Merge tag 'xfs-for-linus-v3.13-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs update from Ben Myers:
 "For 3.13-rc1 we have an eclectic assortment of bugfixes, cleanups, and
  refactoring.  Bugfixes that stand out are the fix for the AGF/AGI
  deadlock, incore extent list fixes, verifier fixes for v4 superblocks
  and growfs, and memory leaks.  There are some asserts, warnings, and
  strings that were cleaned up.  There was further rearrangement of code
  to make libxfs and the kernel sync up more easily, differences between
  v2 and v3 directory code were abstracted using an ops vector,
  xfs_inactive was reworked, and the preallocation/hole punching code
  was refactored.

   - simplify kmem_zone_zalloc
   - add traces for AGF/AGI read ops
   - add additional AIL traces
   - fix xfs_remove AGF vs AGI deadlock
   - fix the extent count of new incore extent page in the indirection
     array
   - don't fail bad secondary superblocks verification on v4 filesystems
     due to unzeroed bits after v4 fields
   - fix possible NULL dereference in xlog_verify_iclog
   - remove redundant assert in xfs_dir2_leafn_split
   - prevent stack overflows from page cache allocation
   - fix some sparse warnings
   - fix directory block format verifier to check the leaf entry count
   - abstract the differences in dir2/dir3 via an ops vector
   - continue process of reorganization to make libxfs/kernel code
     merges easier
   - refactor the preallocation and hole punching code
   - fix for growfs and verifiers
   - remove unnecessary scary corruption error when probing non-xfs
     filesystems
   - remove extra newlines from strings passed to printk
   - prevent deadlock trying to cover an active log
   - rework xfs_inactive()
   - add the inode directory type support to XFS_IOC_FSGEOM
   - cleanup (remove) usage of is_bad_inode
   - fix miscalculation in xfs_iext_realloc_direct which results in
     oversized direct extent list
   - remove unnecessary count arg to xfs_iomap_write_allocate
   - fix memory leak in xlog_recover_add_to_trans
   - check superblock instead of block magic to determine if dtype field
     is present
   - fix lockdep annotation due to project quotas
   - fix regression in xfs_node_toosmall which can lead to incorrect
     directory btree node collapse
   - make log recovery verify filesystem uuid of recovering blocks
   - fix XFS_IOC_FREE_EOFBLOCKS definition
   - remove invalid assert in xfs_inode_free
   - fix for AIL lock regression"

* tag 'xfs-for-linus-v3.13-rc1' of git://oss.sgi.com/xfs/xfs: (49 commits)
  xfs: simplify kmem_{zone_}zalloc
  xfs: add tracepoints to AGF/AGI read operations
  xfs: trace AIL manipulations
  xfs: xfs_remove deadlocks due to inverted AGF vs AGI lock ordering
  xfs: fix the extent count when allocating an new indirection array entry
  xfs: be more forgiving of a v4 secondary sb w/ junk in v5 fields
  xfs: fix possible NULL dereference in xlog_verify_iclog
  xfs:xfs_dir2_node.c: pointer use before check for null
  xfs: prevent stack overflows from page cache allocation
  xfs: fix static and extern sparse warnings
  xfs: validity check the directory block leaf entry count
  xfs: make dir2 ftype offset pointers explicit
  xfs: convert directory vector functions to constants
  xfs: convert directory vector functions to constants
  xfs: vectorise encoding/decoding directory headers
  xfs: vectorise DA btree operations
  xfs: vectorise directory leaf operations
  xfs: vectorise directory data operations part 2
  xfs: vectorise directory data operations
  xfs: vectorise remaining shortform dir2 ops
  ...

fs/xfs/Makefile

@@ -66,12 +66,14 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_bmap_btree.o \
 				   xfs_btree.o \
 				   xfs_da_btree.o \
+				   xfs_da_format.o \
 				   xfs_dir2.o \
 				   xfs_dir2_block.o \
 				   xfs_dir2_data.o \
 				   xfs_dir2_leaf.o \
 				   xfs_dir2_node.o \
 				   xfs_dir2_sf.o \
+				   xfs_dquot_buf.o \
 				   xfs_ialloc.o \
 				   xfs_ialloc_btree.o \
 				   xfs_icreate_item.o \
@@ -103,7 +105,11 @@ xfs-$(CONFIG_XFS_QUOTA)		+= xfs_dquot.o \
 				   xfs_qm_bhv.o \
 				   xfs_qm.o \
 				   xfs_quotaops.o
-xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
+
+# xfs_rtbitmap is shared with libxfs
+xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o \
+				   xfs_rtbitmap.o
+
 xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_PROC_FS)		+= xfs_stats.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o

fs/xfs/kmem.c

@@ -62,17 +62,6 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
 	} while (1);
 }
 
