nfsb = (whichfork == XFS_DATA_FORK) ? mp->m_dirblkfsbs : 1;
-	mappedbno = *mappedbnop;
+
 	/*
 	 * Caller doesn't have a mapping.  -2 means don't complain
 	 * if we land in a hole.
@@ -2004,112 +2044,152 @@ xfs_da_do_buf(
 		/*
 		 * Optimize the one-block case.
 		 */
-		if (nfsb == 1)
-			mapp = &map;
-		else
-			mapp = kmem_alloc(sizeof(*mapp) * nfsb, KM_SLEEP);
+		if (nfsb != 1)
+			irecs = kmem_zalloc(sizeof(irec) * nfsb, KM_SLEEP);
 
-		nmap = nfsb;
-		error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, mapp,
-				       &nmap, xfs_bmapi_aflag(whichfork));
+		nirecs = nfsb;
+		error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, irecs,
+				       &nirecs, xfs_bmapi_aflag(whichfork));
 		if (error)
-			goto exit0;
+			goto out;
 	} else {
-		map.br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
-		map.br_startoff = (xfs_fileoff_t)bno;
-		map.br_blockcount = nfsb;
-		mapp = &map;
-		nmap = 1;
+		irecs->br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
+		irecs->br_startoff = (xfs_fileoff_t)bno;
+		irecs->br_blockcount = nfsb;
+		irecs->br_state = 0;
+		nirecs = 1;
 	}
-	if (!xfs_da_map_covers_blocks(nmap, mapp, bno, nfsb)) {
-		error = mappedbno == -2 ? 0 : XFS_ERROR(EFSCORRUPTED);
+
+	if (!xfs_da_map_covers_blocks(nirecs, irecs, bno, nfsb)) {
+		error = mappedbno == -2 ? -1 : XFS_ERROR(EFSCORRUPTED);
 		if (unlikely(error == EFSCORRUPTED)) {
 			if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
+				int i;
 				xfs_alert(mp, "%s: bno %lld dir: inode %lld",
 					__func__, (long long)bno,
 					(long long)dp->i_ino);
-				for (i = 0; i < nmap; i++) {
+				for (i = 0; i < *nmaps; i++) {
 					xfs_alert(mp,
 "[%02d] br_startoff %lld br_startblock %lld br_blockcount %lld br_state %d",
 						i,
-						(long long)mapp[i].br_startoff,
-						(long long)mapp[i].br_startblock,
-						(long long)mapp[i].br_blockcount,
-						mapp[i].br_state);
+						(long long)irecs[i].br_startoff,
+						(long long)irecs[i].br_startblock,
+						(long long)irecs[i].br_blockcount,
+						irecs[i].br_state);
 				}
 			}
 			XFS_ERROR_REPORT("xfs_da_do_buf(1)",
 					 XFS_ERRLEVEL_LOW, mp);
 		}
-		goto exit0;
+		goto out;
 	}
-	if (caller != 3 && nmap > 1) {
-		bplist = kmem_alloc(sizeof(*bplist) * nmap, KM_SLEEP);
-		nbplist = 0;
-	} else
-		bplist = NULL;
-	/*
-	 * Turn the mapping(s) into buffer(s).
-	 */
-	for (i = 0; i < nmap; i++) {
-		int	nmapped;
-
-		mappedbno = XFS_FSB_TO_DADDR(mp, mapp[i].br_startblock);
-		if (i == 0)
-			*mappedbnop = mappedbno;
-		nmapped = (int)XFS_FSB_TO_BB(mp, mapp[i].br_blockcount);
-		switch (caller) {
-		case 0:
-			bp = xfs_trans_get_buf(trans, mp->m_ddev_targp,
-				mappedbno, nmapped, 0);
-			error = bp ? bp->b_error : XFS_ERROR(EIO);
-			break;
-		case 1:
-		case 2:
-			bp = NULL;
-			error = xfs_trans_read_buf(mp, trans, mp->m_ddev_targp,
-				mappedbno, nmapped, 0, &bp);
-			break;
-		case 3:
-			xfs_buf_readahead(mp->m_ddev_targp, mappedbno, nmapped);
+	error = xfs_buf_map_from_irec(mp, map, nmaps, irecs, nirecs);
+out:
+	if (irecs != &irec)
+		kmem_free(irecs);
+	return error;
+}
+
+/*
+ * Get a buffer for the dir/attr block.
+ */
+int
+xfs_da_get_buf(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	xfs_dabuf_t		**bpp,
+	int			whichfork)
+{
+	struct xfs_buf		*bp;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	*bpp = NULL;
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
 			error = 0;
-			bp = NULL;
-			break;
-		}
-		if (error) {
-			if (bp)
-				xfs_trans_brelse(trans, bp);
-			goto exit1;
-		}
-		if (!bp)
-			continue;
-		if (caller == 1) {
-			if (whichfork == XFS_ATTR_FORK)
-				xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
-			else
-				xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
-		}
-		if (bplist) {
-			bplist[nbplist++] = bp;
-		}
+		goto out_free;
 	}
-	/*
-	 * Build a dabuf structure.
-	 */
-	if (bplist) {
-		rbp = xfs_da_buf_make(nbplist, bplist);
-	} else if (bp)
-		rbp = xfs_da_buf_make(1, &bp);
+
+	bp = xfs_trans_get_buf_map(trans, dp->i_mount->m_ddev_targp,
+				    mapp, nmap, 0);
+	error = bp ? bp->b_error : XFS_ERROR(EIO);
+	if (error) {
+		xfs_trans_brelse(trans, bp);
+		goto out_free;
+	}
+
+	*bpp = xfs_da_buf_make(bp);
+
+out_free:
+	if (mapp != &map)
+		kmem_free(mapp);
+
+	return error;
+}
+
+/*
+ * Get a buffer for the dir/attr block, fill in the contents.
+ */
+int
+xfs_da_read_buf(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	xfs_dabuf_t		**bpp,
+	int			whichfork)
+{
+	struct xfs_buf		*bp;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	*bpp = NULL;
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
+			error = 0;
+		goto out_free;
+	}
+
+	error = xfs_trans_read_buf_map(dp->i_mount, trans,
+					dp->i_mount->m_ddev_targp,
+					mapp, nmap, 0, &bp);
+	if (error)
+		goto out_free;
+
+	if (whichfork == XFS_ATTR_FORK)
+		xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
 	else
-		rbp = NULL;
+		xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
+
+	*bpp = xfs_da_buf_make(bp);
+
 	/*
-	 * For read_buf, check the magic number.
+	 * This verification code will be moved to a CRC verification callback
+	 * function so just leave it here unchanged until then.
 	 */
-	if (caller == 1) {
-		xfs_dir2_data_hdr_t	*hdr = rbp->data;
-		xfs_dir2_free_t		*free = rbp->data;
-		xfs_da_blkinfo_t	*info = rbp->data;
+	{
+		xfs_dir2_data_hdr_t	*hdr = (*bpp)->data;
+		xfs_dir2_free_t		*free = (*bpp)->data;
+		xfs_da_blkinfo_t	*info = (*bpp)->data;
 		uint			magic, magic1;
+		struct xfs_mount	*mp = dp->i_mount;
 
 		magic = be16_to_cpu(info->magic);
 		magic1 = be32_to_cpu(hdr->magic);
@@ -2123,66 +2203,20 @@ xfs_da_do_buf(
 				   (free->hdr.magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC)),
 				mp, XFS_ERRTAG_DA_READ_BUF,
 				XFS_RANDOM_DA_READ_BUF))) {
-			trace_xfs_da_btree_corrupt(rbp->bps[0], _RET_IP_);
+			trace_xfs_da_btree_corrupt(bp, _RET_IP_);
 			XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
 					     XFS_ERRLEVEL_LOW, mp, info);
 			error = XFS_ERROR(EFSCORRUPTED);
-			xfs_da_brelse(trans, rbp);
-			nbplist = 0;
-			goto exit1;
+			xfs_da_brelse(trans, *bpp);
+			goto out_free;
 		}
 	}
-	if (bplist) {
-		kmem_free(bplist);
-	}
-	if (mapp != &map) {
-		kmem_free(mapp);
-	}
-	if (bpp)
-		*bpp = rbp;
-	return 0;
-exit1:
-	if (bplist) {
-		for (i = 0; i < nbplist; i++)
-			xfs_trans_brelse(trans, bplist[i]);
-		kmem_free(bplist);
-	}
-exit0:
+
+out_free:
 	if (mapp != &map)
 		kmem_free(mapp);
-	if (bpp)
-		*bpp = NULL;
-	return error;
-}
-
-/*
- * Get a buffer for the dir/attr block.
- */
-int
-xfs_da_get_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t	**bpp,
-	int		whichfork)
-{
-	return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 0);
-}
 
-/*
- * Get a buffer for the dir/attr block, fill in the contents.
- */
-int
-xfs_da_read_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t	**bpp,
-	int		whichfork)
-{
-	return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 1);
+	return error;
 }
 
 /*
@@ -2190,18 +2224,38 @@ xfs_da_read_buf(
  */
 xfs_daddr_t
 xfs_da_reada_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	int		whichfork)
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	int			whichfork)
 {
-	xfs_daddr_t		rval;
+	xfs_daddr_t		mappedbno = -1;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, -1, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
+			error = 0;
+		goto out_free;
+	}
 
-	rval = -1;
-	if (xfs_da_do_buf(trans, dp, bno, &rval, NULL, whichfork, 3))
+	mappedbno = mapp[0].bm_bn;
+	xfs_buf_readahead_map(dp->i_mount->m_ddev_targp, mapp, nmap);
+
+out_free:
+	if (mapp != &map)
+		kmem_free(mapp);
+
+	if (error)
 		return -1;
-	else
-		return rval;
+	return mappedbno;
 }
 
 kmem_zone_t *xfs_da_state_zone;	/* anchor for state struct zone */
@@ -2261,78 +2315,25 @@ xfs_da_state_free(xfs_da_state_t *state)
  */
 /* ARGSUSED */
 STATIC xfs_dabuf_t *
-xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
+xfs_da_buf_make(xfs_buf_t *bp)
 {
-	xfs_buf_t	*bp;
 	xfs_dabuf_t	*dabuf;
-	int		i;
-	int		off;
 
-	if (nbuf == 1)
-		dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
-	else
-		dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
-	dabuf->dirty = 0;
-	if (nbuf == 1) {
-		dabuf->nbuf = 1;
-		bp = bps[0];
-		dabuf->bbcount = bp->b_length;
-		dabuf->data = bp->b_addr;
-		dabuf->bps[0] = bp;
-	} else {
-		dabuf->nbuf = nbuf;
-		for (i = 0, dabuf->bbcount = 0; i < nbuf; i++) {
-			dabuf->bps[i] = bp = bps[i];
-			dabuf->bbcount += bp->b_length;
-		}
-		dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP);
-		for (i = off = 0; i < nbuf; i++, off += BBTOB(bp->b_length)) {
-			bp = bps[i];
-			memcpy((char *)dabuf->data + off, bp->b_addr,
-				BBTOB(bp->b_length));
-		}
-	}
+	dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
+	dabuf->bbcount = bp->b_length;
+	dabuf->data = bp->b_addr;
+	dabuf->bp = bp;
 	return dabuf;
 }
 
 /*
- * Un-dirty a dabuf.
- */
-STATIC void
-xfs_da_buf_clean(xfs_dabuf_t *dabuf)
-{
-	xfs_buf_t	*bp;
-	int		i;
-	int		off;
-
-	if (dabuf->dirty) {
-		ASSERT(dabuf->nbuf > 1);
-		dabuf->dirty = 0;
-		for (i = off = 0; i < dabuf->nbuf;
-				i++, off += BBTOB(bp->b_length)) {
-			bp = dabuf->bps[i];
-			memcpy(bp->b_addr, dabuf->data + off,
-						BBTOB(bp->b_length));
-		}
-	}
-}
-
-/*
  * Release a dabuf.
  */
 void
 xfs_da_buf_done(xfs_dabuf_t *dabuf)
 {
-	ASSERT(dabuf);
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if (dabuf->dirty)
-		xfs_da_buf_clean(dabuf);
-	if (dabuf->nbuf > 1) {
-		kmem_free(dabuf->data);
-		kmem_free(dabuf);
-	} else {
-		kmem_zone_free(xfs_dabuf_zone, dabuf);
-	}
+	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
+	kmem_zone_free(xfs_dabuf_zone, dabuf);
 }
 
 /*
@@ -2341,41 +2342,9 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf)
 void
 xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
 {
-	xfs_buf_t	*bp;
-	uint		f;
-	int		i;
-	uint		l;
-	int		off;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if (dabuf->nbuf == 1) {
-		ASSERT(dabuf->data == dabuf->bps[0]->b_addr);
-		xfs_trans_log_buf(tp, dabuf->bps[0], first, last);
-		return;
-	}
-	dabuf->dirty = 1;
-	ASSERT(first <= last);
-	for (i = off = 0; i < dabuf->nbuf; i++, off += BBTOB(bp->b_length)) {
-		bp = dabuf->bps[i];
-		f = off;
-		l = f + BBTOB(bp->b_length) - 1;
-		if (f < first)
-			f = first;
-		if (l > last)
-			l = last;
-		if (f <= l)
-			xfs_trans_log_buf(tp, bp, f - off, l - off);
-		/*
-		 * B_DONE is set by xfs_trans_log buf.
-		 * If we don't set it on a new buffer (get not read)
-		 * then if we don't put anything in the buffer it won't
-		 * be set, and at commit it it released into the cache,
-		 * and then a read will fail.
-		 */
-		else if (!(XFS_BUF_ISDONE(bp)))
-		  XFS_BUF_DONE(bp);
-	}
-	ASSERT(last < off);
+	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
+	ASSERT(dabuf->data == dabuf->bp->b_addr);
+	xfs_trans_log_buf(tp, dabuf->bp, first, last);
 }
 
 /*
@@ -2386,24 +2355,9 @@ xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
 void
 xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
 {
-	xfs_buf_t	*bp;
-	xfs_buf_t	**bplist;
-	int		i;
-	int		nbuf;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if ((nbuf = dabuf->nbuf) == 1) {
-		bplist = &bp;
-		bp = dabuf->bps[0];
-	} else {
-		bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
-		memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
-	}
+	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
+	xfs_trans_brelse(tp, dabuf->bp);
 	xfs_da_buf_done(dabuf);
-	for (i = 0; i < nbuf; i++)
-		xfs_trans_brelse(tp, bplist[i]);
-	if (bplist != &bp)
-		kmem_free(bplist);
 }
 
 /*
@@ -2412,24 +2366,9 @@ xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
 void
 xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
 {
-	xfs_buf_t	*bp;
-	xfs_buf_t	**bplist;
-	int		i;
-	int		nbuf;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if ((nbuf = dabuf->nbuf) == 1) {
-		bplist = &bp;
-		bp = dabuf->bps[0];
-	} else {
-		bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
-		memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
-	}
+	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
 	xfs_da_buf_done(dabuf);
-	for (i = 0; i < nbuf; i++)
-		xfs_trans_binval(tp, bplist[i]);
-	if (bplist != &bp)
-		kmem_free(bplist);
+	xfs_trans_binval(tp, dabuf->bp);
 }
 
 /*
@@ -2438,7 +2377,6 @@ xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
 xfs_daddr_t
 xfs_da_blkno(xfs_dabuf_t *dabuf)
 {
-	ASSERT(dabuf->nbuf);
 	ASSERT(dabuf->data);
-	return XFS_BUF_ADDR(dabuf->bps[0]);
+	return XFS_BUF_ADDR(dabuf->bp);
 }
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index dbf7c07..0b64c4a 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -141,14 +141,10 @@ typedef struct xfs_da_args {
  * same place as the b_addr field for the buffer, else to kmem_alloced memory.
  */
 typedef struct xfs_dabuf {
-	int		nbuf;		/* number of buffer pointers present */
-	short		dirty;		/* data needs to be copied back */
 	short		bbcount;	/* how large is data in bbs */
 	void		*data;		/* pointer for buffers' data */
-	struct xfs_buf	*bps[1];	/* actually nbuf of these */
+	struct xfs_buf	*bp;		/* actually nbuf of these */
 } xfs_dabuf_t;
-#define	XFS_DA_BUF_SIZE(n)	\
-	(sizeof(xfs_dabuf_t) + sizeof(struct xfs_buf *) * ((n) - 1))
 
 /*
  * Storage for holding state during Btree searches and split/join ops.
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 8/9] xfs: remove struct xfs_dabuf and infrastructure

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

The struct xfs_dabuf now only tracks a single xfs_buf and all the
information it holds can be gained directly from the xfs_buf. Hence
we can remove the struct dabuf and pass the xfs_buf around
everywhere.

Kill the struct dabuf and the associated infrastructure.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_attr.c       |   78 +++++------
 fs/xfs/xfs_attr_leaf.c  |  255 +++++++++++++++++++----------------
 fs/xfs/xfs_attr_leaf.h  |   21 ++-
 fs/xfs/xfs_da_btree.c   |  337 +++++++++++++++++------------------------------
 fs/xfs/xfs_da_btree.h   |   32 +----
 fs/xfs/xfs_dir2.c       |    4 +-
 fs/xfs/xfs_dir2_block.c |  118 +++++++----------
 fs/xfs/xfs_dir2_data.c  |   50 +++----
 fs/xfs/xfs_dir2_leaf.c  |  191 +++++++++++++--------------
 fs/xfs/xfs_dir2_node.c  |  236 ++++++++++++++-------------------
 fs/xfs/xfs_dir2_priv.h  |   46 +++----
 fs/xfs/xfs_dir2_sf.c    |    4 +-
 fs/xfs/xfs_super.c      |    9 +-
 13 files changed, 602 insertions(+), 779 deletions(-)

diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index a17ff01..0ca1f0b 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -893,7 +893,7 @@ STATIC int
 xfs_attr_leaf_addname(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
@@ -915,11 +915,11 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 */
 	retval = xfs_attr_leaf_lookup_int(bp, args);
 	if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(retval);
 	} else if (retval == EEXIST) {
 		if (args->flags & ATTR_CREATE) {	/* pure create op */
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 			return(retval);
 		}
 
@@ -937,7 +937,6 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 * if required.
 	 */
 	retval = xfs_attr_leaf_add(bp, args);
-	xfs_da_buf_done(bp);
 	if (retval == ENOSPC) {
 		/*
 		 * Promote the attribute list to the Btree format, then
@@ -1065,8 +1064,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			 */
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
-		} else
-			xfs_da_buf_done(bp);
+		}
 
 		/*
 		 * Commit the remove and start the next trans in series.
@@ -1092,7 +1090,7 @@ STATIC int
 xfs_attr_leaf_removename(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error, committed, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
@@ -1111,7 +1109,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	ASSERT(bp != NULL);
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error == ENOATTR) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 
@@ -1141,8 +1139,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 		 */
 		if (committed)
 			xfs_trans_ijoin(args->trans, dp, 0);
-	} else
-		xfs_da_buf_done(bp);
+	}
 	return(0);
 }
 
@@ -1155,7 +1152,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 STATIC int
 xfs_attr_leaf_get(xfs_da_args_t *args)
 {
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	args->blkno = 0;
@@ -1167,11 +1164,11 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
 
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error != EEXIST)  {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 	error = xfs_attr_leaf_getvalue(bp, args);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
 		error = xfs_attr_rmtval_get(args);
 	}
@@ -1186,23 +1183,23 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 {
 	xfs_attr_leafblock_t *leaf;
 	int error;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	context->cursor->blkno = 0;
 	error = xfs_da_read_buf(NULL, context->dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return XFS_ERROR(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	if (unlikely(leaf->hdr.info.magic != cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_attr_leaf_list", XFS_ERRLEVEL_LOW,
 				     context->dp->i_mount, leaf);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
 	error = xfs_attr_leaf_list_int(bp, context);
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return XFS_ERROR(error);
 }
 
@@ -1489,7 +1486,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_da_state_t *state;
 	xfs_da_state_blk_t *blk;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_node_removename(args);
@@ -1601,14 +1598,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 		 */
 		ASSERT(state->path.active == 1);
 		ASSERT(state->path.blk[0].bp);
-		xfs_da_buf_done(state->path.blk[0].bp);
 		state->path.blk[0].bp = NULL;
 
 		error = xfs_da_read_buf(args->trans, args->dp, 0, -1, &bp,
 						     XFS_ATTR_FORK);
 		if (error)
 			goto out;
-		ASSERT((((xfs_attr_leafblock_t *)bp->data)->hdr.info.magic) ==
+		ASSERT((((xfs_attr_leafblock_t *)bp->b_addr)->hdr.info.magic) ==
 		       cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
@@ -1635,7 +1631,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
 		} else
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 	}
 	error = 0;
 