-void *
-kmem_zalloc(size_t size, xfs_km_flags_t flags)
-{
-	void	*ptr;
-
-	ptr = kmem_alloc(size, flags);
-	if (ptr)
-		memset((char *)ptr, 0, (int)size);
-	return ptr;
-}
-
 void *
 kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 {
@@ -128,14 +117,3 @@ kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
-
-void *
-kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
-	void	*ptr;
-
-	ptr = kmem_zone_alloc(zone, flags);
-	if (ptr)
-		memset((char *)ptr, 0, kmem_cache_size(zone));
-	return ptr;
-}

fs/xfs/kmem.h

@@ -32,6 +32,7 @@ typedef unsigned __bitwise xfs_km_flags_t;
 #define KM_NOSLEEP	((__force xfs_km_flags_t)0x0002u)
 #define KM_NOFS		((__force xfs_km_flags_t)0x0004u)
 #define KM_MAYFAIL	((__force xfs_km_flags_t)0x0008u)
+#define KM_ZERO		((__force xfs_km_flags_t)0x0010u)
 
 /*
  * We use a special process flag to avoid recursive callbacks into
@@ -43,7 +44,7 @@ kmem_flags_convert(xfs_km_flags_t flags)
 {
 	gfp_t	lflags;
 
-	BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL));
+	BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL|KM_ZERO));
 
 	if (flags & KM_NOSLEEP) {
 		lflags = GFP_ATOMIC | __GFP_NOWARN;
@@ -52,11 +53,14 @@ kmem_flags_convert(xfs_km_flags_t flags)
 		if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
 			lflags &= ~__GFP_FS;
 	}
+
+	if (flags & KM_ZERO)
+		lflags |= __GFP_ZERO;
+
 	return lflags;
 }
 
 extern void *kmem_alloc(size_t, xfs_km_flags_t);
-extern void *kmem_zalloc(size_t, xfs_km_flags_t);
 extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t);
 extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t);
 extern void  kmem_free(const void *);
@@ -64,6 +68,12 @@ extern void  kmem_free(const void *);
 
 extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
 
+static inline void *
+kmem_zalloc(size_t size, xfs_km_flags_t flags)
+{
+	return kmem_alloc(size, flags | KM_ZERO);
+}
+
 /*
  * Zone interfaces
  */
@@ -102,6 +112,11 @@ kmem_zone_destroy(kmem_zone_t *zone)
 }
 
 extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t);
-extern void *kmem_zone_zalloc(kmem_zone_t *, xfs_km_flags_t);
+
+static inline void *
+kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
+{
+	return kmem_zone_alloc(zone, flags | KM_ZERO);
+}
 
 #endif /* __XFS_SUPPORT_KMEM_H__ */

fs/xfs/xfs_acl.c

@@ -16,15 +16,15 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
-#include "xfs_acl.h"
-#include "xfs_attr.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_inode.h"
 #include "xfs_ag.h"
 #include "xfs_sb.h"
 #include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_acl.h"
+#include "xfs_attr.h"
 #include "xfs_trace.h"
 #include <linux/slab.h>
 #include <linux/xattr.h>

fs/xfs/xfs_ag.h

@@ -128,8 +128,6 @@ typedef struct xfs_agf {
 extern int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-
 /*
  * Size of the unlinked inode hash table in the agi.
  */
@@ -191,8 +189,6 @@ typedef struct xfs_agi {
 extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 				xfs_agnumber_t agno, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 /*
  * The third a.g. block contains the a.g. freelist, an array
  * of block pointers to blocks owned by the allocation btree code.

fs/xfs/xfs_alloc.c

@@ -17,25 +17,25 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_extent_busy.h"
 #include "xfs_error.h"
 #include "xfs_cksum.h"
 #include "xfs_trace.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_log.h"
 
 struct workqueue_struct *xfs_alloc_wq;
 
@@ -2294,6 +2294,8 @@ xfs_read_agf(
 {
 	int		error;
 
+	trace_xfs_read_agf(mp, agno);
+
 	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
@@ -2324,8 +2326,9 @@ xfs_alloc_read_agf(
 	struct xfs_perag	*pag;		/* per allocation group data */
 	int			error;
 
-	ASSERT(agno != NULLAGNUMBER);
+	trace_xfs_alloc_read_agf(mp, agno);
 
+	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_read_agf(mp, tp, agno,
 			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
 			bpp);

fs/xfs/xfs_alloc.h

@@ -231,7 +231,4 @@ xfs_alloc_get_rec(
 	xfs_extlen_t		*len,	/* output: length of extent */
 	int			*stat);	/* output: success/failure */
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-extern const struct xfs_buf_ops xfs_agfl_buf_ops;
-
 #endif	/* __XFS_ALLOC_H__ */

fs/xfs/xfs_alloc_btree.c

@@ -17,23 +17,21 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_extent_busy.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_trans.h"
 
 
 STATIC struct xfs_btree_cur *

fs/xfs/xfs_alloc_btree.h

@@ -26,39 +26,6 @@ struct xfs_buf;
 struct xfs_btree_cur;
 struct xfs_mount;
 
-/*
- * There are two on-disk btrees, one sorted by blockno and one sorted
- * by blockcount and blockno.  All blocks look the same to make the code
- * simpler; if we have time later, we'll make the optimizations.
- */
-#define	XFS_ABTB_MAGIC		0x41425442	/* 'ABTB' for bno tree */
-#define	XFS_ABTB_CRC_MAGIC	0x41423342	/* 'AB3B' */
-#define	XFS_ABTC_MAGIC		0x41425443	/* 'ABTC' for cnt tree */
-#define	XFS_ABTC_CRC_MAGIC	0x41423343	/* 'AB3C' */
-
-/*
- * Data record/key structure
- */
-typedef struct xfs_alloc_rec {
-	__be32		ar_startblock;	/* starting block number */
-	__be32		ar_blockcount;	/* count of free blocks */
-} xfs_alloc_rec_t, xfs_alloc_key_t;
-
-typedef struct xfs_alloc_rec_incore {
-	xfs_agblock_t	ar_startblock;	/* starting block number */
-	xfs_extlen_t	ar_blockcount;	/* count of free blocks */
-} xfs_alloc_rec_incore_t;
-
-/* btree pointer type */
-typedef __be32 xfs_alloc_ptr_t;
-
-/*
- * Block numbers in the AG:
- * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
- */
-#define	XFS_BNO_BLOCK(mp)	((xfs_agblock_t)(XFS_AGFL_BLOCK(mp) + 1))
-#define	XFS_CNT_BLOCK(mp)	((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))
-
 /*
  * Btree block header size depends on a superblock flag.
  */
@@ -95,6 +62,4 @@ extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
 		xfs_agnumber_t, xfs_btnum_t);
 extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_allocbt_buf_ops;
-
 #endif	/* __XFS_ALLOC_BTREE_H__ */

fs/xfs/xfs_aops.c

@@ -16,14 +16,15 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
-#include "xfs_log.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_trans.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
@@ -31,6 +32,8 @@
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dinode.h"
 #include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
@@ -333,7 +336,7 @@ xfs_map_blocks(
 
 	if (type == XFS_IO_DELALLOC &&
 	    (!nimaps || isnullstartblock(imap->br_startblock))) {
-		error = xfs_iomap_write_allocate(ip, offset, count, imap);
+		error = xfs_iomap_write_allocate(ip, offset, imap);
 		if (!error)
 			trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
 		return -XFS_ERROR(error);
@@ -1569,8 +1572,7 @@ xfs_vm_write_begin(
 
 	ASSERT(len <= PAGE_CACHE_SIZE);
 
-	page = grab_cache_page_write_begin(mapping, index,
-					   flags | AOP_FLAG_NOFS);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 

fs/xfs/xfs_attr.c

@@ -17,23 +17,24 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_attr.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_attr_remote.h"
@@ -41,6 +42,7 @@
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_trace.h"
+#include "xfs_dinode.h"
 