@@ -1665,8 +1661,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1681,8 +1676,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1792,7 +1786,7 @@ xfs_attr_node_get(xfs_da_args_t *args)
 	 * If not in a transaction, we have to release all the buffers.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 
@@ -1808,7 +1802,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	xfs_da_intnode_t *node;
 	xfs_da_node_entry_t *btree;
 	int error, i;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	cursor = context->cursor;
 	cursor->initted = 1;
@@ -1825,30 +1819,30 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		if ((error != 0) && (error != EFSCORRUPTED))
 			return(error);
 		if (bp) {
-			node = bp->data;
+			node = bp->b_addr;
 			switch (be16_to_cpu(node->hdr.info.magic)) {
 			case XFS_DA_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 				break;
 			case XFS_ATTR_LEAF_MAGIC:
-				leaf = bp->data;
+				leaf = bp->b_addr;
 				if (cursor->hashval > be32_to_cpu(leaf->entries[
 				    be16_to_cpu(leaf->hdr.count)-1].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				} else if (cursor->hashval <=
 					     be32_to_cpu(leaf->entries[0].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				}
 				break;
 			default:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 			}
 		}
@@ -1873,7 +1867,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						 context->dp->i_mount);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
-			node = bp->data;
+			node = bp->b_addr;
 			if (node->hdr.info.magic ==
 			    cpu_to_be16(XFS_ATTR_LEAF_MAGIC))
 				break;
@@ -1883,7 +1877,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						     XFS_ERRLEVEL_LOW,
 						     context->dp->i_mount,
 						     node);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
 			btree = node->btree;
@@ -1898,10 +1892,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				}
 			}
 			if (i == be16_to_cpu(node->hdr.count)) {
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(0);
 			}
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 		}
 	}
 	ASSERT(bp != NULL);
@@ -1912,24 +1906,24 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 * adding the information.
 	 */
 	for (;;) {
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		if (unlikely(leaf->hdr.info.magic !=
 			     cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 			XFS_CORRUPTION_ERROR("xfs_attr_node_list(4)",
 					     XFS_ERRLEVEL_LOW,
 					     context->dp->i_mount, leaf);
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 		error = xfs_attr_leaf_list_int(bp, context);
 		if (error) {
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return error;
 		}
 		if (context->seen_enough || leaf->hdr.info.forw == 0)
 			break;
 		cursor->blkno = be32_to_cpu(leaf->hdr.info.forw);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		error = xfs_da_read_buf(NULL, context->dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if (error)
@@ -1941,7 +1935,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 	}
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return(0);
 }
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 7d89d80..d330111 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -54,10 +54,10 @@
  * Routines used for growing the Btree.
  */
 STATIC int xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t which_block,
-				    xfs_dabuf_t **bpp);
-STATIC int xfs_attr_leaf_add_work(xfs_dabuf_t *leaf_buffer, xfs_da_args_t *args,
-					      int freemap_index);
-STATIC void xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *leaf_buffer);
+				struct xfs_buf **bpp);
+STATIC int xfs_attr_leaf_add_work(struct xfs_buf *leaf_buffer,
+				  xfs_da_args_t *args, int freemap_index);
+STATIC void xfs_attr_leaf_compact(xfs_trans_t *tp, struct xfs_buf *leaf_buffer);
 STATIC void xfs_attr_leaf_rebalance(xfs_da_state_t *state,
 						   xfs_da_state_blk_t *blk1,
 						   xfs_da_state_blk_t *blk2);
@@ -71,9 +71,9 @@ STATIC int xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
  * Routines used for shrinking the Btree.
  */
 STATIC int xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp, int level);
+				  struct xfs_buf *bp, int level);
 STATIC int xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp);
+				  struct xfs_buf *bp);
 STATIC int xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
 				   xfs_dablk_t blkno, int blkcnt);
 
@@ -480,7 +480,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	char *tmpbuffer;
 	int error, i, size;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	xfs_ifork_t *ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
@@ -550,8 +550,6 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	error = 0;
 
 out:
-	if(bp)
-		xfs_da_buf_done(bp);
 	kmem_free(tmpbuffer);
 	return(error);
 }
@@ -737,14 +735,16 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
  * a shortform attribute list.
  */
 int
-xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
+xfs_attr_shortform_allfit(
+	struct xfs_buf	*bp,
+	struct xfs_inode *dp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_local_t *name_loc;
 	int bytes, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	entry = &leaf->entries[0];
@@ -774,7 +774,10 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
  * Convert a leaf attribute list to shortform attribute list
  */
 int
-xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
+xfs_attr_leaf_to_shortform(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		forkoff)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -791,10 +794,10 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	ASSERT(tmpbuffer != NULL);
 
 	ASSERT(bp != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(dp->i_mount));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(dp->i_mount));
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
-	memset(bp->data, 0, XFS_LBSIZE(dp->i_mount));
+	memset(bp->b_addr, 0, XFS_LBSIZE(dp->i_mount));
 
 	/*
 	 * Clean out the prior contents of the attribute list.
@@ -855,7 +858,7 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_da_intnode_t *node;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	xfs_dablk_t blkno;
 	int error;
 
@@ -877,10 +880,9 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	if (error)
 		goto out;
 	ASSERT(bp2 != NULL);
-	memcpy(bp2->data, bp1->data, XFS_LBSIZE(dp->i_mount));
-	xfs_da_buf_done(bp1);
+	memcpy(bp2->b_addr, bp1->b_addr, XFS_LBSIZE(dp->i_mount));
 	bp1 = NULL;
-	xfs_da_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	/*
 	 * Set up the new root node.
@@ -888,21 +890,17 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	error = xfs_da_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK);
 	if (error)
 		goto out;
-	node = bp1->data;
-	leaf = bp2->data;
+	node = bp1->b_addr;
+	leaf = bp2->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	/* both on-disk, don't endian-flip twice */
 	node->btree[0].hashval =
 		leaf->entries[be16_to_cpu(leaf->hdr.count)-1 ].hashval;
 	node->btree[0].before = cpu_to_be32(blkno);
 	node->hdr.count = cpu_to_be16(1);
-	xfs_da_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
 	error = 0;
 out:
-	if (bp1)
-		xfs_da_buf_done(bp1);
-	if (bp2)
-		xfs_da_buf_done(bp2);
 	return(error);
 }
 
@@ -916,12 +914,15 @@ out:
  * or a leaf in a node attribute list.
  */
 STATIC int
-xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
+xfs_attr_leaf_create(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	blkno,
+	struct xfs_buf	**bpp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_create(args);
@@ -933,7 +934,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	memset((char *)leaf, 0, XFS_LBSIZE(dp->i_mount));
 	hdr = &leaf->hdr;
 	hdr->info.magic = cpu_to_be16(XFS_ATTR_LEAF_MAGIC);
@@ -947,7 +948,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	hdr->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr->firstused) -
 					   sizeof(xfs_attr_leaf_hdr_t));
 
-	xfs_da_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	*bpp = bp;
 	return(0);
@@ -1014,7 +1015,9 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
  * Add a name to the leaf attribute list structure.
  */
 int
-xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_add(
+	struct xfs_buf		*bp,
+	struct xfs_da_args	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1023,7 +1026,7 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_add(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT((args->index >= 0)
 		&& (args->index <= be16_to_cpu(leaf->hdr.count)));
@@ -1085,7 +1088,10 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * Add a name to a leaf attribute list structure.
  */
 STATIC int
-xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
+xfs_attr_leaf_add_work(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		mapindex)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1096,7 +1102,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 	xfs_mount_t *mp;
 	int tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	ASSERT((mapindex >= 0) && (mapindex < XFS_ATTR_LEAF_MAPSIZE));
@@ -1110,7 +1116,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		tmp  = be16_to_cpu(hdr->count) - args->index;
 		tmp *= sizeof(xfs_attr_leaf_entry_t);
 		memmove((char *)(entry+1), (char *)entry, tmp);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 		    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	}
 	be16_add_cpu(&hdr->count, 1);
@@ -1142,7 +1148,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 			args->index2++;
 		}
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	ASSERT((args->index == 0) ||
 	       (be32_to_cpu(entry->hashval) >= be32_to_cpu((entry-1)->hashval)));
@@ -1174,7 +1180,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		args->rmtblkno = 1;
 		args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen);
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   xfs_attr_leaf_entsize(leaf, args->index)));
 
@@ -1198,7 +1204,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		}
 	}
 	be16_add_cpu(&hdr->usedbytes, xfs_attr_leaf_entsize(leaf, args->index));
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 		XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 	return(0);
 }
@@ -1207,7 +1213,9 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
  * Garbage collect a leaf attribute list block by copying it to a new buffer.
  */
 STATIC void
-xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
+xfs_attr_leaf_compact(
+	struct xfs_trans *trans,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf_s, *leaf_d;
 	xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
@@ -1217,14 +1225,14 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	mp = trans->t_mountp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(mp));
-	memset(bp->data, 0, XFS_LBSIZE(mp));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));
+	memset(bp->b_addr, 0, XFS_LBSIZE(mp));
 
 	/*
 	 * Copy basic information
 	 */
 	leaf_s = (xfs_attr_leafblock_t *)tmpbuffer;
-	leaf_d = bp->data;
+	leaf_d = bp->b_addr;
 	hdr_s = &leaf_s->hdr;
 	hdr_d = &leaf_d->hdr;
 	hdr_d->info = hdr_s->info;	/* struct copy */
@@ -1247,7 +1255,7 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	 */
 	xfs_attr_leaf_moveents(leaf_s, 0, leaf_d, 0,
 				be16_to_cpu(hdr_s->count), mp);
-	xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
 
 	kmem_free(tmpbuffer);
 }
@@ -1279,8 +1287,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	 */
 	ASSERT(blk1->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC);
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	args = state->args;
@@ -1298,8 +1306,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		tmp_blk = blk1;
 		blk1 = blk2;
 		blk2 = tmp_blk;
-		leaf1 = blk1->bp->data;
-		leaf2 = blk2->bp->data;
+		leaf1 = blk1->bp->b_addr;
+		leaf2 = blk2->bp->b_addr;
 		swap = 1;
 	}
 	hdr1 = &leaf1->hdr;
@@ -1346,8 +1354,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf1, be16_to_cpu(hdr1->count) - count,
 				leaf2, 0, count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	} else if (count > be16_to_cpu(hdr1->count)) {
 		/*
 		 * I assert that since all callers pass in an empty
@@ -1378,8 +1386,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf2, 0, leaf1,
 				be16_to_cpu(hdr1->count), count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	}
 
 	/*
@@ -1448,8 +1456,8 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
 	/*
 	 * Set up environment.
 	 */
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	hdr1 = &leaf1->hdr;
 	hdr2 = &leaf2->hdr;
 	foundit = 0;
@@ -1551,7 +1559,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	xfs_da_blkinfo_t *info;
 	int count, bytes, forward, error, retval, i;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -1559,7 +1567,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[ state->path.active-1 ];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	leaf = (xfs_attr_leafblock_t *)info;
 	count = be16_to_cpu(leaf->hdr.count);
@@ -1622,13 +1630,13 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 		count  = be16_to_cpu(leaf->hdr.count);
 		bytes  = state->blocksize - (state->blocksize>>2);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
 		bytes -= count * sizeof(xfs_attr_leaf_entry_t);
 		bytes -= sizeof(xfs_attr_leaf_hdr_t);
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 		if (bytes >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
@@ -1666,7 +1674,9 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
  * If two leaves are 37% full, when combined they will leave 25% free.
  */
 int
-xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_remove(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1676,7 +1686,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	int tablesize, tmp, i;
 	xfs_mount_t *mp;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	mp = args->trans->t_mountp;
@@ -1769,7 +1779,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	 */
 	memset(xfs_attr_leaf_name(leaf, args->index), 0, entsize);
 	be16_add_cpu(&hdr->usedbytes, -entsize);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   entsize));
 
@@ -1777,7 +1787,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 					* sizeof(xfs_attr_leaf_entry_t);
 	memmove((char *)entry, (char *)(entry+1), tmp);
 	be16_add_cpu(&hdr->count, -1);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	entry = &leaf->entries[be16_to_cpu(hdr->count)];
 	memset((char *)entry, 0, sizeof(xfs_attr_leaf_entry_t));
@@ -1807,7 +1817,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	} else {
 		hdr->holes = 1;		/* mark as needing compaction */
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 
 	/*
@@ -1840,8 +1850,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	mp = state->mp;
 	ASSERT(drop_blk->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(save_blk->magic == XFS_ATTR_LEAF_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	drop_hdr = &drop_leaf->hdr;
@@ -1906,7 +1916,7 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 		kmem_free(tmpbuffer);
 	}
 
-	xfs_da_log_buf(state->args->trans, save_blk->bp, 0,
+	xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
 					   state->blocksize - 1);
 
 	/*
@@ -1934,7 +1944,9 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
  * Don't change the args->value unless we find the attribute.
  */
 int
-xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_lookup_int(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -1945,7 +1957,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_lookup(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2041,7 +2053,9 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * list structure.
  */
 int
-xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_getvalue(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	int valuelen;
 	xfs_attr_leafblock_t *leaf;
@@ -2049,7 +2063,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	xfs_attr_leaf_name_local_t *name_loc;
 	xfs_attr_leaf_name_remote_t *name_rmt;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2247,12 +2261,14 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
  * Return 0 unless leaf2 should go before leaf1.
  */
 int
-xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
+xfs_attr_leaf_order(
+	struct xfs_buf	*leaf1_bp,
+	struct xfs_buf	*leaf2_bp)
 {
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT((leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) &&
 	       (leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)));
 	if ((be16_to_cpu(leaf1->hdr.count) > 0) &&
@@ -2272,11 +2288,13 @@ xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
  * Pick up the last hashvalue from a leaf block.
  */
 xfs_dahash_t
-xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_attr_leaf_lasthash(
+	struct xfs_buf	*bp,
+	int		*count)
 {
 	xfs_attr_leafblock_t *leaf;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -2337,7 +2355,9 @@ xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
  * Copy out attribute list entries for attr_list(), for leaf attribute lists.
  */
 int
-xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
+xfs_attr_leaf_list_int(
+	struct xfs_buf		*bp,
+	xfs_attr_list_context_t	*context)
 {
 	attrlist_cursor_kern_t *cursor;
 	xfs_attr_leafblock_t *leaf;
@@ -2345,7 +2365,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
 	int retval, i;
 
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	cursor = context->cursor;
 	cursor->initted = 1;
 
@@ -2463,7 +2483,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2482,7 +2502,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2505,7 +2525,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 #endif /* DEBUG */
 
 	entry->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 
 	if (args->rmtblkno) {
@@ -2513,10 +2533,9 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2533,7 +2552,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_setflag(args);
@@ -2548,7 +2567,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2556,16 +2575,15 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 
 	ASSERT((entry->flags & XFS_ATTR_INCOMPLETE) == 0);
 	entry->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	if ((entry->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2586,7 +2604,7 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 	xfs_attr_leaf_entry_t *entry1, *entry2;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2620,13 +2638,13 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 		bp2 = bp1;
 	}
 
-	leaf1 = bp1->data;
+	leaf1 = bp1->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf1->hdr.count));
 	ASSERT(args->index >= 0);
 	entry1 = &leaf1->entries[ args->index ];
 
-	leaf2 = bp2->data;
+	leaf2 = bp2->b_addr;
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index2 < be16_to_cpu(leaf2->hdr.count));
 	ASSERT(args->index2 >= 0);
@@ -2660,30 +2678,27 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	ASSERT((entry2->flags & XFS_ATTR_INCOMPLETE) == 0);
 
 	entry1->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp1,
+	xfs_trans_log_buf(args->trans, bp1,
 			  XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1)));
 	if (args->rmtblkno) {
 		ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
 		name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp1,
+		xfs_trans_log_buf(args->trans, bp1,
 			 XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
 	}
 
 	entry2->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp2,
+	xfs_trans_log_buf(args->trans, bp2,
 			  XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2)));
 	if ((entry2->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp2,
+		xfs_trans_log_buf(args->trans, bp2,
 			 XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp1);
-	if (bp1 != bp2)
-		xfs_da_buf_done(bp2);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2706,7 +2721,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_daddr_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	/*
@@ -2718,20 +2733,20 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_read_buf(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	blkno = xfs_da_blkno(bp);
+	blkno = XFS_BUF_ADDR(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
 	 * This is a depth-first traversal!
 	 */
-	info = bp->data;
+	info = bp->b_addr;
 	if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 		error = xfs_attr_node_inactive(trans, dp, bp, 1);
 	} else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) {
 		error = xfs_attr_leaf_inactive(trans, dp, bp);
 	} else {
 		error = XFS_ERROR(EIO);
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 	}
 	if (error)
 		return(error);
@@ -2742,7 +2757,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	xfs_da_binval(*trans, bp);	/* remove from cache */
+	xfs_trans_binval(*trans, bp);	/* remove from cache */
 	/*
 	 * Commit the invalidate and start the next transaction.
 	 */
@@ -2756,34 +2771,37 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
  * We're doing a depth-first traversal in order to invalidate everything.
  */
 STATIC int
-xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
-				   int level)
+xfs_attr_node_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp,
+	int		level)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_da_intnode_t *node;
 	xfs_dablk_t child_fsb;
 	xfs_daddr_t parent_blkno, child_blkno;
 	int error, count, i;
-	xfs_dabuf_t *child_bp;
+	struct xfs_buf *child_bp;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
 	 */
 	if (level > XFS_DA_NODE_MAXDEPTH) {
-		xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 		return(XFS_ERROR(EIO));
 	}
 
-	node = bp->data;
+	node = bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
-	parent_blkno = xfs_da_blkno(bp);	/* save for re-read later */
+	parent_blkno = XFS_BUF_ADDR(bp);	/* save for re-read later */
 	count = be16_to_cpu(node->hdr.count);
 	if (!count) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 	child_fsb = be32_to_cpu(node->btree[0].before);
-	xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 
 	/*
 	 * If this is the node level just above the leaves, simply loop
@@ -2803,12 +2821,12 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			return(error);
 		if (child_bp) {
 						/* save for re-read later */
-			child_blkno = xfs_da_blkno(child_bp);
+			child_blkno = XFS_BUF_ADDR(child_bp);
 
 			/*
 			 * Invalidate the subtree, however we have to.
 			 */
-			info = child_bp->data;
+			info = child_bp->b_addr;
 			if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 				error = xfs_attr_node_inactive(trans, dp,
 						child_bp, level+1);
@@ -2817,7 +2835,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 						child_bp);
 			} else {
 				error = XFS_ERROR(EIO);
-				xfs_da_brelse(*trans, child_bp);
+				xfs_trans_brelse(*trans, child_bp);
 			}
 			if (error)
 				return(error);
@@ -2830,7 +2848,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 				&child_bp, XFS_ATTR_FORK);
 			if (error)
 				return(error);
-			xfs_da_binval(*trans, child_bp);
+			xfs_trans_binval(*trans, child_bp);
 		}
 
 		/*
@@ -2843,7 +2861,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			if (error)
 				return(error);
 			child_fsb = be32_to_cpu(node->btree[i+1].before);
-			xfs_da_brelse(*trans, bp);
+			xfs_trans_brelse(*trans, bp);
 		}
 		/*
 		 * Atomically commit the whole invalidate stuff.
@@ -2863,7 +2881,10 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
  * caught holding something that the logging code wants to flush to disk.
  */
 STATIC int
-xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
+xfs_attr_leaf_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -2871,7 +2892,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	xfs_attr_inactive_list_t *list, *lp;
 	int error, count, size, tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	/*
@@ -2892,7 +2913,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	 * If there are no "remote" values, we're done.
 	 */
 	if (count == 0) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 
@@ -2919,7 +2940,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 			}
 		}
 	}
-	xfs_da_brelse(*trans, bp);	/* unlock for trans. in freextent() */
+	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
 
 	/*
 	 * Invalidate each of the "remote" value extents.
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 9c7d22f..dea1772 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -31,7 +31,6 @@
 struct attrlist;
 struct attrlist_cursor_kern;
 struct xfs_attr_list_context;
-struct xfs_dabuf;
 struct xfs_da_args;
 struct xfs_da_state;
 struct xfs_da_state_blk;
@@ -215,7 +214,7 @@ int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_list(struct xfs_attr_list_context *context);
-int	xfs_attr_shortform_allfit(struct xfs_dabuf *bp, struct xfs_inode *dp);
+int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
 
 
@@ -223,7 +222,7 @@ int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
  */
 int	xfs_attr_leaf_to_node(struct xfs_da_args *args);
-int	xfs_attr_leaf_to_shortform(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_to_shortform(struct xfs_buf *bp,
 				   struct xfs_da_args *args, int forkoff);
 int	xfs_attr_leaf_clearflag(struct xfs_da_args *args);
 int	xfs_attr_leaf_setflag(struct xfs_da_args *args);
@@ -235,14 +234,14 @@ int	xfs_attr_leaf_flipflags(xfs_da_args_t *args);
 int	xfs_attr_leaf_split(struct xfs_da_state *state,
 				   struct xfs_da_state_blk *oldblk,
 				   struct xfs_da_state_blk *newblk);
-int	xfs_attr_leaf_lookup_int(struct xfs_dabuf *leaf,
+int	xfs_attr_leaf_lookup_int(struct xfs_buf *leaf,
 					struct xfs_da_args *args);
-int	xfs_attr_leaf_getvalue(struct xfs_dabuf *bp, struct xfs_da_args *args);
-int	xfs_attr_leaf_add(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args);
+int	xfs_attr_leaf_add(struct xfs_buf *leaf_buffer,
 				 struct xfs_da_args *args);
-int	xfs_attr_leaf_remove(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_remove(struct xfs_buf *leaf_buffer,
 				    struct xfs_da_args *args);
-int	xfs_attr_leaf_list_int(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_list_int(struct xfs_buf *bp,
 				      struct xfs_attr_list_context *context);
 