 /*
  * xfs_attr.c

fs/xfs/xfs_attr_inactive.c

@@ -18,22 +18,20 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
+#include "xfs_inode.h"
 #include "xfs_alloc.h"
-#include "xfs_btree.h"
 #include "xfs_attr_remote.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_attr.h"
@@ -41,7 +39,8 @@
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_trace.h"
-#include "xfs_trans_priv.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
 
 /*
  * Look at all the extents for this logical region,
@@ -232,13 +231,13 @@ xfs_attr3_node_inactive(
 	}
 
 	node = bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&ichdr, node);
+	dp->d_ops->node_hdr_from_disk(&ichdr, node);
 	parent_blkno = bp->b_bn;
 	if (!ichdr.count) {
 		xfs_trans_brelse(*trans, bp);
 		return 0;
 	}
-	btree = xfs_da3_node_tree_p(node);
+	btree = dp->d_ops->node_tree_p(node);
 	child_fsb = be32_to_cpu(btree[0].before);
 	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 

fs/xfs/xfs_attr_leaf.c

@@ -18,32 +18,31 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_attr_remote.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
 #include "xfs_attr.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
 
 
 /*
@@ -918,8 +917,8 @@ xfs_attr3_leaf_to_node(
 	if (error)
 		goto out;
 	node = bp1->b_addr;
-	xfs_da3_node_hdr_from_disk(&icnodehdr, node);
-	btree = xfs_da3_node_tree_p(node);
+	dp->d_ops->node_hdr_from_disk(&icnodehdr, node);
+	btree = dp->d_ops->node_tree_p(node);
 
 	leaf = bp2->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(&icleafhdr, leaf);
@@ -929,7 +928,7 @@ xfs_attr3_leaf_to_node(
 	btree[0].hashval = entries[icleafhdr.count - 1].hashval;
 	btree[0].before = cpu_to_be32(blkno);
 	icnodehdr.count = 1;
-	xfs_da3_node_hdr_to_disk(node, &icnodehdr);
+	dp->d_ops->node_hdr_to_disk(node, &icnodehdr);
 	xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(mp) - 1);
 	error = 0;
 out:

fs/xfs/xfs_attr_leaf.h

@@ -19,16 +19,6 @@
 #ifndef __XFS_ATTR_LEAF_H__
 #define	__XFS_ATTR_LEAF_H__
 
-/*
- * Attribute storage layout, internal structure, access macros, etc.
- *
- * Attribute lists are structured around Btrees where all the data
- * elements are in the leaf nodes.  Attribute names are hashed into an int,
- * then that int is used as the index into the Btree.  Since the hashval
- * of an attribute name may not be unique, we may have duplicate keys.  The
- * internal links in the Btree are logical block offsets into the file.
- */
-
 struct attrlist;
 struct attrlist_cursor_kern;
 struct xfs_attr_list_context;
@@ -38,226 +28,6 @@ struct xfs_da_state_blk;
 struct xfs_inode;
 struct xfs_trans;
 
-/*========================================================================
- * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
-/*
- * This is the structure of the leaf nodes in the Btree.
- *
- * Struct leaf_entry's are packed from the top.  Name/values grow from the
- * bottom but are not packed.  The freemap contains run-length-encoded entries
- * for the free bytes after the leaf_entry's, but only the N largest such,
- * smaller runs are dropped.  When the freemap doesn't show enough space
- * for an allocation, we compact the name/value area and try again.  If we
- * still don't have enough space, then we have to split the block.  The
- * name/value structs (both local and remote versions) must be 32bit aligned.
- *
- * Since we have duplicate hash keys, for each key that matches, compare
- * the actual name string.  The root and intermediate node search always
- * takes the first-in-the-block key match found, so we should only have
- * to work "forw"ard.  If none matches, continue with the "forw"ard leaf
- * nodes until the hash key changes or the attribute name is found.
- *
- * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
- * the leaf_entry.  The namespaces are independent only because we also look
- * at the namespace bit when we are looking for a matching attribute name.
- *
- * We also store an "incomplete" bit in the leaf_entry.  It shows that an
- * attribute is in the middle of being created and should not be shown to
- * the user if we crash during the time that the bit is set.  We clear the
- * bit when we have finished setting up the attribute.  We do this because
- * we cannot create some large attributes inside a single transaction, and we
- * need some indication that we weren't finished if we crash in the middle.
- */
-#define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
-
-typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
-	__be16	base;			  /* base of free region */
-	__be16	size;			  /* length of free region */
-} xfs_attr_leaf_map_t;
-
-typedef struct xfs_attr_leaf_hdr {	/* constant-structure header block */
-	xfs_da_blkinfo_t info;		/* block type, links, etc. */
-	__be16	count;			/* count of active leaf_entry's */
-	__be16	usedbytes;		/* num bytes of names/values stored */
-	__be16	firstused;		/* first used byte in name area */
-	__u8	holes;			/* != 0 if blk needs compaction */
-	__u8	pad1;
-	xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
-					/* N largest free regions */
-} xfs_attr_leaf_hdr_t;
-
-typedef struct xfs_attr_leaf_entry {	/* sorted on key, not name */
-	__be32	hashval;		/* hash value of name */
-	__be16	nameidx;		/* index into buffer of name/value */
-	__u8	flags;			/* LOCAL/ROOT/SECURE/INCOMPLETE flag */
-	__u8	pad2;			/* unused pad byte */
-} xfs_attr_leaf_entry_t;
-
-typedef struct xfs_attr_leaf_name_local {
-	__be16	valuelen;		/* number of bytes in value */
-	__u8	namelen;		/* length of name bytes */
-	__u8	nameval[1];		/* name/value bytes */
-} xfs_attr_leaf_name_local_t;
-
-typedef struct xfs_attr_leaf_name_remote {
-	__be32	valueblk;		/* block number of value bytes */
-	__be32	valuelen;		/* number of bytes in value */
-	__u8	namelen;		/* length of name bytes */
-	__u8	name[1];		/* name bytes */
-} xfs_attr_leaf_name_remote_t;
-
-typedef struct xfs_attr_leafblock {
-	xfs_attr_leaf_hdr_t	hdr;	/* constant-structure header block */
-	xfs_attr_leaf_entry_t	entries[1];	/* sorted on key, not name */
-	xfs_attr_leaf_name_local_t namelist;	/* grows from bottom of buf */
-	xfs_attr_leaf_name_remote_t valuelist;	/* grows from bottom of buf */
-} xfs_attr_leafblock_t;
-
-/*
- * CRC enabled leaf structures. Called "version 3" structures to match the
- * version number of the directory and dablk structures for this feature, and
- * attr2 is already taken by the variable inode attribute fork size feature.
- */
-struct xfs_attr3_leaf_hdr {
-	struct xfs_da3_blkinfo	info;
-	__be16			count;
-	__be16			usedbytes;
-	__be16			firstused;
-	__u8			holes;
-	__u8			pad1;
-	struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE];
-	__be32			pad2;		/* 64 bit alignment */
-};
-
-#define XFS_ATTR3_LEAF_CRC_OFF	(offsetof(struct xfs_attr3_leaf_hdr, info.crc))
-
-struct xfs_attr3_leafblock {
-	struct xfs_attr3_leaf_hdr	hdr;
-	struct xfs_attr_leaf_entry	entries[1];
-
-	/*
-	 * The rest of the block contains the following structures after the
-	 * leaf entries, growing from the bottom up. The variables are never
-	 * referenced, the locations accessed purely from helper functions.
-	 *
-	 * struct xfs_attr_leaf_name_local
-	 * struct xfs_attr_leaf_name_remote
-	 */
-};
-
-/*
- * incore, neutral version of the attribute leaf header
- */
-struct xfs_attr3_icleaf_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	usedbytes;
-	__uint16_t	firstused;
-	__u8		holes;
-	struct {
-		__uint16_t	base;
-		__uint16_t	size;
-	} freemap[XFS_ATTR_LEAF_MAPSIZE];
-};
-
-/*
- * Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
- */
-#define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
-#define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
-#define	XFS_ATTR_SECURE_BIT	2	/* limit access to secure attrs */
-#define	XFS_ATTR_INCOMPLETE_BIT	7	/* attr in middle of create/delete */
-#define XFS_ATTR_LOCAL		(1 << XFS_ATTR_LOCAL_BIT)
-#define XFS_ATTR_ROOT		(1 << XFS_ATTR_ROOT_BIT)
-#define XFS_ATTR_SECURE		(1 << XFS_ATTR_SECURE_BIT)
-#define XFS_ATTR_INCOMPLETE	(1 << XFS_ATTR_INCOMPLETE_BIT)
-
-/*
- * Conversion macros for converting namespace bits from argument flags
- * to ondisk flags.
- */
-#define XFS_ATTR_NSP_ARGS_MASK		(ATTR_ROOT | ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK(flags)	((flags) & XFS_ATTR_NSP_ONDISK_MASK)
-#define XFS_ATTR_NSP_ARGS(flags)	((flags) & XFS_ATTR_NSP_ARGS_MASK)
-#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x)	(((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
-					 ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
-#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x)	(((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
-					 ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
-
-/*
- * Alignment for namelist and valuelist entries (since they are mixed
- * there can be only one alignment value)
- */
-#define	XFS_ATTR_LEAF_NAME_ALIGN	((uint)sizeof(xfs_dablk_t))
-
-static inline int
-xfs_attr3_leaf_hdr_size(struct xfs_attr_leafblock *leafp)
-{
-	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
-		return sizeof(struct xfs_attr3_leaf_hdr);
-	return sizeof(struct xfs_attr_leaf_hdr);
-}
-
-static inline struct xfs_attr_leaf_entry *
-xfs_attr3_leaf_entryp(xfs_attr_leafblock_t *leafp)
-{
-	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
-		return &((struct xfs_attr3_leafblock *)leafp)->entries[0];
-	return &leafp->entries[0];
-}
-
-/*
- * Cast typed pointers for "local" and "remote" name/value structs.
- */
-static inline char *
-xfs_attr3_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
-{
-	struct xfs_attr_leaf_entry *entries = xfs_attr3_leaf_entryp(leafp);
-
-	return &((char *)leafp)[be16_to_cpu(entries[idx].nameidx)];
-}
-
-static inline xfs_attr_leaf_name_remote_t *
-xfs_attr3_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
-{
-	return (xfs_attr_leaf_name_remote_t *)xfs_attr3_leaf_name(leafp, idx);
-}
-
-static inline xfs_attr_leaf_name_local_t *
-xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
-{
-	return (xfs_attr_leaf_name_local_t *)xfs_attr3_leaf_name(leafp, idx);
-}
-
-/*
- * Calculate total bytes used (including trailing pad for alignment) for
- * a "local" name/value structure, a "remote" name/value structure, and
- * a pointer which might be either.
- */
-static inline int xfs_attr_leaf_entsize_remote(int nlen)
-{
-	return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
-{
-	return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local_max(int bsize)
-{
-	return (((bsize) >> 1) + ((bsize) >> 2));
-}
-
 /*
  * Used to keep a list of "remote value" extents when unlinking an inode.
  */
@@ -336,6 +106,4 @@ void	xfs_attr3_leaf_hdr_from_disk(struct xfs_attr3_icleaf_hdr *to,
 void	xfs_attr3_leaf_hdr_to_disk(struct xfs_attr_leafblock *to,
 				   struct xfs_attr3_icleaf_hdr *from);
 