 /*
@@ -257,9 +256,9 @@ int	xfs_attr_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
 /*
  * Utility routines.
  */
-xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_dabuf *bp, int *count);
-int	xfs_attr_leaf_order(struct xfs_dabuf *leaf1_bp,
-				   struct xfs_dabuf *leaf2_bp);
+xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
+int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
+				   struct xfs_buf *leaf2_bp);
 int	xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
 					int *local);
 #endif	/* __XFS_ATTR_LEAF_H__ */
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 76e5dba..7bfb7dd 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -83,9 +83,9 @@ STATIC void xfs_da_node_unbalance(xfs_da_state_t *state,
 /*
  * Utility routines.
  */
-STATIC uint	xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count);
-STATIC int	xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp);
-STATIC xfs_dabuf_t *xfs_da_buf_make(xfs_buf_t *bp);
+STATIC uint	xfs_da_node_lasthash(struct xfs_buf *bp, int *count);
+STATIC int	xfs_da_node_order(struct xfs_buf *node1_bp,
+				  struct xfs_buf *node2_bp);
 STATIC int	xfs_da_blk_unlink(xfs_da_state_t *state,
 				  xfs_da_state_blk_t *drop_blk,
 				  xfs_da_state_blk_t *save_blk);
@@ -100,10 +100,10 @@ STATIC void	xfs_da_state_kill_altpath(xfs_da_state_t *state);
  */
 int
 xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
-				 xfs_dabuf_t **bpp, int whichfork)
+				 struct xfs_buf **bpp, int whichfork)
 {
 	xfs_da_intnode_t *node;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 	xfs_trans_t *tp;
 
@@ -114,7 +114,7 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	node = bp->data;
+	node = bp->b_addr;
 	node->hdr.info.forw = 0;
 	node->hdr.info.back = 0;
 	node->hdr.info.magic = cpu_to_be16(XFS_DA_NODE_MAGIC);
@@ -122,7 +122,7 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	node->hdr.count = 0;
 	node->hdr.level = cpu_to_be16(level);
 
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	*bpp = bp;
@@ -138,7 +138,7 @@ xfs_da_split(xfs_da_state_t *state)
 {
 	xfs_da_state_blk_t *oldblk, *newblk, *addblk;
 	xfs_da_intnode_t *node;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int max, action, error, i;
 
 	trace_xfs_da_split(state->args);
@@ -203,7 +203,6 @@ xfs_da_split(xfs_da_state_t *state)
 		case XFS_DA_NODE_MAGIC:
 			error = xfs_da_node_split(state, oldblk, newblk, addblk,
 							 max - i, &action);
-			xfs_da_buf_done(addblk->bp);
 			addblk->bp = NULL;
 			if (error)
 				return(error);	/* GROT: dir is inconsistent */
@@ -221,13 +220,6 @@ xfs_da_split(xfs_da_state_t *state)
 		 * Update the btree to show the new hashval for this child.
 		 */
 		xfs_da_fixhashpath(state, &state->path);
-		/*
-		 * If we won't need this block again, it's getting dropped
-		 * from the active path by the loop control, so we need
-		 * to mark it done now.
-		 */
-		if (i > 0 || !addblk)
-			xfs_da_buf_done(oldblk->bp);
 	}
 	if (!addblk)
 		return(0);
@@ -239,8 +231,6 @@ xfs_da_split(xfs_da_state_t *state)
 	oldblk = &state->path.blk[0];
 	error = xfs_da_root_split(state, oldblk, addblk);
 	if (error) {
-		xfs_da_buf_done(oldblk->bp);
-		xfs_da_buf_done(addblk->bp);
 		addblk->bp = NULL;
 		return(error);	/* GROT: dir is inconsistent */
 	}
@@ -252,7 +242,7 @@ xfs_da_split(xfs_da_state_t *state)
 	 * and the original block 0 could be at any position in the list.
 	 */
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (node->hdr.info.forw) {
 		if (be32_to_cpu(node->hdr.info.forw) == addblk->blkno) {
 			bp = addblk->bp;
@@ -260,13 +250,13 @@ xfs_da_split(xfs_da_state_t *state)
 			ASSERT(state->extravalid);
 			bp = state->extrablk.bp;
 		}
-		node = bp->data;
+		node = bp->b_addr;
 		node->hdr.info.back = cpu_to_be32(oldblk->blkno);
-		xfs_da_log_buf(state->args->trans, bp,
+		xfs_trans_log_buf(state->args->trans, bp,
 		    XFS_DA_LOGRANGE(node, &node->hdr.info,
 		    sizeof(node->hdr.info)));
 	}
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (node->hdr.info.back) {
 		if (be32_to_cpu(node->hdr.info.back) == addblk->blkno) {
 			bp = addblk->bp;
@@ -274,14 +264,12 @@ xfs_da_split(xfs_da_state_t *state)
 			ASSERT(state->extravalid);
 			bp = state->extrablk.bp;
 		}
-		node = bp->data;
+		node = bp->b_addr;
 		node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
-		xfs_da_log_buf(state->args->trans, bp,
+		xfs_trans_log_buf(state->args->trans, bp,
 		    XFS_DA_LOGRANGE(node, &node->hdr.info,
 		    sizeof(node->hdr.info)));
 	}
-	xfs_da_buf_done(oldblk->bp);
-	xfs_da_buf_done(addblk->bp);
 	addblk->bp = NULL;
 	return(0);
 }
@@ -298,7 +286,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	xfs_da_intnode_t *node, *oldroot;
 	xfs_da_args_t *args;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error, size;
 	xfs_inode_t *dp;
 	xfs_trans_t *tp;
@@ -323,8 +311,8 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	node = bp->data;
-	oldroot = blk1->bp->data;
+	node = bp->b_addr;
+	oldroot = blk1->bp->b_addr;
 	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 		size = (int)((char *)&oldroot->btree[be16_to_cpu(oldroot->hdr.count)] -
 			     (char *)oldroot);
@@ -335,8 +323,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 			     (char *)leaf);
 	}
 	memcpy(node, oldroot, size);
-	xfs_da_log_buf(tp, bp, 0, size - 1);
-	xfs_da_buf_done(blk1->bp);
+	xfs_trans_log_buf(tp, bp, 0, size - 1);
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 
@@ -348,7 +335,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		be16_to_cpu(node->hdr.level) + 1, &bp, args->whichfork);
 	if (error)
 		return(error);
-	node = bp->data;
+	node = bp->b_addr;
 	node->btree[0].hashval = cpu_to_be32(blk1->hashval);
 	node->btree[0].before = cpu_to_be32(blk1->blkno);
 	node->btree[1].hashval = cpu_to_be32(blk2->hashval);
@@ -365,10 +352,9 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 #endif
 
 	/* Header is already logged by xfs_da_node_create */
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		XFS_DA_LOGRANGE(node, node->btree,
 			sizeof(xfs_da_node_entry_t) * 2));
-	xfs_da_buf_done(bp);
 
 	return(0);
 }
@@ -389,7 +375,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 
 	trace_xfs_da_node_split(state->args);
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 
 	/*
@@ -436,7 +422,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	 *
 	 * If we had double-split op below us, then add the extra block too.
 	 */
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (oldblk->index <= be16_to_cpu(node->hdr.count)) {
 		oldblk->index++;
 		xfs_da_node_add(state, oldblk, addblk);
@@ -477,8 +463,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 
 	trace_xfs_da_node_rebalance(state->args);
 
-	node1 = blk1->bp->data;
-	node2 = blk2->bp->data;
+	node1 = blk1->bp->b_addr;
+	node2 = blk2->bp->b_addr;
 	/*
 	 * Figure out how many entries need to move, and in which direction.
 	 * Swap the nodes around if that makes it simpler.
@@ -532,7 +518,7 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		btree_d = &node1->btree[be16_to_cpu(node1->hdr.count)];
 		memcpy(btree_d, btree_s, tmp);
 		be16_add_cpu(&node1->hdr.count, count);
-		xfs_da_log_buf(tp, blk1->bp,
+		xfs_trans_log_buf(tp, blk1->bp,
 			XFS_DA_LOGRANGE(node1, btree_d, tmp));
 
 		/*
@@ -549,9 +535,9 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	/*
 	 * Log header of node 1 and all current bits of node 2.
 	 */
-	xfs_da_log_buf(tp, blk1->bp,
+	xfs_trans_log_buf(tp, blk1->bp,
 		XFS_DA_LOGRANGE(node1, &node1->hdr, sizeof(node1->hdr)));
-	xfs_da_log_buf(tp, blk2->bp,
+	xfs_trans_log_buf(tp, blk2->bp,
 		XFS_DA_LOGRANGE(node2, &node2->hdr,
 			sizeof(node2->hdr) +
 			sizeof(node2->btree[0]) * be16_to_cpu(node2->hdr.count)));
@@ -560,8 +546,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	 * Record the last hashval from each block for upward propagation.
 	 * (note: don't use the swapped node pointers)
 	 */
-	node1 = blk1->bp->data;
-	node2 = blk2->bp->data;
+	node1 = blk1->bp->b_addr;
+	node2 = blk2->bp->b_addr;
 	blk1->hashval = be32_to_cpu(node1->btree[be16_to_cpu(node1->hdr.count)-1].hashval);
 	blk2->hashval = be32_to_cpu(node2->btree[be16_to_cpu(node2->hdr.count)-1].hashval);
 
@@ -587,7 +573,7 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 
 	trace_xfs_da_node_add(state->args);
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count)));
 	ASSERT(newblk->blkno != 0);
@@ -606,10 +592,10 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	}
 	btree->hashval = cpu_to_be32(newblk->hashval);
 	btree->before = cpu_to_be32(newblk->blkno);
-	xfs_da_log_buf(state->args->trans, oldblk->bp,
+	xfs_trans_log_buf(state->args->trans, oldblk->bp,
 		XFS_DA_LOGRANGE(node, btree, tmp + sizeof(*btree)));
 	be16_add_cpu(&node->hdr.count, 1);
-	xfs_da_log_buf(state->args->trans, oldblk->bp,
+	xfs_trans_log_buf(state->args->trans, oldblk->bp,
 		XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	/*
@@ -735,7 +721,7 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	xfs_da_intnode_t *oldroot;
 	xfs_da_args_t *args;
 	xfs_dablk_t child;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_da_root_join(state->args);
@@ -743,7 +729,7 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	args = state->args;
 	ASSERT(args != NULL);
 	ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC);
-	oldroot = root_blk->bp->data;
+	oldroot = root_blk->bp->b_addr;
 	ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT(!oldroot->hdr.info.forw);
 	ASSERT(!oldroot->hdr.info.back);
@@ -765,11 +751,11 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	xfs_da_blkinfo_onlychild_validate(bp->data,
+	xfs_da_blkinfo_onlychild_validate(bp->b_addr,
 					be16_to_cpu(oldroot->hdr.level));
 
-	memcpy(root_blk->bp->data, bp->data, state->blocksize);
-	xfs_da_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
+	memcpy(root_blk->bp->b_addr, bp->b_addr, state->blocksize);
+	xfs_trans_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
 	error = xfs_da_shrink_inode(args, child, bp);
 	return(error);
 }
@@ -791,7 +777,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 	xfs_da_blkinfo_t *info;
 	int count, forward, error, retval, i;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -799,7 +785,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[ state->path.active-1 ];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	node = (xfs_da_intnode_t *)info;
 	count = be16_to_cpu(node->hdr.count);
@@ -859,10 +845,10 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 		count  = state->node_ents;
 		count -= state->node_ents >> 2;
 		count -= be16_to_cpu(node->hdr.count);
-		node = bp->data;
+		node = bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		count -= be16_to_cpu(node->hdr.count);
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 		if (count >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
@@ -934,14 +920,14 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
 		break;
 	}
 	for (blk--, level--; level >= 0; blk--, level--) {
-		node = blk->bp->data;
+		node = blk->bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		btree = &node->btree[ blk->index ];
 		if (be32_to_cpu(btree->hashval) == lasthash)
 			break;
 		blk->hashval = lasthash;
 		btree->hashval = cpu_to_be32(lasthash);
-		xfs_da_log_buf(state->args->trans, blk->bp,
+		xfs_trans_log_buf(state->args->trans, blk->bp,
 				  XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
 
 		lasthash = be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1].hashval);
@@ -960,7 +946,7 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 
 	trace_xfs_da_node_remove(state->args);
 
-	node = drop_blk->bp->data;
+	node = drop_blk->bp->b_addr;
 	ASSERT(drop_blk->index < be16_to_cpu(node->hdr.count));
 	ASSERT(drop_blk->index >= 0);
 
@@ -972,15 +958,15 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 		tmp  = be16_to_cpu(node->hdr.count) - drop_blk->index - 1;
 		tmp *= (uint)sizeof(xfs_da_node_entry_t);
 		memmove(btree, btree + 1, tmp);
-		xfs_da_log_buf(state->args->trans, drop_blk->bp,
+		xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 		    XFS_DA_LOGRANGE(node, btree, tmp));
 		btree = &node->btree[be16_to_cpu(node->hdr.count)-1];
 	}
 	memset((char *)btree, 0, sizeof(xfs_da_node_entry_t));
-	xfs_da_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
 	be16_add_cpu(&node->hdr.count, -1);
-	xfs_da_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	/*
@@ -1005,8 +991,8 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 
 	trace_xfs_da_node_unbalance(state->args);
 
-	drop_node = drop_blk->bp->data;
-	save_node = save_blk->bp->data;
+	drop_node = drop_blk->bp->b_addr;
+	save_node = save_blk->bp->b_addr;
 	ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT(save_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	tp = state->args->trans;
@@ -1023,13 +1009,13 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 		tmp = be16_to_cpu(save_node->hdr.count) * (uint)sizeof(xfs_da_node_entry_t);
 		memmove(btree, &save_node->btree[0], tmp);
 		btree = &save_node->btree[0];
-		xfs_da_log_buf(tp, save_blk->bp,
+		xfs_trans_log_buf(tp, save_blk->bp,
 			XFS_DA_LOGRANGE(save_node, btree,
 				(be16_to_cpu(save_node->hdr.count) + be16_to_cpu(drop_node->hdr.count)) *
 				sizeof(xfs_da_node_entry_t)));
 	} else {
 		btree = &save_node->btree[be16_to_cpu(save_node->hdr.count)];
-		xfs_da_log_buf(tp, save_blk->bp,
+		xfs_trans_log_buf(tp, save_blk->bp,
 			XFS_DA_LOGRANGE(save_node, btree,
 				be16_to_cpu(drop_node->hdr.count) *
 				sizeof(xfs_da_node_entry_t)));
@@ -1042,7 +1028,7 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	memcpy(btree, &drop_node->btree[0], tmp);
 	be16_add_cpu(&save_node->hdr.count, be16_to_cpu(drop_node->hdr.count));
 
-	xfs_da_log_buf(tp, save_blk->bp,
+	xfs_trans_log_buf(tp, save_blk->bp,
 		XFS_DA_LOGRANGE(save_node, &save_node->hdr,
 			sizeof(save_node->hdr)));
 
@@ -1100,7 +1086,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
 			state->path.active--;
 			return(error);
 		}
-		curr = blk->bp->data;
+		curr = blk->bp->b_addr;
 		blk->magic = be16_to_cpu(curr->magic);
 		ASSERT(blk->magic == XFS_DA_NODE_MAGIC ||
 		       blk->magic == XFS_DIR2_LEAFN_MAGIC ||
@@ -1110,7 +1096,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
 		 * Search an intermediate node for a match.
 		 */
 		if (blk->magic == XFS_DA_NODE_MAGIC) {
-			node = blk->bp->data;
+			node = blk->bp->b_addr;
 			max = be16_to_cpu(node->hdr.count);
 			blk->hashval = be32_to_cpu(node->btree[max-1].hashval);
 
@@ -1216,15 +1202,15 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 	xfs_da_blkinfo_t *old_info, *new_info, *tmp_info;
 	xfs_da_args_t *args;
 	int before=0, error;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Set up environment.
 	 */
 	args = state->args;
 	ASSERT(args != NULL);
-	old_info = old_blk->bp->data;
-	new_info = new_blk->bp->data;
+	old_info = old_blk->bp->b_addr;
+	new_info = new_blk->bp->b_addr;
 	ASSERT(old_blk->magic == XFS_DA_NODE_MAGIC ||
 	       old_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 	       old_blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -1261,12 +1247,11 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(be16_to_cpu(tmp_info->magic) == be16_to_cpu(old_info->magic));
 			ASSERT(be32_to_cpu(tmp_info->forw) == old_blk->blkno);
 			tmp_info->forw = cpu_to_be32(new_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
-			xfs_da_buf_done(bp);
+			xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
 		}
 		old_info->back = cpu_to_be32(new_blk->blkno);
 	} else {
@@ -1283,18 +1268,17 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->back) == old_blk->blkno);
 			tmp_info->back = cpu_to_be32(new_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
-			xfs_da_buf_done(bp);
+			xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
 		}
 		old_info->forw = cpu_to_be32(new_blk->blkno);
 	}
 
-	xfs_da_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
-	xfs_da_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
+	xfs_trans_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
+	xfs_trans_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
 	return(0);
 }
 
@@ -1302,12 +1286,14 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
  * Compare two intermediate nodes for "order".
  */
 STATIC int
-xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp)
+xfs_da_node_order(
+	struct xfs_buf	*node1_bp,
+	struct xfs_buf	*node2_bp)
 {
 	xfs_da_intnode_t *node1, *node2;
 
-	node1 = node1_bp->data;
-	node2 = node2_bp->data;
+	node1 = node1_bp->b_addr;
+	node2 = node2_bp->b_addr;
 	ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) &&
 	       node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	if ((be16_to_cpu(node1->hdr.count) > 0) && (be16_to_cpu(node2->hdr.count) > 0) &&
@@ -1324,11 +1310,13 @@ xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp)
  * Pick up the last hashvalue from an intermediate node.
  */
 STATIC uint
-xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_da_node_lasthash(
+	struct xfs_buf	*bp,
+	int		*count)
 {
 	xfs_da_intnode_t *node;
 
-	node = bp->data;
+	node = bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	if (count)
 		*count = be16_to_cpu(node->hdr.count);
@@ -1346,7 +1334,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 {
 	xfs_da_blkinfo_t *drop_info, *save_info, *tmp_info;
 	xfs_da_args_t *args;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	/*
@@ -1354,8 +1342,8 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	 */
 	args = state->args;
 	ASSERT(args != NULL);
-	save_info = save_blk->bp->data;
-	drop_info = drop_blk->bp->data;
+	save_info = save_blk->bp->b_addr;
+	drop_info = drop_blk->bp->b_addr;
 	ASSERT(save_blk->magic == XFS_DA_NODE_MAGIC ||
 	       save_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 	       save_blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -1380,13 +1368,12 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->forw) == drop_blk->blkno);
 			tmp_info->forw = cpu_to_be32(save_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0,
+			xfs_trans_log_buf(args->trans, bp, 0,
 						    sizeof(*tmp_info) - 1);
-			xfs_da_buf_done(bp);
 		}
 	} else {
 		trace_xfs_da_unlink_forward(args);
@@ -1398,17 +1385,16 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->back) == drop_blk->blkno);
 			tmp_info->back = cpu_to_be32(save_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0,
+			xfs_trans_log_buf(args->trans, bp, 0,
 						    sizeof(*tmp_info) - 1);
-			xfs_da_buf_done(bp);
 		}
 	}
 
-	xfs_da_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
+	xfs_trans_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
 	return(0);
 }
 
@@ -1443,7 +1429,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 	level = (path->active-1) - 1;	/* skip bottom layer in path */
 	for (blk = &path->blk[level]; level >= 0; blk--, level--) {
 		ASSERT(blk->bp != NULL);
-		node = blk->bp->data;
+		node = blk->bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		if (forward && (blk->index < be16_to_cpu(node->hdr.count)-1)) {
 			blk->index++;
@@ -1471,7 +1457,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 		 * (if it's dirty, trans won't actually let go)
 		 */
 		if (release)
-			xfs_da_brelse(args->trans, blk->bp);
+			xfs_trans_brelse(args->trans, blk->bp);
 
 		/*
 		 * Read the next child block.
@@ -1482,7 +1468,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 		if (error)
 			return(error);
 		ASSERT(blk->bp != NULL);
-		info = blk->bp->data;
+		info = blk->bp->b_addr;
 		ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
 		       info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 		       info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
@@ -1702,11 +1688,13 @@ xfs_da_grow_inode(
  * a bmap btree split to do that.
  */
 STATIC int
-xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
-		      xfs_dabuf_t **dead_bufp)
+xfs_da_swap_lastblock(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	*dead_blknop,
+	struct xfs_buf	**dead_bufp)
 {
 	xfs_dablk_t dead_blkno, last_blkno, sib_blkno, par_blkno;
-	xfs_dabuf_t *dead_buf, *last_buf, *sib_buf, *par_buf;
+	struct xfs_buf *dead_buf, *last_buf, *sib_buf, *par_buf;
 	xfs_fileoff_t lastoff;
 	xfs_inode_t *ip;
 	xfs_trans_t *tp;
@@ -1744,9 +1732,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
-	memcpy(dead_buf->data, last_buf->data, mp->m_dirblksize);
-	xfs_da_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
-	dead_info = dead_buf->data;
+	memcpy(dead_buf->b_addr, last_buf->b_addr, mp->m_dirblksize);
+	xfs_trans_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
+	dead_info = dead_buf->b_addr;
 	/*
 	 * Get values from the moved block.
 	 */
@@ -1767,7 +1755,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	if ((sib_blkno = be32_to_cpu(dead_info->back))) {
 		if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
 			goto done;
-		sib_info = sib_buf->data;
+		sib_info = sib_buf->b_addr;
 		if (unlikely(
 		    be32_to_cpu(sib_info->forw) != last_blkno ||
 		    sib_info->magic != dead_info->magic)) {
@@ -1777,10 +1765,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 			goto done;
 		}
 		sib_info->forw = cpu_to_be32(dead_blkno);
-		xfs_da_log_buf(tp, sib_buf,
+		xfs_trans_log_buf(tp, sib_buf,
 			XFS_DA_LOGRANGE(sib_info, &sib_info->forw,
 					sizeof(sib_info->forw)));
-		xfs_da_buf_done(sib_buf);
 		sib_buf = NULL;
 	}
 	/*
@@ -1789,7 +1776,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	if ((sib_blkno = be32_to_cpu(dead_info->forw))) {
 		if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
 			goto done;
-		sib_info = sib_buf->data;
+		sib_info = sib_buf->b_addr;
 		if (unlikely(
 		       be32_to_cpu(sib_info->back) != last_blkno ||
 		       sib_info->magic != dead_info->magic)) {
@@ -1799,10 +1786,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 			goto done;
 		}
 		sib_info->back = cpu_to_be32(dead_blkno);
-		xfs_da_log_buf(tp, sib_buf,
+		xfs_trans_log_buf(tp, sib_buf,
 			XFS_DA_LOGRANGE(sib_info, &sib_info->back,
 					sizeof(sib_info->back)));
-		xfs_da_buf_done(sib_buf);
 		sib_buf = NULL;
 	}
 	par_blkno = mp->m_dirleafblk;
@@ -1813,7 +1799,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	for (;;) {
 		if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
 			goto done;
-		par_node = par_buf->data;
+		par_node = par_buf->b_addr;
 		if (unlikely(par_node->hdr.info.magic !=
 		    cpu_to_be16(XFS_DA_NODE_MAGIC) ||
 		    (level >= 0 && level != be16_to_cpu(par_node->hdr.level) + 1))) {
@@ -1837,7 +1823,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		par_blkno = be32_to_cpu(par_node->btree[entno].before);
 		if (level == dead_level + 1)
 			break;
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 	}
 	/*
@@ -1853,7 +1839,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		if (entno < be16_to_cpu(par_node->hdr.count))
 			break;
 		par_blkno = be32_to_cpu(par_node->hdr.info.forw);
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 		if (unlikely(par_blkno == 0)) {
 			XFS_ERROR_REPORT("xfs_da_swap_lastblock(6)",
@@ -1863,7 +1849,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		}
 		if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
 			goto done;
-		par_node = par_buf->data;
+		par_node = par_buf->b_addr;
 		if (unlikely(
 		    be16_to_cpu(par_node->hdr.level) != level ||
 		    par_node->hdr.info.magic != cpu_to_be16(XFS_DA_NODE_MAGIC))) {
@@ -1878,20 +1864,18 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	 * Update the parent entry pointing to the moved block.
 	 */
 	par_node->btree[entno].before = cpu_to_be32(dead_blkno);
-	xfs_da_log_buf(tp, par_buf,
+	xfs_trans_log_buf(tp, par_buf,
 		XFS_DA_LOGRANGE(par_node, &par_node->btree[entno].before,
 				sizeof(par_node->btree[entno].before)));
-	xfs_da_buf_done(par_buf);
-	xfs_da_buf_done(dead_buf);
 	*dead_blknop = last_blkno;
 	*dead_bufp = last_buf;
 	return 0;
 done:
 	if (par_buf)
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 	if (sib_buf)
-		xfs_da_brelse(tp, sib_buf);
-	xfs_da_brelse(tp, last_buf);
+		xfs_trans_brelse(tp, sib_buf);
+	xfs_trans_brelse(tp, last_buf);
 	return error;
 }
 
@@ -1899,8 +1883,10 @@ done:
  * Remove a btree block from a directory or attribute.
  */
 int
-xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
-		    xfs_dabuf_t *dead_buf)
+xfs_da_shrink_inode(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	dead_blkno,
+	struct xfs_buf	*dead_buf)
 {
 	xfs_inode_t *dp;
 	int done, error, w, count;
@@ -1935,7 +1921,7 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 			break;
 		}
 	}
-	xfs_da_binval(tp, dead_buf);
+	xfs_trans_binval(tp, dead_buf);
 	return error;
 }
 
@@ -2099,7 +2085,7 @@ xfs_da_get_buf(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
 	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t		**bpp,
+	struct xfs_buf		**bpp,
 	int			whichfork)
 {
 	struct xfs_buf		*bp;
@@ -2128,7 +2114,7 @@ xfs_da_get_buf(
 		goto out_free;
 	}
 
-	*bpp = xfs_da_buf_make(bp);
+	*bpp = bp;
 
 out_free:
 	if (mapp != &map)
@@ -2146,7 +2132,7 @@ xfs_da_read_buf(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
 	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t		**bpp,
+	struct xfs_buf		**bpp,
 	int			whichfork)
 {
 	struct xfs_buf		*bp;
@@ -2178,16 +2164,14 @@ xfs_da_read_buf(
 	else
 		xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
 
-	*bpp = xfs_da_buf_make(bp);
-
 	/*
 	 * This verification code will be moved to a CRC verification callback
 	 * function so just leave it here unchanged until then.
 	 */
 	{
-		xfs_dir2_data_hdr_t	*hdr = (*bpp)->data;
-		xfs_dir2_free_t		*free = (*bpp)->data;
-		xfs_da_blkinfo_t	*info = (*bpp)->data;
+		xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
+		xfs_dir2_free_t		*free = bp->b_addr;
+		xfs_da_blkinfo_t	*info = bp->b_addr;
 		uint			magic, magic1;
 		struct xfs_mount	*mp = dp->i_mount;
 
@@ -2207,11 +2191,11 @@ xfs_da_read_buf(
 			XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
 					     XFS_ERRLEVEL_LOW, mp, info);
 			error = XFS_ERROR(EFSCORRUPTED);
-			xfs_da_brelse(trans, *bpp);
+			xfs_trans_brelse(trans, bp);
 			goto out_free;
 		}
 	}
-
+	*bpp = bp;
 out_free:
 	if (mapp != &map)
 		kmem_free(mapp);
@@ -2259,7 +2243,6 @@ out_free:
 }
 
 kmem_zone_t *xfs_da_state_zone;	/* anchor for state struct zone */
-kmem_zone_t *xfs_dabuf_zone;		/* dabuf zone */
 
 /*
  * Allocate a dir-state structure.
@@ -2279,13 +2262,8 @@ xfs_da_state_kill_altpath(xfs_da_state_t *state)
 {
 	int	i;
 
-	for (i = 0; i < state->altpath.active; i++) {
-		if (state->altpath.blk[i].bp) {
-			if (state->altpath.blk[i].bp != state->path.blk[i].bp)
-				xfs_da_buf_done(state->altpath.blk[i].bp);
-			state->altpath.blk[i].bp = NULL;
-		}
-	}
+	for (i = 0; i < state->altpath.active; i++)
+		state->altpath.blk[i].bp = NULL;
 	state->altpath.active = 0;
 }
 
@@ -2295,88 +2273,9 @@ xfs_da_state_kill_altpath(xfs_da_state_t *state)
 void
 xfs_da_state_free(xfs_da_state_t *state)
 {
-	int	i;
-
 	xfs_da_state_kill_altpath(state);
-	for (i = 0; i < state->path.active; i++) {
-		if (state->path.blk[i].bp)
-			xfs_da_buf_done(state->path.blk[i].bp);
-	}
-	if (state->extravalid && state->extrablk.bp)
-		xfs_da_buf_done(state->extrablk.bp);
 #ifdef DEBUG
 	memset((char *)state, 0, sizeof(*state));
 #endif /* DEBUG */
 	kmem_zone_free(xfs_da_state_zone, state);
 }
-
-/*
- * Create a dabuf.
- */
-/* ARGSUSED */
-STATIC xfs_dabuf_t *
-xfs_da_buf_make(xfs_buf_t *bp)
-{
-	xfs_dabuf_t	*dabuf;
-
-	dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
-	dabuf->bbcount = bp->b_length;
-	dabuf->data = bp->b_addr;
-	dabuf->bp = bp;
-	return dabuf;
-}
-
-/*
- * Release a dabuf.
- */
-void
-xfs_da_buf_done(xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
-	kmem_zone_free(xfs_dabuf_zone, dabuf);
-}
-
-/*
- * Log transaction from a dabuf.
- */
-void
-xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
-{
-	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
-	ASSERT(dabuf->data == dabuf->bp->b_addr);
-	xfs_trans_log_buf(tp, dabuf->bp, first, last);
-}
-
-/*
- * Release dabuf from a transaction.
- * Have to free up the dabuf before the buffers are released,
- * since the synchronization on the dabuf is really the lock on the buffer.
- */
-void
-xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
-	xfs_trans_brelse(tp, dabuf->bp);
-	xfs_da_buf_done(dabuf);
-}
-
-/*
- * Invalidate dabuf from a transaction.
- */
-void
-xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf->data && dabuf->bbcount && dabuf->bp);
-	xfs_da_buf_done(dabuf);
-	xfs_trans_binval(tp, dabuf->bp);
-}
-
-/*
- * Get the first daddr from a dabuf.
- */
-xfs_daddr_t
-xfs_da_blkno(xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf->data);
-	return XFS_BUF_ADDR(dabuf->bp);
-}
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 0b64c4a..9f37aa0 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -133,20 +133,6 @@ typedef struct xfs_da_args {
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }
 
 /*
- * Structure to describe buffer(s) for a block.
- * This is needed in the directory version 2 format case, when
- * multiple non-contiguous fsblocks might be needed to cover one
- * logical directory block.
- * If the buffer count is 1 then the data pointer points to the
- * same place as the b_addr field for the buffer, else to kmem_alloced memory.
- */
-typedef struct xfs_dabuf {
-	short		bbcount;	/* how large is data in bbs */
-	void		*data;		/* pointer for buffers' data */
-	struct xfs_buf	*bp;		/* actually nbuf of these */
-} xfs_dabuf_t;
-
-/*
  * Storage for holding state during Btree searches and split/join ops.
  *
  * Only need space for 5 intermediate nodes.  With a minimum of 62-way
@@ -154,7 +140,7 @@ typedef struct xfs_dabuf {
  * which is slightly more than enough.
  */
 typedef struct xfs_da_state_blk {
-	xfs_dabuf_t	*bp;		/* buffer containing block */
+	struct xfs_buf	*bp;		/* buffer containing block */
 	xfs_dablk_t	blkno;		/* filesystem blkno of buffer */
 	xfs_daddr_t	disk_blkno;	/* on-disk blkno (in BBs) of buffer */
 	int		index;		/* relevant index into block */
@@ -207,7 +193,7 @@ struct xfs_nameops {
  * Routines used for growing the Btree.
  */
 int	xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
-					 xfs_dabuf_t **bpp, int whichfork);
+					 struct xfs_buf **bpp, int whichfork);
 int	xfs_da_split(xfs_da_state_t *state);
 
 /*
@@ -237,14 +223,14 @@ int	xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
 			      int count);
 int	xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			      xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			      xfs_dabuf_t **bp, int whichfork);
+			      struct xfs_buf **bp, int whichfork);
 int	xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			       xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			       xfs_dabuf_t **bpp, int whichfork);
+			       struct xfs_buf **bpp, int whichfork);
 xfs_daddr_t	xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			xfs_dablk_t bno, int whichfork);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
-					  xfs_dabuf_t *dead_buf);
+					  struct xfs_buf *dead_buf);
 
 uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
@@ -254,15 +240,7 @@ enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 xfs_da_state_t *xfs_da_state_alloc(void);
 void xfs_da_state_free(xfs_da_state_t *state);
 
-void xfs_da_buf_done(xfs_dabuf_t *dabuf);
-void xfs_da_log_buf(struct xfs_trans *tp, xfs_dabuf_t *dabuf, uint first,
-			   uint last);
-void xfs_da_brelse(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-void xfs_da_binval(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
-
 extern struct kmem_zone *xfs_da_state_zone;
-extern struct kmem_zone *xfs_dabuf_zone;
 extern const struct xfs_nameops xfs_default_nameops;
 
 #endif	/* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index 67a250c..b26a50f 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -592,7 +592,7 @@ int
 xfs_dir2_shrink_inode(
 	xfs_da_args_t	*args,
 	xfs_dir2_db_t	db,
-	xfs_dabuf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	xfs_fileoff_t	bno;		/* directory file offset */
 	xfs_dablk_t	da;		/* directory file offset */
@@ -634,7 +634,7 @@ xfs_dir2_shrink_inode(
 	/*
 	 * Invalidate the buffer from the transaction.
 	 */
-	xfs_da_binval(tp, bp);
+	xfs_trans_binval(tp, bp);
 	/*
 	 * If it's not a data block, we're done.
 	 */
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 586732f..e93ca8f 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -37,10 +37,10 @@
 /*
  * Local function prototypes.
  */
-static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, xfs_dabuf_t *bp, int first,
-				    int last);
-static void xfs_dir2_block_log_tail(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **bpp,
+static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp,
+				    int first, int last);
+static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp);
+static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp,
 				     int *entno);
 static int xfs_dir2_block_sort(const void *a, const void *b);
 
@@ -66,7 +66,7 @@ xfs_dir2_block_addname(
 	xfs_dir2_data_free_t	*bf;		/* bestfree table in block */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	int			compact;	/* need to compact leaf ents */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
@@ -102,14 +102,14 @@ xfs_dir2_block_addname(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	/*
 	 * Check the magic number, corrupted if wrong.
 	 */
 	if (unlikely(hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_dir2_block_addname",
 				     XFS_ERRLEVEL_LOW, mp, hdr);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 	len = xfs_dir2_data_entsize(args->namelen);
@@ -212,7 +212,7 @@ xfs_dir2_block_addname(
 	 * If this isn't a real add, we're done with the buffer.
 	 */
 	if (args->op_flags & XFS_DA_OP_JUSTCHECK)
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 	/*
 	 * If we don't have space for the new entry & leaf ...
 	 */
@@ -228,7 +228,6 @@ xfs_dir2_block_addname(
 		 * Then add the new entry in that format.
 		 */
 		error = xfs_dir2_block_to_leaf(args, bp);
-		xfs_da_buf_done(bp);
 		if (error)
 			return error;
 		return xfs_dir2_leaf_addname(args);
@@ -422,7 +421,6 @@ xfs_dir2_block_addname(
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_log_entry(tp, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -437,7 +435,7 @@ xfs_dir2_block_getdents(
 	filldir_t		filldir)
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
@@ -469,7 +467,7 @@ xfs_dir2_block_getdents(
 	 * We'll skip entries before this.
 	 */
 	wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	/*
 	 * Set up values for the loop.
@@ -514,7 +512,7 @@ xfs_dir2_block_getdents(
 			    cook & 0x7fffffff, be64_to_cpu(dep->inumber),
 			    DT_UNKNOWN)) {
 			*offset = cook & 0x7fffffff;
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return 0;
 		}
 	}
@@ -525,7 +523,7 @@ xfs_dir2_block_getdents(
 	 */
 	*offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
 			0x7fffffff;
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return 0;
 }
 
@@ -535,17 +533,17 @@ xfs_dir2_block_getdents(
 static void
 xfs_dir2_block_log_leaf(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,		/* block buffer */
 	int			first,		/* index of first logged leaf */
 	int			last)		/* index of last logged leaf */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_leaf_entry_t	*blp;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
-	xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
 		(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
 }
 
@@ -555,13 +553,13 @@ xfs_dir2_block_log_leaf(
 static void
 xfs_dir2_block_log_tail(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_buf		*bp)		/* block buffer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
-	xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
 		(uint)((char *)(btp + 1) - (char *)hdr - 1));
 }
 
@@ -575,7 +573,7 @@ xfs_dir2_block_lookup(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -593,7 +591,7 @@ xfs_dir2_block_lookup(
 		return error;
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -607,7 +605,7 @@ xfs_dir2_block_lookup(
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	return XFS_ERROR(error);
 }
 
@@ -617,13 +615,13 @@ xfs_dir2_block_lookup(
 static int					/* error */
 xfs_dir2_block_lookup_int(
 	xfs_da_args_t		*args,		/* dir lookup arguments */
-	xfs_dabuf_t		**bpp,		/* returned block buffer */
+	struct xfs_buf		**bpp,		/* returned block buffer */
 	int			*entno)		/* returned entry number */
 {
 	xfs_dir2_dataptr_t	addr;		/* data entry address */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -647,7 +645,7 @@ xfs_dir2_block_lookup_int(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -666,7 +664,7 @@ xfs_dir2_block_lookup_int(
 			high = mid - 1;
 		if (low > high) {
 			ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
-			xfs_da_brelse(tp, bp);
+			xfs_trans_brelse(tp, bp);
 			return XFS_ERROR(ENOENT);
 		}
 	}
@@ -714,7 +712,7 @@ xfs_dir2_block_lookup_int(
 	/*
 	 * No match, release the buffer and return ENOENT.
 	 */
-	xfs_da_brelse(tp, bp);
+	xfs_trans_brelse(tp, bp);
 	return XFS_ERROR(ENOENT);
 }
 
@@ -728,7 +726,7 @@ xfs_dir2_block_removename(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf pointer */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -753,7 +751,7 @@ xfs_dir2_block_removename(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -790,10 +788,9 @@ xfs_dir2_block_removename(
 	 * See if the size as a shortform is good enough.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		xfs_da_buf_done(bp);
+	if (size > XFS_IFORK_DSIZE(dp))
 		return 0;
-	}
+
 	/*
 	 * If it works, do the conversion.
 	 */
@@ -810,7 +807,7 @@ xfs_dir2_block_replace(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -829,7 +826,7 @@ xfs_dir2_block_replace(
 	}
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -844,7 +841,6 @@ xfs_dir2_block_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	xfs_dir2_data_log_entry(args->trans, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -871,8 +867,8 @@ xfs_dir2_block_sort(
 int						/* error */
 xfs_dir2_leaf_to_block(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp,		/* leaf buffer */
-	xfs_dabuf_t		*dbp)		/* data buffer */
+	struct xfs_buf		*lbp,		/* leaf buffer */
+	struct xfs_buf		*dbp)		/* data buffer */
 {
 	__be16			*bestsp;	/* leaf bests table */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
@@ -898,7 +894,7 @@ xfs_dir2_leaf_to_block(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
@@ -914,11 +910,9 @@ xfs_dir2_leaf_to_block(
 			if ((error =
 			    xfs_dir2_leaf_trim_data(args, lbp,
 				    (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
-				goto out;
-		} else {
-			error = 0;
-			goto out;
-		}
+				return error;
+		} else
+			return 0;
 	}
 	/*
 	 * Read the data block if we don't already have it, give up if it fails.
@@ -926,9 +920,9 @@ xfs_dir2_leaf_to_block(
 	if (dbp == NULL &&
 	    (error = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &dbp,
 		    XFS_DATA_FORK))) {
-		goto out;
+		return error;
 	}
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 	/*
 	 * Size of the "leaf" area in the block.
@@ -944,10 +938,9 @@ xfs_dir2_leaf_to_block(
 	 * If it's not free or is too short we can't do it.
 	 */
 	if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG ||
-	    be16_to_cpu(dup->length) < size) {
-		error = 0;
-		goto out;
-	}
+	    be16_to_cpu(dup->length) < size)
+		return 0;
+
 	/*
 	 * Start converting it to block form.
 	 */
@@ -989,25 +982,17 @@ xfs_dir2_leaf_to_block(
 	 * Pitch the old leaf block.
 	 */
 	error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
-	lbp = NULL;
-	if (error) {
-		goto out;
-	}
+	if (error)
+		return error;
+
 	/*
 	 * Now see if the resulting block can be shrunken to shortform.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		error = 0;
-		goto out;
-	}
+	if (size > XFS_IFORK_DSIZE(dp))
+		return 0;
+
 	return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
-out:
-	if (lbp)
-		xfs_da_buf_done(lbp);
-	if (dbp)
-		xfs_da_buf_done(dbp);
-	return error;
 }
 