-extern const struct xfs_buf_ops xfs_attr3_leaf_buf_ops;
-
 #endif	/* __XFS_ATTR_LEAF_H__ */

fs/xfs/xfs_attr_list.c

@@ -18,31 +18,29 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_attr_remote.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_attr.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
 
 STATIC int
 xfs_attr_shortform_compare(const void *a, const void *b)
@@ -229,6 +227,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	struct xfs_da_node_entry *btree;
 	int error, i;
 	struct xfs_buf *bp;
+	struct xfs_inode	*dp = context->dp;
 
 	trace_xfs_attr_node_list(context);
 
@@ -242,7 +241,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 */
 	bp = NULL;
 	if (cursor->blkno > 0) {
-		error = xfs_da3_node_read(NULL, context->dp, cursor->blkno, -1,
+		error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if ((error != 0) && (error != EFSCORRUPTED))
 			return(error);
@@ -292,7 +291,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		for (;;) {
 			__uint16_t magic;
 
-			error = xfs_da3_node_read(NULL, context->dp,
+			error = xfs_da3_node_read(NULL, dp,
 						      cursor->blkno, -1, &bp,
 						      XFS_ATTR_FORK);
 			if (error)
@@ -312,8 +311,8 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				return XFS_ERROR(EFSCORRUPTED);
 			}
 