 /*
@@ -1020,7 +1005,7 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_db_t		blkno;		/* dir-relative block # (0) */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail pointer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -1088,7 +1073,7 @@ xfs_dir2_sf_to_block(
 		kmem_free(sfp);
 		return error;
 	}
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
 	/*
 	 * Compute size of block "tail" area.
@@ -1217,6 +1202,5 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index 2046988..44ffd4d 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -42,8 +42,8 @@ xfs_dir2_data_freefind(xfs_dir2_data_hdr_t *hdr, xfs_dir2_data_unused_t *dup);
  */
 void
 xfs_dir2_data_check(
-	xfs_inode_t		*dp,		/* incore inode pointer */
-	xfs_dabuf_t		*bp)		/* data block's buffer */
+	struct xfs_inode	*dp,		/* incore inode pointer */
+	struct xfs_buf		*bp)		/* data block's buffer */
 {
 	xfs_dir2_dataptr_t	addr;		/* addr for leaf lookup */
 	xfs_dir2_data_free_t	*bf;		/* bestfree table */
@@ -65,7 +65,7 @@ xfs_dir2_data_check(
 	struct xfs_name		name;
 
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	bf = hdr->bestfree;
 	p = (char *)(hdr + 1);
 
@@ -389,9 +389,9 @@ int						/* error */
 xfs_dir2_data_init(
 	xfs_da_args_t		*args,		/* directory operation args */
 	xfs_dir2_db_t		blkno,		/* logical dir block number */
-	xfs_dabuf_t		**bpp)		/* output block buffer */
+	struct xfs_buf		**bpp)		/* output block buffer */
 {
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry pointer */
@@ -417,7 +417,7 @@ xfs_dir2_data_init(
 	/*
 	 * Initialize the header.
 	 */
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
 	hdr->bestfree[0].offset = cpu_to_be16(sizeof(*hdr));
 	for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
@@ -449,16 +449,16 @@ xfs_dir2_data_init(
  */
 void
 xfs_dir2_data_log_entry(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
 		(uint)((char *)(xfs_dir2_data_entry_tag_p(dep) + 1) -
 		       (char *)hdr - 1));
 }
@@ -468,15 +468,15 @@ xfs_dir2_data_log_entry(
  */
 void
 xfs_dir2_data_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
+	xfs_trans_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
 }
 
 /*
@@ -484,11 +484,11 @@ xfs_dir2_data_log_header(
  */
 void
 xfs_dir2_data_log_unused(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup)		/* data unused pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
@@ -496,13 +496,13 @@ xfs_dir2_data_log_unused(
 	/*
 	 * Log the first part of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
 		(uint)((char *)&dup->length + sizeof(dup->length) -
 		       1 - (char *)hdr));
 	/*
 	 * Log the end (tag) of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
 		       sizeof(xfs_dir2_data_off_t) - 1));
@@ -514,8 +514,8 @@ xfs_dir2_data_log_unused(
  */
 void
 xfs_dir2_data_make_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
 	xfs_dir2_data_aoff_t	len,		/* length in bytes */
 	int			*needlogp,	/* out: log header */
@@ -531,7 +531,7 @@ xfs_dir2_data_make_free(
 	xfs_dir2_data_unused_t	*prevdup;	/* unused entry before us */
 
 	mp = tp->t_mountp;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 
 	/*
 	 * Figure out where the end of the data area is.
@@ -696,8 +696,8 @@ xfs_dir2_data_make_free(
  */
 void
 xfs_dir2_data_use_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* data block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup,		/* unused entry */
 	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
 	xfs_dir2_data_aoff_t	len,		/* length to use */
@@ -713,7 +713,7 @@ xfs_dir2_data_use_free(
 	xfs_dir2_data_unused_t	*newdup2;	/* another new unused entry */
 	int			oldlen;		/* old unused entry's length */
 
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 	ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 397ffbc..69accf6 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -38,15 +38,15 @@
  * Local function declarations.
  */
 #ifdef DEBUG
-static void xfs_dir2_leaf_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+static void xfs_dir2_leaf_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_leaf_check(dp, bp)
 #endif
-static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **lbpp,
-				    int *indexp, xfs_dabuf_t **dbpp);
-static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_dabuf *bp,
+static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, struct xfs_buf **lbpp,
+				    int *indexp, struct xfs_buf **dbpp);
+static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_buf *bp,
 				    int first, int last);
-static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
+static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_buf *bp);
 
 
 /*
@@ -55,7 +55,7 @@ static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
 int						/* error */
 xfs_dir2_block_to_leaf(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*dbp)		/* input block's buffer */
+	struct xfs_buf		*dbp)		/* input block's buffer */
 {
 	__be16			*bestsp;	/* leaf's bestsp entries */
 	xfs_dablk_t		blkno;		/* leaf block's bno */
@@ -64,7 +64,7 @@ xfs_dir2_block_to_leaf(
 	xfs_dir2_block_tail_t	*btp;		/* block's tail */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
-	xfs_dabuf_t		*lbp;		/* leaf block's buffer */
+	struct xfs_buf		*lbp;		/* leaf block's buffer */
 	xfs_dir2_db_t		ldb;		/* leaf block's bno */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf's tail */
@@ -95,8 +95,8 @@ xfs_dir2_block_to_leaf(
 		return error;
 	}
 	ASSERT(lbp != NULL);
-	leaf = lbp->data;
-	hdr = dbp->data;
+	leaf = lbp->b_addr;
+	hdr = dbp->b_addr;
 	xfs_dir2_data_check(dp, dbp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -143,7 +143,6 @@ xfs_dir2_block_to_leaf(
 	xfs_dir2_leaf_check(dp, lbp);
 	xfs_dir2_data_check(dp, dbp);
 	xfs_dir2_leaf_log_bests(tp, lbp, 0, 0);
-	xfs_da_buf_done(lbp);
 	return 0;
 }
 
@@ -282,7 +281,7 @@ xfs_dir2_leaf_addname(
 	__be16			*bestsp;	/* freespace table in leaf */
 	int			compact;	/* need to compact leaves */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* data unused entry */
@@ -291,7 +290,7 @@ xfs_dir2_leaf_addname(
 	int			highstale;	/* index of next stale leaf */
 	int			i;		/* temporary, index */
 	int			index;		/* leaf table position */
-	xfs_dabuf_t		*lbp;		/* leaf's buffer */
+	struct xfs_buf		*lbp;		/* leaf's buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	int			length;		/* length of new entry */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry table pointer */
@@ -328,7 +327,7 @@ xfs_dir2_leaf_addname(
 	 * But if there are dup hash values the index is of the first of those.
 	 */
 	index = xfs_dir2_leaf_search_hash(args, lbp);
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	length = xfs_dir2_data_entsize(args->namelen);
@@ -402,14 +401,13 @@ xfs_dir2_leaf_addname(
 		 */
 		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
 							args->total == 0) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return XFS_ERROR(ENOSPC);
 		}
 		/*
 		 * Convert to node form.
 		 */
 		error = xfs_dir2_leaf_to_node(args, lbp);
-		xfs_da_buf_done(lbp);
 		if (error)
 			return error;
 		/*
@@ -427,7 +425,7 @@ xfs_dir2_leaf_addname(
 	 * a new data block.
 	 */
 	if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
-		xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, lbp);
 		return use_block == -1 ? XFS_ERROR(ENOSPC) : 0;
 	}
 	/*
@@ -435,7 +433,7 @@ xfs_dir2_leaf_addname(
 	 * changed anything.
 	 */
 	if (args->total == 0 && use_block == -1) {
-		xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, lbp);
 		return XFS_ERROR(ENOSPC);
 	}
 	/*
@@ -466,14 +464,14 @@ xfs_dir2_leaf_addname(
 		 */
 		if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE,
 				&use_block))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
 		/*
 		 * Initialize the block.
 		 */
 		if ((error = xfs_dir2_data_init(args, use_block, &dbp))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
 		/*
@@ -493,7 +491,7 @@ xfs_dir2_leaf_addname(
 		 */
 		else
 			xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		bestsp[use_block] = hdr->bestfree[0].length;
 		grown = 1;
 	}
@@ -505,10 +503,10 @@ xfs_dir2_leaf_addname(
 		if ((error =
 		    xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, use_block),
 			    -1, &dbp, XFS_DATA_FORK))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		grown = 0;
 	}
 	xfs_dir2_data_check(dp, dbp);
@@ -570,9 +568,7 @@ xfs_dir2_leaf_addname(
 	xfs_dir2_leaf_log_header(tp, lbp);
 	xfs_dir2_leaf_log_ents(tp, lbp, lfloglow, lfloghigh);
 	xfs_dir2_leaf_check(dp, lbp);
-	xfs_da_buf_done(lbp);
 	xfs_dir2_data_check(dp, dbp);
-	xfs_da_buf_done(dbp);
 	return 0;
 }
 
@@ -583,8 +579,8 @@ xfs_dir2_leaf_addname(
  */
 STATIC void
 xfs_dir2_leaf_check(
-	xfs_inode_t		*dp,		/* incore directory inode */
-	xfs_dabuf_t		*bp)		/* leaf's buffer */
+	struct xfs_inode	*dp,		/* incore directory inode */
+	struct xfs_buf		*bp)		/* leaf's buffer */
 {
 	int			i;		/* leaf index */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -592,7 +588,7 @@ xfs_dir2_leaf_check(
 	xfs_mount_t		*mp;		/* filesystem mount point */
 	int			stale;		/* count of stale leaves */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	mp = dp->i_mount;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	/*
@@ -628,14 +624,14 @@ xfs_dir2_leaf_check(
 void
 xfs_dir2_leaf_compact(
 	xfs_da_args_t	*args,		/* operation arguments */
-	xfs_dabuf_t	*bp)		/* leaf buffer */
+	struct xfs_buf	*bp)		/* leaf buffer */
 {
 	int		from;		/* source leaf index */
 	xfs_dir2_leaf_t	*leaf;		/* leaf structure */
 	int		loglow;		/* first leaf entry to log */
 	int		to;		/* target leaf index */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	if (!leaf->hdr.stale) {
 		return;
 	}
@@ -677,7 +673,7 @@ xfs_dir2_leaf_compact(
  */
 void
 xfs_dir2_leaf_compact_x1(
-	xfs_dabuf_t	*bp,		/* leaf buffer */
+	struct xfs_buf	*bp,		/* leaf buffer */
 	int		*indexp,	/* insertion index */
 	int		*lowstalep,	/* out: stale entry before us */
 	int		*highstalep,	/* out: stale entry after us */
@@ -693,7 +689,7 @@ xfs_dir2_leaf_compact_x1(
 	int		newindex=0;	/* new insertion index */
 	int		to;		/* destination copy index */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(be16_to_cpu(leaf->hdr.stale) > 1);
 	index = *indexp;
 
@@ -775,7 +771,7 @@ xfs_dir2_leaf_getdents(
 	xfs_off_t		*offset,
 	filldir_t		filldir)
 {
-	xfs_dabuf_t		*bp;		/* data block buffer */
+	struct xfs_buf		*bp;		/* data block buffer */
 	int			byteoff;	/* offset in current block */
 	xfs_dir2_db_t		curdb;		/* db for current block */
 	xfs_dir2_off_t		curoff;		/* current overall offset */
@@ -839,13 +835,13 @@ xfs_dir2_leaf_getdents(
 		 * If we have no buffer, or we're off the end of the
 		 * current buffer, need to get another one.
 		 */
-		if (!bp || ptr >= (char *)bp->data + mp->m_dirblksize) {
+		if (!bp || ptr >= (char *)bp->b_addr + mp->m_dirblksize) {
 			/*
 			 * If we have a buffer, we need to release it and
 			 * take it out of the mapping.
 			 */
 			if (bp) {
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 				map_blocks -= mp->m_dirblkfsbs;
 				/*
@@ -1035,7 +1031,7 @@ xfs_dir2_leaf_getdents(
 			else if (curoff > newoff)
 				ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
 				       curdb);
-			hdr = bp->data;
+			hdr = bp->b_addr;
 			xfs_dir2_data_check(dp, bp);
 			/*
 			 * Find our position in the block.
@@ -1119,7 +1115,7 @@ xfs_dir2_leaf_getdents(
 		*offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
 	kmem_free(map);
 	if (bp)
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 	return error;
 }
 
@@ -1130,10 +1126,10 @@ int
 xfs_dir2_leaf_init(
 	xfs_da_args_t		*args,		/* operation arguments */
 	xfs_dir2_db_t		bno,		/* directory block number */
-	xfs_dabuf_t		**bpp,		/* out: leaf buffer */
+	struct xfs_buf		**bpp,		/* out: leaf buffer */
 	int			magic)		/* magic number for block */
 {
-	xfs_dabuf_t		*bp;		/* leaf buffer */
+	struct xfs_buf		*bp;		/* leaf buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -1156,7 +1152,7 @@ xfs_dir2_leaf_init(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	/*
 	 * Initialize the header.
 	 */
@@ -1186,7 +1182,7 @@ xfs_dir2_leaf_init(
 static void
 xfs_dir2_leaf_log_bests(
 	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
@@ -1195,12 +1191,12 @@ xfs_dir2_leaf_log_bests(
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf);
 	firstb = xfs_dir2_leaf_bests_p(ltp) + first;
 	lastb = xfs_dir2_leaf_bests_p(ltp) + last;
-	xfs_da_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
 		(uint)((char *)lastb - (char *)leaf + sizeof(*lastb) - 1));
 }
 
@@ -1210,7 +1206,7 @@ xfs_dir2_leaf_log_bests(
 void
 xfs_dir2_leaf_log_ents(
 	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
@@ -1218,12 +1214,12 @@ xfs_dir2_leaf_log_ents(
 	xfs_dir2_leaf_entry_t	*lastlep;	/* pointer to last entry */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	firstlep = &leaf->ents[first];
 	lastlep = &leaf->ents[last];
-	xfs_da_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
 		(uint)((char *)lastlep - (char *)leaf + sizeof(*lastlep) - 1));
 }
 
@@ -1232,15 +1228,15 @@ xfs_dir2_leaf_log_ents(
  */
 void
 xfs_dir2_leaf_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* leaf buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
-	xfs_da_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
 		(uint)(sizeof(leaf->hdr) - 1));
 }
 
@@ -1249,18 +1245,18 @@ xfs_dir2_leaf_log_header(
  */
 STATIC void
 xfs_dir2_leaf_log_tail(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* leaf buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
 
 	mp = tp->t_mountp;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
-	xfs_da_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
 		(uint)(mp->m_dirblksize - 1));
 }
 
@@ -1273,12 +1269,12 @@ int
 xfs_dir2_leaf_lookup(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* found entry index */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_trans_t		*tp;		/* transaction pointer */
@@ -1294,7 +1290,7 @@ xfs_dir2_leaf_lookup(
 	tp = args->trans;
 	dp = args->dp;
 	xfs_dir2_leaf_check(dp, lbp);
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	/*
 	 * Get to the leaf entry and contained data entry address.
 	 */
@@ -1303,15 +1299,15 @@ xfs_dir2_leaf_lookup(
 	 * Point to the data entry.
 	 */
 	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)dbp->data +
+	      ((char *)dbp->b_addr +
 	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
 	/*
 	 * Return the found inode number & CI name if appropriate
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
-	xfs_da_brelse(tp, dbp);
-	xfs_da_brelse(tp, lbp);
+	xfs_trans_brelse(tp, dbp);
+	xfs_trans_brelse(tp, lbp);
 	return XFS_ERROR(error);
 }
 
@@ -1324,17 +1320,17 @@ xfs_dir2_leaf_lookup(
 static int					/* error */
 xfs_dir2_leaf_lookup_int(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		**lbpp,		/* out: leaf buffer */
+	struct xfs_buf		**lbpp,		/* out: leaf buffer */
 	int			*indexp,	/* out: index in leaf block */
-	xfs_dabuf_t		**dbpp)		/* out: data buffer */
+	struct xfs_buf		**dbpp)		/* out: data buffer */
 {
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
-	xfs_dabuf_t		*dbp = NULL;	/* data buffer */
+	struct xfs_buf		*dbp = NULL;	/* data buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* index in leaf block */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
@@ -1354,7 +1350,7 @@ xfs_dir2_leaf_lookup_int(
 	if (error)
 		return error;
 	*lbpp = lbp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	xfs_dir2_leaf_check(dp, lbp);
 	/*
 	 * Look for the first leaf entry with our hash value.
@@ -1382,12 +1378,12 @@ xfs_dir2_leaf_lookup_int(
 		 */
 		if (newdb != curdb) {
 			if (dbp)
-				xfs_da_brelse(tp, dbp);
+				xfs_trans_brelse(tp, dbp);
 			error = xfs_da_read_buf(tp, dp,
 						xfs_dir2_db_to_da(mp, newdb),
 						-1, &dbp, XFS_DATA_FORK);
 			if (error) {
-				xfs_da_brelse(tp, lbp);
+				xfs_trans_brelse(tp, lbp);
 				return error;
 			}
 			xfs_dir2_data_check(dp, dbp);
@@ -1396,7 +1392,7 @@ xfs_dir2_leaf_lookup_int(
 		/*
 		 * Point to the data entry.
 		 */
-		dep = (xfs_dir2_data_entry_t *)((char *)dbp->data +
+		dep = (xfs_dir2_data_entry_t *)((char *)dbp->b_addr +
 			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
 		/*
 		 * Compare name and if it's an exact match, return the index
@@ -1424,12 +1420,12 @@ xfs_dir2_leaf_lookup_int(
 	if (args->cmpresult == XFS_CMP_CASE) {
 		ASSERT(cidb != -1);
 		if (cidb != curdb) {
-			xfs_da_brelse(tp, dbp);
+			xfs_trans_brelse(tp, dbp);
 			error = xfs_da_read_buf(tp, dp,
 						xfs_dir2_db_to_da(mp, cidb),
 						-1, &dbp, XFS_DATA_FORK);
 			if (error) {
-				xfs_da_brelse(tp, lbp);
+				xfs_trans_brelse(tp, lbp);
 				return error;
 			}
 		}
@@ -1441,8 +1437,8 @@ xfs_dir2_leaf_lookup_int(
 	 */
 	ASSERT(cidb == -1);
 	if (dbp)
-		xfs_da_brelse(tp, dbp);
-	xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, dbp);
+	xfs_trans_brelse(tp, lbp);
 	return XFS_ERROR(ENOENT);
 }
 
@@ -1456,13 +1452,13 @@ xfs_dir2_leaf_removename(
 	__be16			*bestsp;	/* leaf block best freespace */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		db;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry structure */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_db_t		i;		/* temporary data block # */
 	int			index;		/* index into leaf entries */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
@@ -1483,8 +1479,8 @@ xfs_dir2_leaf_removename(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = lbp->data;
-	hdr = dbp->data;
+	leaf = lbp->b_addr;
+	hdr = dbp->b_addr;
 	xfs_dir2_data_check(dp, dbp);
 	/*
 	 * Point to the leaf entry, use that to point to the data entry.
@@ -1541,12 +1537,9 @@ xfs_dir2_leaf_removename(
 			 * Just go on, returning success, leaving the
 			 * empty block in place.
 			 */
-			if (error == ENOSPC && args->total == 0) {
-				xfs_da_buf_done(dbp);
+			if (error == ENOSPC && args->total == 0)
 				error = 0;
-			}
 			xfs_dir2_leaf_check(dp, lbp);
-			xfs_da_buf_done(lbp);
 			return error;
 		}
 		dbp = NULL;
@@ -1577,10 +1570,9 @@ xfs_dir2_leaf_removename(
 	/*
 	 * If the data block was not the first one, drop it.
 	 */
-	else if (db != mp->m_dirdatablk && dbp != NULL) {
-		xfs_da_buf_done(dbp);
+	else if (db != mp->m_dirdatablk)
 		dbp = NULL;
-	}
+
 	xfs_dir2_leaf_check(dp, lbp);
 	/*
 	 * See if we can convert to block form.
@@ -1595,12 +1587,12 @@ int						/* error */
 xfs_dir2_leaf_replace(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* index of leaf entry */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_trans_t		*tp;		/* transaction pointer */
@@ -1614,7 +1606,7 @@ xfs_dir2_leaf_replace(
 		return error;
 	}
 	dp = args->dp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	/*
 	 * Point to the leaf entry, get data address from it.
 	 */
@@ -1623,7 +1615,7 @@ xfs_dir2_leaf_replace(
 	 * Point to the data entry.
 	 */
 	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)dbp->data +
+	      ((char *)dbp->b_addr +
 	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
 	ASSERT(args->inumber != be64_to_cpu(dep->inumber));
 	/*
@@ -1632,9 +1624,8 @@ xfs_dir2_leaf_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	tp = args->trans;
 	xfs_dir2_data_log_entry(tp, dbp, dep);
-	xfs_da_buf_done(dbp);
 	xfs_dir2_leaf_check(dp, lbp);
-	xfs_da_brelse(tp, lbp);
+	xfs_trans_brelse(tp, lbp);
 	return 0;
 }
 
@@ -1646,7 +1637,7 @@ xfs_dir2_leaf_replace(
 int						/* index value */
 xfs_dir2_leaf_search_hash(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp)		/* leaf buffer */
+	struct xfs_buf		*lbp)		/* leaf buffer */
 {
 	xfs_dahash_t		hash=0;		/* hash from this entry */
 	xfs_dahash_t		hashwant;	/* hash value looking for */
@@ -1656,7 +1647,7 @@ xfs_dir2_leaf_search_hash(
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	int			mid=0;		/* current leaf index */
 
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 #ifndef __KERNEL__
 	if (!leaf->hdr.count)
 		return 0;
@@ -1699,11 +1690,11 @@ xfs_dir2_leaf_search_hash(
 int						/* error */
 xfs_dir2_leaf_trim_data(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp,		/* leaf buffer */
+	struct xfs_buf		*lbp,		/* leaf buffer */
 	xfs_dir2_db_t		db)		/* data block number */
 {
 	__be16			*bestsp;	/* leaf bests table */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -1722,12 +1713,12 @@ xfs_dir2_leaf_trim_data(
 		return error;
 	}
 
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 
 #ifdef DEBUG
 {
-	struct xfs_dir2_data_hdr *hdr = dbp->data;
+	struct xfs_dir2_data_hdr *hdr = dbp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 	ASSERT(be16_to_cpu(hdr->bestfree[0].length) ==
@@ -1741,7 +1732,7 @@ xfs_dir2_leaf_trim_data(
 	 */
 	if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
 		ASSERT(error != ENOSPC);
-		xfs_da_brelse(tp, dbp);
+		xfs_trans_brelse(tp, dbp);
 		return error;
 	}
 	/*
@@ -1781,10 +1772,10 @@ xfs_dir2_node_to_leaf(
 	xfs_da_args_t		*args;		/* operation arguments */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
-	xfs_dabuf_t		*fbp;		/* buffer for freespace block */
+	struct xfs_buf		*fbp;		/* buffer for freespace block */
 	xfs_fileoff_t		fo;		/* freespace file offset */
 	xfs_dir2_free_t		*free;		/* freespace structure */
-	xfs_dabuf_t		*lbp;		/* buffer for leaf block */
+	struct xfs_buf		*lbp;		/* buffer for leaf block */
 	xfs_dir2_leaf_tail_t	*ltp;		/* tail of leaf structure */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
@@ -1838,7 +1829,7 @@ xfs_dir2_node_to_leaf(
 	if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + mp->m_dirblksize)
 		return 0;
 	lbp = state->path.blk[0].bp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
 	 * Read the freespace block.
@@ -1847,7 +1838,7 @@ xfs_dir2_node_to_leaf(
 			XFS_DATA_FORK))) {
 		return error;
 	}
-	free = fbp->data;
+	free = fbp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	ASSERT(!free->hdr.firstdb);
 
@@ -1857,7 +1848,7 @@ xfs_dir2_node_to_leaf(
 	 */
 	if (xfs_dir2_leaf_size(&leaf->hdr, be32_to_cpu(free->hdr.nvalid)) >
 			mp->m_dirblksize) {
-		xfs_da_brelse(tp, fbp);
+		xfs_trans_brelse(tp, fbp);
 		return 0;
 	}
 
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index b0f2678..6c70524 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -36,20 +36,20 @@
 /*
  * Function declarations.
  */
-static void xfs_dir2_free_log_header(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_leafn_add(xfs_dabuf_t *bp, xfs_da_args_t *args, int index);
+static int xfs_dir2_leafn_add(struct xfs_buf *bp, xfs_da_args_t *args,
+			      int index);
 #ifdef DEBUG
-static void xfs_dir2_leafn_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+static void xfs_dir2_leafn_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_leafn_check(dp, bp)
 #endif
-static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, xfs_dabuf_t *bp_s,
-				    int start_s, xfs_dabuf_t *bp_d, int start_d,
-				    int count);
+static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, struct xfs_buf *bp_s,
+				    int start_s, struct xfs_buf *bp_d,
+				    int start_d, int count);
 static void xfs_dir2_leafn_rebalance(xfs_da_state_t *state,
 				     xfs_da_state_blk_t *blk1,
 				     xfs_da_state_blk_t *blk2);
-static int xfs_dir2_leafn_remove(xfs_da_args_t *args, xfs_dabuf_t *bp,
+static int xfs_dir2_leafn_remove(xfs_da_args_t *args, struct xfs_buf *bp,
 				 int index, xfs_da_state_blk_t *dblk,
 				 int *rval);
 static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
@@ -60,16 +60,16 @@ static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
  */
 STATIC void
 xfs_dir2_free_log_bests(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)&free->bests[first] - (char *)free),
 		(uint)((char *)&free->bests[last] - (char *)free +
 		       sizeof(free->bests[0]) - 1));
@@ -80,14 +80,14 @@ xfs_dir2_free_log_bests(
  */
 static void
 xfs_dir2_free_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
 		(uint)(sizeof(xfs_dir2_free_hdr_t) - 1));
 }
 
@@ -99,11 +99,11 @@ xfs_dir2_free_log_header(
 int						/* error */
 xfs_dir2_leaf_to_node(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp)		/* leaf buffer */
+	struct xfs_buf		*lbp)		/* leaf buffer */
 {
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	xfs_dir2_db_t		fdb;		/* freespace block number */
 	xfs_dir2_free_t		*free;		/* freespace structure */
 	__be16			*from;		/* pointer to freespace entry */
@@ -136,8 +136,8 @@ xfs_dir2_leaf_to_node(
 		return error;
 	}
 	ASSERT(fbp != NULL);
-	free = fbp->data;
-	leaf = lbp->data;
+	free = fbp->b_addr;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
 	 * Initialize the freespace block header.
@@ -164,7 +164,6 @@ xfs_dir2_leaf_to_node(
 	xfs_dir2_leaf_log_header(tp, lbp);
 	xfs_dir2_free_log_header(tp, fbp);
 	xfs_dir2_free_log_bests(tp, fbp, 0, be32_to_cpu(free->hdr.nvalid) - 1);
-	xfs_da_buf_done(fbp);
 	xfs_dir2_leafn_check(dp, lbp);
 	return 0;
 }
@@ -175,7 +174,7 @@ xfs_dir2_leaf_to_node(
  */
 static int					/* error */
 xfs_dir2_leafn_add(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			index)		/* insertion pt for new entry */
 {
@@ -195,7 +194,7 @@ xfs_dir2_leafn_add(
 	dp = args->dp;
 	mp = dp->i_mount;
 	tp = args->trans;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 
 	/*
 	 * Quick check just to make sure we are not going to index
@@ -261,15 +260,15 @@ xfs_dir2_leafn_add(
  */
 void
 xfs_dir2_leafn_check(
-	xfs_inode_t	*dp,			/* incore directory inode */
-	xfs_dabuf_t	*bp)			/* leaf buffer */
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	int		i;			/* leaf index */
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 	xfs_mount_t	*mp;			/* filesystem mount point */
 	int		stale;			/* count of stale leaves */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	mp = dp->i_mount;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
@@ -291,12 +290,12 @@ xfs_dir2_leafn_check(
  */
 xfs_dahash_t					/* hash value */
 xfs_dir2_leafn_lasthash(
-	xfs_dabuf_t	*bp,			/* leaf buffer */
+	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
 {
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -311,12 +310,12 @@ xfs_dir2_leafn_lasthash(
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_addname(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_db_t		curfdb = -1;	/* current free block number */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -335,7 +334,7 @@ xfs_dir2_leafn_lookup_for_addname(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -352,7 +351,7 @@ xfs_dir2_leafn_lookup_for_addname(
 		/* If so, it's a free block buffer, get the block number. */
 		curbp = state->extrablk.bp;
 		curfdb = state->extrablk.blkno;
-		free = curbp->data;
+		free = curbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	}
 	length = xfs_dir2_data_entsize(args->namelen);
@@ -394,7 +393,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				 * If we had one before, drop it.
 				 */
 				if (curbp)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				/*
 				 * Read the free block.
 				 */
@@ -403,7 +402,7 @@ xfs_dir2_leafn_lookup_for_addname(
 						-1, &curbp, XFS_DATA_FORK);
 				if (error)
 					return error;
-				free = curbp->data;
+				free = curbp->b_addr;
 				ASSERT(be32_to_cpu(free->hdr.magic) ==
 					XFS_DIR2_FREE_MAGIC);
 				ASSERT((be32_to_cpu(free->hdr.firstdb) %
@@ -424,7 +423,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
 							XFS_ERRLEVEL_LOW, mp);
 				if (curfdb != newfdb)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				return XFS_ERROR(EFSCORRUPTED);
 			}
 			curfdb = newfdb;
@@ -459,12 +458,12 @@ out:
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_entry(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -480,7 +479,7 @@ xfs_dir2_leafn_lookup_for_entry(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -525,7 +524,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			 */
 			if (curbp && (args->cmpresult == XFS_CMP_DIFFERENT ||
 						curdb != state->extrablk.blkno))
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 			/*
 			 * If needing the block that is saved with a CI match,
 			 * use it otherwise read in the new data block.
@@ -547,7 +546,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		/*
 		 * Point to the data entry.
 		 */
-		dep = (xfs_dir2_data_entry_t *)((char *)curbp->data +
+		dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
 			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
 		/*
 		 * Compare the entry and if it's an exact match, return
@@ -559,7 +558,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			/* If there is a CI match block, drop it */
 			if (args->cmpresult != XFS_CMP_DIFFERENT &&
 						curdb != state->extrablk.blkno)
-				xfs_da_brelse(tp, state->extrablk.bp);
+				xfs_trans_brelse(tp, state->extrablk.bp);
 			args->cmpresult = cmp;
 			args->inumber = be64_to_cpu(dep->inumber);
 			*indexp = index;
@@ -567,7 +566,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			state->extrablk.bp = curbp;
 			state->extrablk.blkno = curdb;
 			state->extrablk.index = (int)((char *)dep -
-							(char *)curbp->data);
+							(char *)curbp->b_addr);
 			state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
 			if (cmp == XFS_CMP_EXACT)
 				return XFS_ERROR(EEXIST);
@@ -586,7 +585,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		} else {
 			/* If the curbp is not the CI match block, drop it */
 			if (state->extrablk.bp != curbp)
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 		}
 	} else {
 		state->extravalid = 0;
@@ -602,7 +601,7 @@ xfs_dir2_leafn_lookup_for_entry(
  */
 int
 xfs_dir2_leafn_lookup_int(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
@@ -620,9 +619,9 @@ xfs_dir2_leafn_lookup_int(
 static void
 xfs_dir2_leafn_moveents(
 	xfs_da_args_t	*args,			/* operation arguments */
-	xfs_dabuf_t	*bp_s,			/* source leaf buffer */
+	struct xfs_buf	*bp_s,			/* source leaf buffer */
 	int		start_s,		/* source leaf index */
-	xfs_dabuf_t	*bp_d,			/* destination leaf buffer */
+	struct xfs_buf	*bp_d,			/* destination leaf buffer */
 	int		start_d,		/* destination leaf index */
 	int		count)			/* count of leaves to copy */
 {
@@ -640,8 +639,8 @@ xfs_dir2_leafn_moveents(
 		return;
 	}
 	tp = args->trans;
-	leaf_s = bp_s->data;
-	leaf_d = bp_d->data;
+	leaf_s = bp_s->b_addr;
+	leaf_d = bp_d->b_addr;
 	/*
 	 * If the destination index is not the end of the current
 	 * destination leaf entries, open up a hole in the destination
@@ -702,14 +701,14 @@ xfs_dir2_leafn_moveents(
  */
 int						/* sort order */
 xfs_dir2_leafn_order(
-	xfs_dabuf_t	*leaf1_bp,		/* leaf1 buffer */
-	xfs_dabuf_t	*leaf2_bp)		/* leaf2 buffer */
+	struct xfs_buf	*leaf1_bp,		/* leaf1 buffer */
+	struct xfs_buf	*leaf2_bp)		/* leaf2 buffer */
 {
 	xfs_dir2_leaf_t	*leaf1;			/* leaf1 structure */
 	xfs_dir2_leaf_t	*leaf2;			/* leaf2 structure */
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (be16_to_cpu(leaf1->hdr.count) > 0 &&
@@ -757,8 +756,8 @@ xfs_dir2_leafn_rebalance(
 		blk1 = blk2;
 		blk2 = tmp;
 	}
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	oldsum = be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count);
 #ifdef DEBUG
 	oldstale = be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale);
@@ -834,14 +833,14 @@ xfs_dir2_leafn_rebalance(
 static int					/* error */
 xfs_dir2_leafn_remove(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			index,		/* leaf entry index */
 	xfs_da_state_blk_t	*dblk,		/* data block */
 	int			*rval)		/* resulting block needs join */
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		db;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -858,7 +857,7 @@ xfs_dir2_leafn_remove(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
 	 * Point to the entry we're removing.
@@ -884,7 +883,7 @@ xfs_dir2_leafn_remove(
 	 * in the data block in case it changes.
 	 */
 	dbp = dblk->bp;
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	dep = (xfs_dir2_data_entry_t *)((char *)hdr + off);
 	longest = be16_to_cpu(hdr->bestfree[0].length);
 	needlog = needscan = 0;
@@ -905,7 +904,7 @@ xfs_dir2_leafn_remove(
 	 */
 	if (longest < be16_to_cpu(hdr->bestfree[0].length)) {
 		int		error;		/* error return value */
-		xfs_dabuf_t	*fbp;		/* freeblock buffer */
+		struct xfs_buf	*fbp;		/* freeblock buffer */
 		xfs_dir2_db_t	fdb;		/* freeblock block number */
 		int		findex;		/* index in freeblock entries */
 		xfs_dir2_free_t	*free;		/* freeblock structure */
@@ -920,7 +919,7 @@ xfs_dir2_leafn_remove(
 				-1, &fbp, XFS_DATA_FORK))) {
 			return error;
 		}
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		ASSERT(be32_to_cpu(free->hdr.firstdb) ==
 		       xfs_dir2_free_max_bests(mp) *
@@ -948,9 +947,7 @@ xfs_dir2_leafn_remove(
 			 * In this case just drop the buffer and some one else
 			 * will eventually get rid of the empty block.
 			 */
-			else if (error == ENOSPC && args->total == 0)
-				xfs_da_buf_done(dbp);
-			else
+			else if (!(error == ENOSPC && args->total == 0))
 				return error;
 		}
 		/*
@@ -1018,11 +1015,6 @@ xfs_dir2_leafn_remove(
 		 */
 		if (logfree)
 			xfs_dir2_free_log_bests(tp, fbp, findex, findex);
-		/*
-		 * Drop the buffer if we still have it.
-		 */
-		if (fbp)
-			xfs_da_buf_done(fbp);
 	}
 	xfs_dir2_leafn_check(dp, bp);
 	/*
@@ -1114,7 +1106,7 @@ xfs_dir2_leafn_toosmall(
 {
 	xfs_da_state_blk_t	*blk;		/* leaf block */
 	xfs_dablk_t		blkno;		/* leaf block number */
-	xfs_dabuf_t		*bp;		/* leaf buffer */
+	struct xfs_buf		*bp;		/* leaf buffer */
 	int			bytes;		/* bytes in use */
 	int			count;		/* leaf live entry count */
 	int			error;		/* error return value */
@@ -1130,7 +1122,7 @@ xfs_dir2_leafn_toosmall(
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[state->path.active - 1];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	leaf = (xfs_dir2_leaf_t *)info;
 	count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
@@ -1189,7 +1181,7 @@ xfs_dir2_leafn_toosmall(
 		leaf = (xfs_dir2_leaf_t *)info;
 		count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes = state->blocksize - (state->blocksize >> 2);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes -= count * (uint)sizeof(leaf->ents[0]);
@@ -1198,7 +1190,7 @@ xfs_dir2_leafn_toosmall(
 		 */
 		if (bytes >= 0)
 			break;
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 	}
 	/*
 	 * Didn't like either block, give up.
@@ -1207,11 +1199,7 @@ xfs_dir2_leafn_toosmall(
 		*action = 0;
 		return 0;
 	}
-	/*
-	 * Done with the sibling leaf block here, drop the dabuf
-	 * so path_shift can get it.
-	 */
-	xfs_da_buf_done(bp);
+
 	/*
 	 * Make altpath point to the block we want to keep (the lower
 	 * numbered block) and path point to the block we want to drop.
@@ -1247,8 +1235,8 @@ xfs_dir2_leafn_unbalance(
 	args = state->args;
 	ASSERT(drop_blk->magic == XFS_DIR2_LEAFN_MAGIC);
 	ASSERT(save_blk->magic == XFS_DIR2_LEAFN_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
@@ -1356,13 +1344,13 @@ xfs_dir2_node_addname_int(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		dbno;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* data unused entry pointer */
 	int			error;		/* error return value */
 	xfs_dir2_db_t		fbno;		/* freespace block number */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	int			findex;		/* freespace entry index */
 	xfs_dir2_free_t		*free=NULL;	/* freespace block structure */
 	xfs_dir2_db_t		ifbno;		/* initial freespace block no */
@@ -1390,7 +1378,7 @@ xfs_dir2_node_addname_int(
 		 * Remember initial freespace block number.
 		 */
 		ifbno = fblk->blkno;
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		findex = fblk->index;
 		/*
@@ -1474,7 +1462,7 @@ xfs_dir2_node_addname_int(
 			if (unlikely(fbp == NULL)) {
 				continue;
 			}
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 			findex = 0;
 		}
@@ -1492,7 +1480,7 @@ xfs_dir2_node_addname_int(
 				/*
 				 * Drop the block.
 				 */
-				xfs_da_brelse(tp, fbp);
+				xfs_trans_brelse(tp, fbp);
 				fbp = NULL;
 				if (fblk && fblk->bp)
 					fblk->bp = NULL;
@@ -1507,36 +1495,23 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Not allowed to allocate, return failure.
 		 */
-		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
-							args->total == 0) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
 			return XFS_ERROR(ENOSPC);
-		}
+
 		/*
 		 * Allocate and initialize the new data block.
 		 */
 		if (unlikely((error = xfs_dir2_grow_inode(args,
 							 XFS_DIR2_DATA_SPACE,
 							 &dbno)) ||
-		    (error = xfs_dir2_data_init(args, dbno, &dbp)))) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		    (error = xfs_dir2_data_init(args, dbno, &dbp))))
 			return error;
-		}
+
 		/*
 		 * If (somehow) we have a freespace block, get rid of it.
 		 */
 		if (fbp)
-			xfs_da_brelse(tp, fbp);
+			xfs_trans_brelse(tp, fbp);
 		if (fblk && fblk->bp)
 			fblk->bp = NULL;
 
@@ -1547,10 +1522,9 @@ xfs_dir2_node_addname_int(
 		fbno = xfs_dir2_db_to_fdb(mp, dbno);
 		if (unlikely(error = xfs_da_read_buf(tp, dp,
 				xfs_dir2_db_to_da(mp, fbno), -2, &fbp,
-				XFS_DATA_FORK))) {
-			xfs_da_buf_done(dbp);
+				XFS_DATA_FORK)))
 			return error;
-  		}
+
 		/*
 		 * If there wasn't a freespace block, the read will
 		 * return a NULL fbp.  Allocate and initialize a new one.
@@ -1598,7 +1572,7 @@ xfs_dir2_node_addname_int(
 			 * Initialize the new block to be empty, and remember
 			 * its first slot as our empty slot.
 			 */
-			free = fbp->data;
+			free = fbp->b_addr;
 			free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
 			free->hdr.firstdb = cpu_to_be32(
 				(fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
@@ -1606,7 +1580,7 @@ xfs_dir2_node_addname_int(
 			free->hdr.nvalid = 0;
 			free->hdr.nused = 0;
 		} else {
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		}
 