-			xfs_da3_node_hdr_from_disk(&nodehdr, node);
-			btree = xfs_da3_node_tree_p(node);
+			dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+			btree = dp->d_ops->node_tree_p(node);
 			for (i = 0; i < nodehdr.count; btree++, i++) {
 				if (cursor->hashval
 						<= be32_to_cpu(btree->hashval)) {
@@ -349,8 +348,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			break;
 		cursor->blkno = leafhdr.forw;
 		xfs_trans_brelse(NULL, bp);
-		error = xfs_attr3_leaf_read(NULL, context->dp, cursor->blkno, -1,
-					   &bp);
+		error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp);
 		if (error)
 			return error;
 	}

fs/xfs/xfs_attr_remote.c

@@ -18,20 +18,19 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_error.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
@@ -42,6 +41,7 @@
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
 #include "xfs_buf_item.h"
+#include "xfs_error.h"
 
 #define ATTR_RMTVALUE_MAPSIZE	1	/* # of map entries at once */
 

fs/xfs/xfs_attr_remote.h

@@ -18,35 +18,6 @@
 #ifndef __XFS_ATTR_REMOTE_H__
 #define	__XFS_ATTR_REMOTE_H__
 
-#define XFS_ATTR3_RMT_MAGIC	0x5841524d	/* XARM */
-
-/*
- * There is one of these headers per filesystem block in a remote attribute.
- * This is done to ensure there is a 1:1 mapping between the attribute value
- * length and the number of blocks needed to store the attribute. This makes the
- * verification of a buffer a little more complex, but greatly simplifies the
- * allocation, reading and writing of these attributes as we don't have to guess
- * the number of blocks needed to store the attribute data.
- */
-struct xfs_attr3_rmt_hdr {
-	__be32	rm_magic;
-	__be32	rm_offset;
-	__be32	rm_bytes;
-	__be32	rm_crc;
-	uuid_t	rm_uuid;
-	__be64	rm_owner;
-	__be64	rm_blkno;
-	__be64	rm_lsn;
-};
-
-#define XFS_ATTR3_RMT_CRC_OFF	offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
-
-#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize)	\
-	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
-			sizeof(struct xfs_attr3_rmt_hdr) : 0))
-
-extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops;
-
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);

fs/xfs/xfs_bit.c

@@ -16,10 +16,8 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_log_format.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_buf_item.h"
 
 /*
  * XFS bit manipulation routines, used in non-realtime code.

fs/xfs/xfs_bmap.c

@@ -17,39 +17,37 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
-#include "xfs_mount.h"
-#include "xfs_itable.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_extfree_item.h"
 #include "xfs_alloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
-#include "xfs_attr_leaf.h"
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_buf_item.h"
-#include "xfs_filestream.h"
 #include "xfs_trace.h"
 #include "xfs_symlink.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_dinode.h"
+#include "xfs_filestream.h"
 
 
 kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -1482,7 +1480,7 @@ xfs_bmap_search_extents(
 		xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
 				"Access to block zero in inode %llu "
 				"start_block: %llx start_off: %llx "
-				"blkcnt: %llx extent-state: %x lastx: %x\n",
+				"blkcnt: %llx extent-state: %x lastx: %x",
 			(unsigned long long)ip->i_ino,
 			(unsigned long long)gotp->br_startblock,
 			(unsigned long long)gotp->br_startoff,

fs/xfs/xfs_bmap_btree.c

@@ -17,27 +17,26 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_alloc.h"
 #include "xfs_btree.h"
-#include "xfs_itable.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_dinode.h"
 
 /*
  * Determine the extent state.

fs/xfs/xfs_bmap_btree.h

@@ -18,94 +18,12 @@
 #ifndef __XFS_BMAP_BTREE_H__
 #define __XFS_BMAP_BTREE_H__
 
-#define XFS_BMAP_MAGIC		0x424d4150	/* 'BMAP' */
-#define XFS_BMAP_CRC_MAGIC	0x424d4133	/* 'BMA3' */
-
 struct xfs_btree_cur;
 struct xfs_btree_block;
 struct xfs_mount;
 struct xfs_inode;
 struct xfs_trans;
 