@@ -1639,7 +1613,7 @@ xfs_dir2_node_addname_int(
 		 * We haven't allocated the data entry yet so this will
 		 * change again.
 		 */
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		free->bests[findex] = hdr->bestfree[0].length;
 		logfree = 1;
 	}
@@ -1650,22 +1624,17 @@ xfs_dir2_node_addname_int(
 		/*
 		 * If just checking, we succeeded.
 		 */
-		if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if (args->op_flags & XFS_DA_OP_JUSTCHECK)
 			return 0;
-		}
+
 		/*
 		 * Read the data block in.
 		 */
-		if (unlikely(
-		    error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
-				-1, &dbp, XFS_DATA_FORK))) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
+				-1, &dbp, XFS_DATA_FORK);
+		if (error)
 			return error;
-		}
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		logfree = 0;
 	}
 	ASSERT(be16_to_cpu(hdr->bestfree[0].length) >= length);
@@ -1714,16 +1683,10 @@ xfs_dir2_node_addname_int(
 	if (logfree)
 		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
 	/*
-	 * If the caller didn't hand us the freespace block, drop it.
-	 */
-	if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-		xfs_da_buf_done(fbp);
-	/*
 	 * Return the data block and offset in args, then drop the data block.
 	 */
 	args->blkno = (xfs_dablk_t)dbno;
 	args->index = be16_to_cpu(*tagp);
-	xfs_da_buf_done(dbp);
 	return 0;
 }
 
@@ -1761,22 +1724,23 @@ xfs_dir2_node_lookup(
 		/* If a CI match, dup the actual name and return EEXIST */
 		xfs_dir2_data_entry_t	*dep;
 
-		dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp->
-						data + state->extrablk.index);
+		dep = (xfs_dir2_data_entry_t *)
+			((char *)state->extrablk.bp->b_addr +
+						 state->extrablk.index);
 		rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
 	}
 	/*
 	 * Release the btree blocks and leaf block.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	/*
 	 * Release the data block if we have it.
 	 */
 	if (state->extravalid && state->extrablk.bp) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1893,13 +1857,13 @@ xfs_dir2_node_replace(
 		 */
 		blk = &state->path.blk[state->path.active - 1];
 		ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
-		leaf = blk->bp->data;
+		leaf = blk->bp->b_addr;
 		lep = &leaf->ents[blk->index];
 		ASSERT(state->extravalid);
 		/*
 		 * Point to the data entry.
 		 */
-		hdr = state->extrablk.bp->data;
+		hdr = state->extrablk.bp->b_addr;
 		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 		dep = (xfs_dir2_data_entry_t *)
 		      ((char *)hdr +
@@ -1916,14 +1880,14 @@ xfs_dir2_node_replace(
 	 * Didn't find it, and we're holding a data block.  Drop it.
 	 */
 	else if (state->extravalid) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	/*
 	 * Release all the buffers in the cursor.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1940,7 +1904,7 @@ xfs_dir2_node_trim_free(
 	xfs_fileoff_t		fo,		/* free block number */
 	int			*rvalp)		/* out: did something */
 {
-	xfs_dabuf_t		*bp;		/* freespace buffer */
+	struct xfs_buf		*bp;		/* freespace buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_free_t		*free;		/* freespace structure */
@@ -1965,13 +1929,13 @@ xfs_dir2_node_trim_free(
 	if (bp == NULL) {
 		return 0;
 	}
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	/*
 	 * If there are used entries, there's nothing to do.
 	 */
 	if (be32_to_cpu(free->hdr.nused) > 0) {
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		*rvalp = 0;
 		return 0;
 	}
@@ -1987,7 +1951,7 @@ xfs_dir2_node_trim_free(
 		 * pieces.  This is the last block of an extent.
 		 */
 		ASSERT(error != ENOSPC);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return error;
 	}
 	/*
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h
index 067f403..3523d3e 100644
--- a/fs/xfs/xfs_dir2_priv.h
+++ b/fs/xfs/xfs_dir2_priv.h
@@ -25,7 +25,7 @@ extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
 extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
 				xfs_dir2_db_t *dbp);
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
-				struct xfs_dabuf *bp);
+				struct xfs_buf *bp);
 extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
 				const unsigned char *name, int len);
 
@@ -37,11 +37,11 @@ extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_block_removename(struct xfs_da_args *args);
 extern int xfs_dir2_block_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, struct xfs_dabuf *dbp);
+		struct xfs_buf *lbp, struct xfs_buf *dbp);
 
 /* xfs_dir2_data.c */
 #ifdef DEBUG
-extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_dabuf *bp);
+extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_data_check(dp,bp)
 #endif
@@ -51,43 +51,43 @@ xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
 extern void xfs_dir2_data_freescan(struct xfs_mount *mp,
 		struct xfs_dir2_data_hdr *hdr, int *loghead);
 extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
-		struct xfs_dabuf **bpp);
-extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp);
+extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_entry *dep);
 extern void xfs_dir2_data_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup);
-extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
 		int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup, xfs_dir2_data_aoff_t offset,
 		xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
 
 /* xfs_dir2_leaf.c */
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
-		struct xfs_dabuf *dbp);
+		struct xfs_buf *dbp);
 extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);
 extern void xfs_dir2_leaf_compact(struct xfs_da_args *args,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_leaf_compact_x1(struct xfs_dabuf *bp, int *indexp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_leaf_compact_x1(struct xfs_buf *bp, int *indexp,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir2_leaf_getdents(struct xfs_inode *dp, void *dirent,
 		size_t bufsize, xfs_off_t *offset, filldir_t filldir);
 extern int xfs_dir2_leaf_init(struct xfs_da_args *args, xfs_dir2_db_t bno,
-		struct xfs_dabuf **bpp, int magic);
-extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp, int magic);
+extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_buf *bp,
 		int first, int last);
 extern void xfs_dir2_leaf_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
+		struct xfs_buf *bp);
 extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_search_hash(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
+		struct xfs_buf *lbp);
 extern int xfs_dir2_leaf_trim_data(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, xfs_dir2_db_t db);
+		struct xfs_buf *lbp, xfs_dir2_db_t db);
 extern struct xfs_dir2_leaf_entry *
 xfs_dir2_leaf_find_entry(struct xfs_dir2_leaf *leaf, int index, int compact,
 		int lowstale, int highstale,
@@ -96,13 +96,13 @@ extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_dabuf *bp, int *count);
-extern int xfs_dir2_leafn_lookup_int(struct xfs_dabuf *bp,
+		struct xfs_buf *lbp);
+extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_buf *bp, int *count);
+extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp,
 		struct xfs_da_args *args, int *indexp,
 		struct xfs_da_state *state);
-extern int xfs_dir2_leafn_order(struct xfs_dabuf *leaf1_bp,
-		struct xfs_dabuf *leaf2_bp);
+extern int xfs_dir2_leafn_order(struct xfs_buf *leaf1_bp,
+		struct xfs_buf *leaf2_bp);
 extern int xfs_dir2_leafn_split(struct xfs_da_state *state,
 	struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk);
 extern int xfs_dir2_leafn_toosmall(struct xfs_da_state *state, int *action);
@@ -122,7 +122,7 @@ extern xfs_ino_t xfs_dir2_sfe_get_ino(struct xfs_dir2_sf_hdr *sfp,
 		struct xfs_dir2_sf_entry *sfep);
 extern int xfs_dir2_block_sfsize(struct xfs_inode *dp,
 		struct xfs_dir2_data_hdr *block, struct xfs_dir2_sf_hdr *sfhp);
-extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_dabuf *bp,
+extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_buf *bp,
 		int size, xfs_dir2_sf_hdr_t *sfhp);
 extern int xfs_dir2_sf_addname(struct xfs_da_args *args);
 extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index 19bf0c5..1b9fc3e 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -222,7 +222,7 @@ xfs_dir2_block_sfsize(
 int						/* error */
 xfs_dir2_block_to_sf(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,
 	int			size,		/* shortform directory size */
 	xfs_dir2_sf_hdr_t	*sfhp)		/* shortform directory hdr */
 {
@@ -249,7 +249,7 @@ xfs_dir2_block_to_sf(
 	 * and add local data.
 	 */
 	hdr = kmem_alloc(mp->m_dirblksize, KM_SLEEP);
-	memcpy(hdr, bp->data, mp->m_dirblksize);
+	memcpy(hdr, bp->b_addr, mp->m_dirblksize);
 	logflags = XFS_ILOG_CORE;
 	if ((error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp))) {
 		ASSERT(error != ENOSPC);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 425f6e9..07f70e1 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1491,13 +1491,9 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
-	if (!xfs_dabuf_zone)
-		goto out_destroy_da_state_zone;
-
 	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
 	if (!xfs_ifork_zone)
-		goto out_destroy_dabuf_zone;
+		goto out_destroy_da_state_zone;
 
 	xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
 	if (!xfs_trans_zone)
@@ -1560,8 +1556,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_trans_zone);
  out_destroy_ifork_zone:
 	kmem_zone_destroy(xfs_ifork_zone);
- out_destroy_dabuf_zone:
-	kmem_zone_destroy(xfs_dabuf_zone);
  out_destroy_da_state_zone:
 	kmem_zone_destroy(xfs_da_state_zone);
  out_destroy_btree_cur_zone:
@@ -1589,7 +1583,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_log_item_desc_zone);
 	kmem_zone_destroy(xfs_trans_zone);
 	kmem_zone_destroy(xfs_ifork_zone);
-	kmem_zone_destroy(xfs_dabuf_zone);
 	kmem_zone_destroy(xfs_da_state_zone);
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 9/9] xfs: factor buffer reading from xfs_dir2_leaf_getdents

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

The buffer reading code in xfs_dir2_leaf_getdents is complex and difficult to
follow due to the readahead and all the context is carries. it is also badly
indented and so difficult to read. Factor it out into a separate function to
make it easier to understand and optimise in future patches.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_dir2_leaf.c |  434 ++++++++++++++++++++++++++----------------------
 1 file changed, 232 insertions(+), 202 deletions(-)

diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 69accf6..0b29625 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -759,6 +759,218 @@ xfs_dir2_leaf_compact_x1(
 	*highstalep = highstale;
 }
 
+struct xfs_dir2_leaf_map_info {
+	xfs_extlen_t	map_blocks;	/* number of fsbs in map */
+	xfs_dablk_t	map_off;	/* last mapped file offset */
+	int		map_size;	/* total entries in *map */
+	int		map_valid;	/* valid entries in *map */
+	int		nmap;		/* mappings to ask xfs_bmapi */
+	xfs_dir2_db_t	curdb;		/* db for current block */
+	int		ra_current;	/* number of read-ahead blks */
+	int		ra_index;	/* *map index for read-ahead */
+	int		ra_offset;	/* map entry offset for ra */
+	int		ra_want;	/* readahead count wanted */
+	struct xfs_bmbt_irec map[];	/* map vector for blocks */
+};
+
+STATIC int
+xfs_dir2_leaf_readbuf(
+	struct xfs_inode	*dp,
+	size_t			bufsize,
+	struct xfs_dir2_leaf_map_info *mip,
+	xfs_dir2_off_t		*curoff,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_buf		*bp = *bpp;
+	struct xfs_bmbt_irec	*map = mip->map;
+	int			error = 0;
+	int			length;
+	int			i;
+	int			j;
+
+	/*
+	 * If we have a buffer, we need to release it and
+	 * take it out of the mapping.
+	 */
+
+	if (bp) {
+		xfs_trans_brelse(NULL, bp);
+		bp = NULL;
+		mip->map_blocks -= mp->m_dirblkfsbs;
+		/*
+		 * Loop to get rid of the extents for the
+		 * directory block.
+		 */
+		for (i = mp->m_dirblkfsbs; i > 0; ) {
+			j = min_t(int, map->br_blockcount, i);
+			map->br_blockcount -= j;
+			map->br_startblock += j;
+			map->br_startoff += j;
+			/*
+			 * If mapping is done, pitch it from
+			 * the table.
+			 */
+			if (!map->br_blockcount && --mip->map_valid)
+				memmove(&map[0], &map[1],
+					sizeof(map[0]) * mip->map_valid);
+			i -= j;
+		}
+	}
+
+	/*
+	 * Recalculate the readahead blocks wanted.
+	 */
+	mip->ra_want = howmany(bufsize + mp->m_dirblksize,
+			       mp->m_sb.sb_blocksize) - 1;
+	ASSERT(mip->ra_want >= 0);
+
+	/*
+	 * If we don't have as many as we want, and we haven't
+	 * run out of data blocks, get some more mappings.
+	 */
+	if (1 + mip->ra_want > mip->map_blocks &&
+	    mip->map_off < xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
+		/*
+		 * Get more bmaps, fill in after the ones
+		 * we already have in the table.
+		 */
+		mip->nmap = mip->map_size - mip->map_valid;
+		error = xfs_bmapi_read(dp, mip->map_off,
+				xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET) -
+								mip->map_off,
+				&map[mip->map_valid], &mip->nmap, 0);
+
+		/*
+		 * Don't know if we should ignore this or try to return an
+		 * error.  The trouble with returning errors is that readdir
+		 * will just stop without actually passing the error through.
+		 */
+		if (error)
+			goto out;	/* XXX */
+
+		/*
+		 * If we got all the mappings we asked for, set the final map
+		 * offset based on the last bmap value received.  Otherwise,
+		 * we've reached the end.
+		 */
+		if (mip->nmap == mip->map_size - mip->map_valid) {
+			i = mip->map_valid + mip->nmap - 1;
+			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
+		} else
+			mip->map_off = xfs_dir2_byte_to_da(mp,
+							XFS_DIR2_LEAF_OFFSET);
+
+		/*
+		 * Look for holes in the mapping, and eliminate them.  Count up
+		 * the valid blocks.
+		 */
+		for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) {
+			if (map[i].br_startblock == HOLESTARTBLOCK) {
+				mip->nmap--;
+				length = mip->map_valid + mip->nmap - i;
+				if (length)
+					memmove(&map[i], &map[i + 1],
+						sizeof(map[i]) * length);
+			} else {
+				mip->map_blocks += map[i].br_blockcount;
+				i++;
+			}
+		}
+		mip->map_valid += mip->nmap;
+	}
+
+	/*
+	 * No valid mappings, so no more data blocks.
+	 */
+	if (!mip->map_valid) {
+		*curoff = xfs_dir2_da_to_byte(mp, mip->map_off);
+		goto out;
+	}
+
+	/*
+	 * Read the directory block starting at the first mapping.
+	 */
+	mip->curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
+	error = xfs_da_read_buf(NULL, dp, map->br_startoff,
+			map->br_blockcount >= mp->m_dirblkfsbs ?
+			    XFS_FSB_TO_DADDR(mp, map->br_startblock) : -1,
+			&bp, XFS_DATA_FORK);
+
+	/*
+	 * Should just skip over the data block instead of giving up.
+	 */
+	if (error)
+		goto out;	/* XXX */
+
+	/*
+	 * Adjust the current amount of read-ahead: we just read a block that
+	 * was previously ra.
+	 */
+	if (mip->ra_current)
+		mip->ra_current -= mp->m_dirblkfsbs;
+
+	/*
+	 * Do we need more readahead?
+	 */
+	for (mip->ra_index = mip->ra_offset = i = 0;
+	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
+	     i += mp->m_dirblkfsbs) {
+		ASSERT(mip->ra_index < mip->map_valid);
+		/*
+		 * Read-ahead a contiguous directory block.
+		 */
+		if (i > mip->ra_current &&
+		    map[mip->ra_index].br_blockcount >= mp->m_dirblkfsbs) {
+			xfs_buf_readahead(mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(mp,
+					map[mip->ra_index].br_startblock +
+							mip->ra_offset),
+				(int)BTOBB(mp->m_dirblksize));
+			mip->ra_current = i;
+		}
+
+		/*
+		 * Read-ahead a non-contiguous directory block.  This doesn't
+		 * use our mapping, but this is a very rare case.
+		 */
+		else if (i > mip->ra_current) {
+			xfs_da_reada_buf(NULL, dp,
+					map[mip->ra_index].br_startoff +
+							mip->ra_offset,
+					XFS_DATA_FORK);
+			mip->ra_current = i;
+		}
+
+		/*
+		 * Advance offset through the mapping table.
+		 */
+		for (j = 0; j < mp->m_dirblkfsbs; j++) {
+			/*
+			 * The rest of this extent but not more than a dir
+			 * block.
+			 */
+			length = min_t(int, mp->m_dirblkfsbs,
+					map[mip->ra_index].br_blockcount -
+							mip->ra_offset);
+			j += length;
+			mip->ra_offset += length;
+
+			/*
+			 * Advance to the next mapping if this one is used up.
+			 */
+			if (mip->ra_offset == map[mip->ra_index].br_blockcount) {
+				mip->ra_offset = 0;
+				mip->ra_index++;
+			}
+		}
+	}
+
+out:
+	*bpp = bp;
+	return error;
+}
+
 /*
  * Getdents (readdir) for leaf and node directories.
  * This reads the data blocks only, so is the same for both forms.
@@ -771,30 +983,18 @@ xfs_dir2_leaf_getdents(
 	xfs_off_t		*offset,
 	filldir_t		filldir)
 {
-	struct xfs_buf		*bp;		/* data block buffer */
-	int			byteoff;	/* offset in current block */
-	xfs_dir2_db_t		curdb;		/* db for current block */
-	xfs_dir2_off_t		curoff;		/* current overall offset */
+	struct xfs_buf		*bp = NULL;	/* data block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
 	int			error = 0;	/* error return value */
-	int			i;		/* temporary loop index */
-	int			j;		/* temporary loop index */
 	int			length;		/* temporary length value */
-	xfs_bmbt_irec_t		*map;		/* map vector for blocks */
-	xfs_extlen_t		map_blocks;	/* number of fsbs in map */
-	xfs_dablk_t		map_off;	/* last mapped file offset */
-	int			map_size;	/* total entries in *map */
-	int			map_valid;	/* valid entries in *map */
 	xfs_mount_t		*mp;		/* filesystem mount point */
+	int			byteoff;	/* offset in current block */
+	xfs_dir2_off_t		curoff;		/* current overall offset */
 	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
-	int			nmap;		/* mappings to ask xfs_bmapi */
 	char			*ptr = NULL;	/* pointer to current data */
-	int			ra_current;	/* number of read-ahead blks */
-	int			ra_index;	/* *map index for read-ahead */
-	int			ra_offset;	/* map entry offset for ra */
-	int			ra_want;	/* readahead count wanted */
+	struct xfs_dir2_leaf_map_info *map_info;
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -810,10 +1010,12 @@ xfs_dir2_leaf_getdents(
 	 * buffer size, the directory block size, and the filesystem
 	 * block size.
 	 */
-	map_size = howmany(bufsize + mp->m_dirblksize, mp->m_sb.sb_blocksize);
-	map = kmem_alloc(map_size * sizeof(*map), KM_SLEEP);
-	map_valid = ra_index = ra_offset = ra_current = map_blocks = 0;
-	bp = NULL;
+	length = howmany(bufsize + mp->m_dirblksize,
+				     mp->m_sb.sb_blocksize);
+	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
+				(length * sizeof(struct xfs_bmbt_irec)),
+			       KM_SLEEP);
+	map_info->map_size = length;
 
 	/*
 	 * Inside the loop we keep the main offset value as a byte offset
@@ -825,7 +1027,9 @@ xfs_dir2_leaf_getdents(
 	 * Force this conversion through db so we truncate the offset
 	 * down to get the start of the data block.
 	 */
-	map_off = xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, curoff));
+	map_info->map_off = xfs_dir2_db_to_da(mp,
+					      xfs_dir2_byte_to_db(mp, curoff));
+
 	/*
 	 * Loop over directory entries until we reach the end offset.
 	 * Get more blocks and readahead as necessary.
@@ -836,190 +1040,16 @@ xfs_dir2_leaf_getdents(
 		 * current buffer, need to get another one.
 		 */
 		if (!bp || ptr >= (char *)bp->b_addr + mp->m_dirblksize) {
-			/*
-			 * If we have a buffer, we need to release it and
-			 * take it out of the mapping.
-			 */
-			if (bp) {
-				xfs_trans_brelse(NULL, bp);
-				bp = NULL;
-				map_blocks -= mp->m_dirblkfsbs;
-				/*
-				 * Loop to get rid of the extents for the
-				 * directory block.
-				 */
-				for (i = mp->m_dirblkfsbs; i > 0; ) {
-					j = MIN((int)map->br_blockcount, i);
-					map->br_blockcount -= j;
-					map->br_startblock += j;
-					map->br_startoff += j;
-					/*
-					 * If mapping is done, pitch it from
-					 * the table.
-					 */
-					if (!map->br_blockcount && --map_valid)
-						memmove(&map[0], &map[1],
-							sizeof(map[0]) *
-							map_valid);
-					i -= j;
-				}
-			}
-			/*
-			 * Recalculate the readahead blocks wanted.
-			 */
-			ra_want = howmany(bufsize + mp->m_dirblksize,
-					  mp->m_sb.sb_blocksize) - 1;
-			ASSERT(ra_want >= 0);
 