-/*
- * Bmap root header, on-disk form only.
- */
-typedef struct xfs_bmdr_block {
-	__be16		bb_level;	/* 0 is a leaf */
-	__be16		bb_numrecs;	/* current # of data records */
-} xfs_bmdr_block_t;
-
-/*
- * Bmap btree record and extent descriptor.
- *  l0:63 is an extent flag (value 1 indicates non-normal).
- *  l0:9-62 are startoff.
- *  l0:0-8 and l1:21-63 are startblock.
- *  l1:0-20 are blockcount.
- */
-#define BMBT_EXNTFLAG_BITLEN	1
-#define BMBT_STARTOFF_BITLEN	54
-#define BMBT_STARTBLOCK_BITLEN	52
-#define BMBT_BLOCKCOUNT_BITLEN	21
-
-typedef struct xfs_bmbt_rec {
-	__be64			l0, l1;
-} xfs_bmbt_rec_t;
-
-typedef __uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
-typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
-
-typedef struct xfs_bmbt_rec_host {
-	__uint64_t		l0, l1;
-} xfs_bmbt_rec_host_t;
-
-/*
- * Values and macros for delayed-allocation startblock fields.
- */
-#define STARTBLOCKVALBITS	17
-#define STARTBLOCKMASKBITS	(15 + XFS_BIG_BLKNOS * 20)
-#define DSTARTBLOCKMASKBITS	(15 + 20)
-#define STARTBLOCKMASK		\
-	(((((xfs_fsblock_t)1) << STARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
-#define DSTARTBLOCKMASK		\
-	(((((xfs_dfsbno_t)1) << DSTARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
-
-static inline int isnullstartblock(xfs_fsblock_t x)
-{
-	return ((x) & STARTBLOCKMASK) == STARTBLOCKMASK;
-}
-
-static inline int isnulldstartblock(xfs_dfsbno_t x)
-{
-	return ((x) & DSTARTBLOCKMASK) == DSTARTBLOCKMASK;
-}
-
-static inline xfs_fsblock_t nullstartblock(int k)
-{
-	ASSERT(k < (1 << STARTBLOCKVALBITS));
-	return STARTBLOCKMASK | (k);
-}
-
-static inline xfs_filblks_t startblockval(xfs_fsblock_t x)
-{
-	return (xfs_filblks_t)((x) & ~STARTBLOCKMASK);
-}
-
-/*
- * Possible extent formats.
- */
-typedef enum {
-	XFS_EXTFMT_NOSTATE = 0,
-	XFS_EXTFMT_HASSTATE
-} xfs_exntfmt_t;
-
-/*
- * Possible extent states.
- */
-typedef enum {
-	XFS_EXT_NORM, XFS_EXT_UNWRITTEN,
-	XFS_EXT_DMAPI_OFFLINE, XFS_EXT_INVALID
-} xfs_exntst_t;
-
 /*
  * Extent state and extent format macros.
  */
@@ -114,27 +32,6 @@ typedef enum {
 		XFS_EXTFMT_HASSTATE : XFS_EXTFMT_NOSTATE)
 #define ISUNWRITTEN(x)	((x)->br_state == XFS_EXT_UNWRITTEN)
 
-/*
- * Incore version of above.
- */
-typedef struct xfs_bmbt_irec
-{
-	xfs_fileoff_t	br_startoff;	/* starting file offset */
-	xfs_fsblock_t	br_startblock;	/* starting block number */
-	xfs_filblks_t	br_blockcount;	/* number of blocks */
-	xfs_exntst_t	br_state;	/* extent state */
-} xfs_bmbt_irec_t;
-
-/*
- * Key structure for non-leaf levels of the tree.
- */
-typedef struct xfs_bmbt_key {
-	__be64		br_startoff;	/* starting file offset */
-} xfs_bmbt_key_t, xfs_bmdr_key_t;
-
-/* btree pointer type */
-typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
-
 /*
  * Btree block header size depends on a superblock flag.
  */
@@ -243,6 +140,4 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
-extern const struct xfs_buf_ops xfs_bmbt_buf_ops;
-
 #endif	/* __XFS_BMAP_BTREE_H__ */

fs/xfs/xfs_bmap_util.c

@@ -18,31 +18,31 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_trans.h"
 #include "xfs_extfree_item.h"
 #include "xfs_alloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_log.h"
+#include "xfs_dinode.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -965,32 +965,12 @@ xfs_free_eofblocks(
 	return error;
 }
 
-/*
- * xfs_alloc_file_space()
- *      This routine allocates disk space for the