-			/*
-			 * If we don't have as many as we want, and we haven't
-			 * run out of data blocks, get some more mappings.
-			 */
-			if (1 + ra_want > map_blocks &&
-			    map_off <
-			    xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
-				/*
-				 * Get more bmaps, fill in after the ones
-				 * we already have in the table.
-				 */
-				nmap = map_size - map_valid;
-				error = xfs_bmapi_read(dp, map_off,
-					xfs_dir2_byte_to_da(mp,
-						XFS_DIR2_LEAF_OFFSET) - map_off,
-					&map[map_valid], &nmap, 0);
-				/*
-				 * Don't know if we should ignore this or
-				 * try to return an error.
-				 * The trouble with returning errors
-				 * is that readdir will just stop without
-				 * actually passing the error through.
-				 */
-				if (error)
-					break;	/* XXX */
-				/*
-				 * If we got all the mappings we asked for,
-				 * set the final map offset based on the
-				 * last bmap value received.
-				 * Otherwise, we've reached the end.
-				 */
-				if (nmap == map_size - map_valid)
-					map_off =
-					map[map_valid + nmap - 1].br_startoff +
-					map[map_valid + nmap - 1].br_blockcount;
-				else
-					map_off =
-						xfs_dir2_byte_to_da(mp,
-							XFS_DIR2_LEAF_OFFSET);
-				/*
-				 * Look for holes in the mapping, and
-				 * eliminate them.  Count up the valid blocks.
-				 */
-				for (i = map_valid; i < map_valid + nmap; ) {
-					if (map[i].br_startblock ==
-					    HOLESTARTBLOCK) {
-						nmap--;
-						length = map_valid + nmap - i;
-						if (length)
-							memmove(&map[i],
-								&map[i + 1],
-								sizeof(map[i]) *
-								length);
-					} else {
-						map_blocks +=
-							map[i].br_blockcount;
-						i++;
-					}
-				}
-				map_valid += nmap;
-			}
-			/*
-			 * No valid mappings, so no more data blocks.
-			 */
-			if (!map_valid) {
-				curoff = xfs_dir2_da_to_byte(mp, map_off);
+			error = xfs_dir2_leaf_readbuf(dp, bufsize, map_info,
+						      &curoff, &bp);
+			if (error || !map_info->map_valid)
 				break;
-			}
-			/*
-			 * Read the directory block starting at the first
-			 * mapping.
-			 */
-			curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
-			error = xfs_da_read_buf(NULL, dp, map->br_startoff,
-				map->br_blockcount >= mp->m_dirblkfsbs ?
-				    XFS_FSB_TO_DADDR(mp, map->br_startblock) :
-				    -1,
-				&bp, XFS_DATA_FORK);
-			/*
-			 * Should just skip over the data block instead
-			 * of giving up.
-			 */
-			if (error)
-				break;	/* XXX */
-			/*
-			 * Adjust the current amount of read-ahead: we just
-			 * read a block that was previously ra.
-			 */
-			if (ra_current)
-				ra_current -= mp->m_dirblkfsbs;
-			/*
-			 * Do we need more readahead?
-			 */
-			for (ra_index = ra_offset = i = 0;
-			     ra_want > ra_current && i < map_blocks;
-			     i += mp->m_dirblkfsbs) {
-				ASSERT(ra_index < map_valid);
-				/*
-				 * Read-ahead a contiguous directory block.
-				 */
-				if (i > ra_current &&
-				    map[ra_index].br_blockcount >=
-				    mp->m_dirblkfsbs) {
-					xfs_buf_readahead(mp->m_ddev_targp,
-						XFS_FSB_TO_DADDR(mp,
-						   map[ra_index].br_startblock +
-						   ra_offset),
-						(int)BTOBB(mp->m_dirblksize));
-					ra_current = i;
-				}
-				/*
-				 * Read-ahead a non-contiguous directory block.
-				 * This doesn't use our mapping, but this
-				 * is a very rare case.
-				 */
-				else if (i > ra_current) {
-					(void)xfs_da_reada_buf(NULL, dp,
-						map[ra_index].br_startoff +
-						ra_offset, XFS_DATA_FORK);
-					ra_current = i;
-				}
-				/*
-				 * Advance offset through the mapping table.
-				 */
-				for (j = 0; j < mp->m_dirblkfsbs; j++) {
-					/*
-					 * The rest of this extent but not
-					 * more than a dir block.
-					 */
-					length = MIN(mp->m_dirblkfsbs,
-						(int)(map[ra_index].br_blockcount -
-						ra_offset));
-					j += length;
-					ra_offset += length;
-					/*
-					 * Advance to the next mapping if
-					 * this one is used up.
-					 */
-					if (ra_offset ==
-					    map[ra_index].br_blockcount) {
-						ra_offset = 0;
-						ra_index++;
-					}
-				}
-			}
+
 			/*
 			 * Having done a read, we need to set a new offset.
 			 */
-			newoff = xfs_dir2_db_off_to_byte(mp, curdb, 0);
+			newoff = xfs_dir2_db_off_to_byte(mp, map_info->curdb, 0);
 			/*
 			 * Start of the current block.
 			 */
@@ -1030,7 +1060,7 @@ xfs_dir2_leaf_getdents(
 			 */
 			else if (curoff > newoff)
 				ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
-				       curdb);
+				       map_info->curdb);
 			hdr = bp->b_addr;
 			xfs_dir2_data_check(dp, bp);
 			/*
@@ -1113,7 +1143,7 @@ xfs_dir2_leaf_getdents(
 		*offset = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
 		*offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
-	kmem_free(map);
+	kmem_free(map_info);
 	if (bp)
 		xfs_trans_brelse(NULL, bp);
 	return error;
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 9/9] xfs: factor buffer reading from xfs_dir2_leaf_getdents

[Christoph Hellwig]

On Fri, Jun 22, 2012 at 06:50:15PM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> The buffer reading code in xfs_dir2_leaf_getdents is complex and difficult to
> follow due to the readahead and all the context is carries. it is also badly
> indented and so difficult to read. Factor it out into a separate function to
> make it easier to understand and optimise in future patches.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 0/9] xfs: discontiguous directory buffer support

[Dave Chinner]

This is the latest version of the native xfs_buf discontiguous
buffer support series. It has been rebased on 3.5-rc1 and Jan Kara's
buffer initialisation/allocation fix ("Fix overallocation in
xfs_buf_allocate_memory()").

The series introduces Dateh concept of buffer block maps, then
adds APIs for using them, converts the internal xfs_buf method 
implementation to use them exclusively, adds support for
discontiguous buffer log items in transactions, converts
the directory code to use them and finally removes the xfs_dabuf
from the picture.

This greatly simplifies the directory buffer code and avoids
copy-up/copy-down for discontiguous buffers. It also avoids needing
to create and destroy a xfs-dabuf for every directory block that is
read or written, greatly reducing buffer setup and teardown
overhead and memory footprint.

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 6/9] xfs: support discontiguous buffers in the xfs_buf_log_item

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

>From the perspective of the log, we need to keep each segment of a
discontigous buffer in separate buffer format structures. This means log
recovery will recover all the changes on a per segment basis without
requiring any knowledge of the fact that it was logged from a
compound buffer.

To do this, we need to be able to determine what buffer segment any
given offset into the compound buffer sits over. This enables us to
translate the dirty bitmap in the number of separate buffer format
structures required.

We also need to be able to determine the number of bitmap elements
that a given buffer segment has, as this determines the size of the
buffer format structure. Hence we need to be able to determine the
both the start offset into the buffer and the length of a given
segment to be able to calculate this.

With this information, we can preallocate, build and format the
correct log vector array for each segment in a compound buffer to
appear exactly the same as individually logged buffers in the log.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_buf_item.c |  332 +++++++++++++++++++++++++++++++++++--------------
 fs/xfs/xfs_buf_item.h |    2 +
 2 files changed, 243 insertions(+), 91 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 22ce073..465d9cd 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -153,33 +153,25 @@ STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
  * If the XFS_BLI_STALE flag has been set, then log nothing.
  */
 STATIC uint
-xfs_buf_item_size(
-	struct xfs_log_item	*lip)
+xfs_buf_item_size_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_buf_log_format *blfp)
 {
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			nvecs;
 	int			next_bit;
 	int			last_bit;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	if (bip->bli_flags & XFS_BLI_STALE) {
-		/*
-		 * The buffer is stale, so all we need to log
-		 * is the buf log format structure with the
-		 * cancel flag in it.
-		 */
-		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		return 1;
-	}
+	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (last_bit == -1)
+		return 0;
+
+	/*
+	 * initial count for a dirty buffer is 2 vectors - the format structure
+	 * and the first dirty region.
+	 */
+	nvecs = 2;
 
-	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
-	nvecs = 1;
-	last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
-	ASSERT(last_bit != -1);
-	nvecs++;
 	while (last_bit != -1) {
 		/*
 		 * This takes the bit number to start looking from and
@@ -187,16 +179,15 @@ xfs_buf_item_size(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					last_bit + 1);
 		/*
 		 * If we run out of bits, leave the loop,
 		 * else if we find a new set of bits bump the number of vecs,
 		 * else keep scanning the current set of bits.
 		 */
 		if (next_bit == -1) {
-			last_bit = -1;
+			break;
 		} else if (next_bit != last_bit + 1) {
 			last_bit = next_bit;
 			nvecs++;
@@ -210,22 +201,73 @@ xfs_buf_item_size(
 		}
 	}
 
-	trace_xfs_buf_item_size(bip);
 	return nvecs;
 }
 
 /*
- * This is called to fill in the vector of log iovecs for the
- * given log buf item.  It fills the first entry with a buf log
- * format structure, and the rest point to contiguous chunks
- * within the buffer.
+ * This returns the number of log iovecs needed to log the given buf log item.
+ *
+ * It calculates this as 1 iovec for the buf log format structure and 1 for each
+ * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
+ * in a single iovec.
+ *
+ * Discontiguous buffers need a format structure per region that that is being
+ * logged. This makes the changes in the buffer appear to log recovery as though
+ * they came from separate buffers, just like would occur if multiple buffers
+ * were used instead of a single discontiguous buffer. This enables
+ * discontiguous buffers to be in-memory constructs, completely transparent to
+ * what ends up on disk.
+ *
+ * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
+ * format structures.
  */
-STATIC void
-xfs_buf_item_format(
-	struct xfs_log_item	*lip,
-	struct xfs_log_iovec	*vecp)
+STATIC uint
+xfs_buf_item_size(
+	struct xfs_log_item	*lip)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	uint			nvecs;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	if (bip->bli_flags & XFS_BLI_STALE) {
+		/*
+		 * The buffer is stale, so all we need to log
+		 * is the buf log format structure with the
+		 * cancel flag in it.
+		 */
+		trace_xfs_buf_item_size_stale(bip);
+		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		return bip->bli_format_count;
+	}
+
+	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
+
+	/*
+	 * the vector count is based on the number of buffer vectors we have
+	 * dirty bits in. This will only be greater than one when we have a
+	 * compound buffer with more than one segment dirty. Hence for compound
+	 * buffers we need to track which segment the dirty bits correspond to,
+	 * and when we move from one segment to the next increment the vector
+	 * count for the extra buf log format structure that will need to be
+	 * written.
+	 */
+	nvecs = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		nvecs += xfs_buf_item_size_segment(bip, &bip->bli_formats[i]);
+	}
+
+	trace_xfs_buf_item_size(bip);
+	return nvecs;
+}
+
+static struct xfs_log_iovec *
+xfs_buf_item_format_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_log_iovec	*vecp,
+	uint			offset,
+	struct xfs_buf_log_format *blfp)
+{
 	struct xfs_buf	*bp = bip->bli_buf;
 	uint		base_size;
 	uint		nvecs;
@@ -235,9 +277,8 @@ xfs_buf_item_format(
 	uint		nbits;
 	uint		buffer_offset;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
-	       (bip->bli_flags & XFS_BLI_STALE));
+	/* copy the flags across from the base format item */
+	blfp->blf_flags = bip->bli_format.blf_flags;
 
 	/*
 	 * Base size is the actual size of the ondisk structure - it reflects
@@ -248,26 +289,12 @@ xfs_buf_item_format(
 	base_size = sizeof(struct xfs_buf_log_format) -
 		    ((XFS_BLF_DATAMAP_SIZE - bip->bli_format.blf_map_size) *
 								sizeof(uint));
-	vecp->i_addr = &bip->bli_format;
+	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
 	vecp++;
 	nvecs = 1;
 
-	/*
-	 * If it is an inode buffer, transfer the in-memory state to the
-	 * format flags and clear the in-memory state. We do not transfer
-	 * this state if the inode buffer allocation has not yet been committed
-	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
-	 * correct replay of the inode allocation.
-	 */
-	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
-		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
-		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
-		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
-	}
-
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		/*
 		 * The buffer is stale, so all we need to log
@@ -275,16 +302,15 @@ xfs_buf_item_format(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_format_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		bip->bli_format.blf_size = nvecs;
-		return;
+		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
+		blfp->blf_size = nvecs;
+		return vecp;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	ASSERT(first_bit != -1);
 	last_bit = first_bit;
 	nbits = 1;
@@ -295,9 +321,8 @@ xfs_buf_item_format(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 (uint)last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)last_bit + 1);
 		/*
 		 * If we run out of bits fill in the last iovec and get
 		 * out of the loop.
@@ -308,14 +333,14 @@ xfs_buf_item_format(
 		 * keep counting and scanning.
 		 */
 		if (next_bit == -1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
 			nvecs++;
 			break;
 		} else if (next_bit != last_bit + 1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
@@ -324,14 +349,17 @@ xfs_buf_item_format(
 			first_bit = next_bit;
 			last_bit = next_bit;
 			nbits = 1;
-		} else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
-			   (xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
+		} else if (xfs_buf_offset(bp, offset +
+					      (next_bit << XFS_BLF_SHIFT)) !=
+			   (xfs_buf_offset(bp, offset +
+					       (last_bit << XFS_BLF_SHIFT)) +
 			    XFS_BLF_CHUNK)) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/* You would think we need to bump the nvecs here too, but we do not
+/*
+ * You would think we need to bump the nvecs here too, but we do not
  * this number is used by recovery, and it gets confused by the boundary
  * split here
  *			nvecs++;
@@ -346,6 +374,48 @@ xfs_buf_item_format(
 		}
 	}
 	bip->bli_format.blf_size = nvecs;
+	return vecp;
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the
+ * given log buf item.  It fills the first entry with a buf log
+ * format structure, and the rest point to contiguous chunks
+ * within the buffer.
+ */
+STATIC void
+xfs_buf_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_iovec	*vecp)
+{
+	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	struct xfs_buf		*bp = bip->bli_buf;
+	uint			offset = 0;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+	       (bip->bli_flags & XFS_BLI_STALE));
+
+	/*
+	 * If it is an inode buffer, transfer the in-memory state to the
+	 * format flags and clear the in-memory state. We do not transfer
+	 * this state if the inode buffer allocation has not yet been committed
+	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
+	 * correct replay of the inode allocation.
+	 */
+	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
+		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+		      xfs_log_item_in_current_chkpt(lip)))
+			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+	}
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		vecp = xfs_buf_item_format_segment(bip, vecp, offset,
+						&bip->bli_formats[i]);
+		offset += bp->b_maps[i].bm_len;
+	}
 
 	/*
 	 * Check to make sure everything is consistent.
@@ -621,6 +691,35 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_committing = xfs_buf_item_committing
 };
 
+STATIC int
+xfs_buf_item_get_format(
+	struct xfs_buf_log_item	*bip,
+	int			count)
+{
+	ASSERT(bip->bli_formats == NULL);
+	bip->bli_format_count = count;
+
+	if (count == 1) {
+		bip->bli_formats = &bip->bli_format;
+		return 0;
+	}
+
+	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
+				KM_SLEEP);
+	if (!bip->bli_formats)
+		return ENOMEM;
+	return 0;
+}
+
+STATIC void
+xfs_buf_item_free_format(
+	struct xfs_buf_log_item	*bip)
+{
+	if (bip->bli_formats != &bip->bli_format) {
+		kmem_free(bip->bli_formats);
+		bip->bli_formats = NULL;
+	}
+}
 
 /*
  * Allocate a new buf log item to go with the given buffer.
@@ -638,6 +737,8 @@ xfs_buf_item_init(
 	xfs_buf_log_item_t	*bip;
 	int			chunks;
 	int			map_size;
+	int			error;
+	int			i;
 
 	/*
 	 * Check to see if there is already a buf log item for
@@ -649,25 +750,33 @@ xfs_buf_item_init(
 	if (lip != NULL && lip->li_type == XFS_LI_BUF)
 		return;
 
-	/*
-	 * chunks is the number of XFS_BLF_CHUNK size pieces
-	 * the buffer can be divided into. Make sure not to
-	 * truncate any pieces.  map_size is the size of the
-	 * bitmap needed to describe the chunks of the buffer.
-	 */
-	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
-								XFS_BLF_SHIFT);
-	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
-
-	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
-						    KM_SLEEP);
+	bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
 	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
 	bip->bli_buf = bp;
 	xfs_buf_hold(bp);
-	bip->bli_format.blf_type = XFS_LI_BUF;
-	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)bp->b_length;
-	bip->bli_format.blf_map_size = map_size;
+
+	/*
+	 * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
+	 * can be divided into. Make sure not to truncate any pieces.
+	 * map_size is the size of the bitmap needed to describe the
+	 * chunks of the buffer.
+	 *
+	 * Discontiguous buffer support follows the layout of the underlying
+	 * buffer. This makes the implementation as simple as possible.
+	 */
+	error = xfs_buf_item_get_format(bip, bp->b_map_count);
+	ASSERT(error == 0);
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+				      XFS_BLF_CHUNK);
+		map_size = DIV_ROUND_UP(chunks, NBWORD);
+
+		bip->bli_formats[i].blf_type = XFS_LI_BUF;
+		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
+		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
+		bip->bli_formats[i].blf_map_size = map_size;
+	}
 
 #ifdef XFS_TRANS_DEBUG
 	/*
@@ -698,10 +807,11 @@ xfs_buf_item_init(
  * item's bitmap.
  */
 void
-xfs_buf_item_log(
-	xfs_buf_log_item_t	*bip,
+xfs_buf_item_log_segment(
+	struct xfs_buf_log_item	*bip,
 	uint			first,
-	uint			last)
+	uint			last,
+	uint			*map)
 {
 	uint		first_bit;
 	uint		last_bit;
@@ -714,12 +824,6 @@ xfs_buf_item_log(
 	uint		mask;
 
 	/*
-	 * Mark the item as having some dirty data for
-	 * quick reference in xfs_buf_item_dirty.
-	 */
-	bip->bli_flags |= XFS_BLI_DIRTY;
-
-	/*
 	 * Convert byte offsets to bit numbers.
 	 */
 	first_bit = first >> XFS_BLF_SHIFT;
@@ -735,7 +839,7 @@ xfs_buf_item_log(
 	 * to set a bit in.
 	 */
 	word_num = first_bit >> BIT_TO_WORD_SHIFT;
-	wordp = &(bip->bli_format.blf_data_map[word_num]);
+	wordp = &map[word_num];
 
 	/*
 	 * Calculate the starting bit in the first word.
@@ -782,6 +886,51 @@ xfs_buf_item_log(
 	xfs_buf_item_log_debug(bip, first, last);
 }
 
+/*
+ * Mark bytes first through last inclusive as dirty in the buf
+ * item's bitmap.
+ */
+void
+xfs_buf_item_log(
+	xfs_buf_log_item_t	*bip,
+	uint			first,
+	uint			last)
+{
+	int			i;
+	uint			start;
+	uint			end;
+	struct xfs_buf		*bp = bip->bli_buf;
+
+	/*
+	 * Mark the item as having some dirty data for
+	 * quick reference in xfs_buf_item_dirty.
+	 */
+	bip->bli_flags |= XFS_BLI_DIRTY;
+
+	/*
+	 * walk each buffer segment and mark them dirty appropriately.
+	 */
+	start = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (start > last)
+			break;
+		end = start + BBTOB(bp->b_maps[i].bm_len);
+		if (first > end) {
+			start += BBTOB(bp->b_maps[i].bm_len);
+			continue;
+		}
+		if (first < start)
+			first = start;
+		if (end > last)
+			end = last;
+
+		xfs_buf_item_log_segment(bip, first, end,
+					 &bip->bli_formats[i].blf_data_map[0]);
+
+		start += bp->b_maps[i].bm_len;
+	}
+}
+
 
 /*
  * Return 1 if the buffer has some data that has been logged (at any
@@ -803,6 +952,7 @@ xfs_buf_item_free(
 	kmem_free(bip->bli_logged);
 #endif /* XFS_TRANS_DEBUG */
 
+	xfs_buf_item_free_format(bip);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index ff26867..6850f49 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -102,6 +102,8 @@ typedef struct xfs_buf_log_item {
 	char			*bli_orig;	/* original buffer copy */
 	char			*bli_logged;	/* bytes logged (bitmap) */
 #endif
+	int			bli_format_count;	/* count of headers */
+	struct xfs_buf_log_format *bli_formats;	/* array of in-log header ptrs */
 	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
-- 
1.7.10

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 6/9] xfs: support discontiguous buffers in the xfs_buf_log_item

[Christoph Hellwig]

Looks good,


Reviewed-by: Christoph Hellwig <hch@lst.de>

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs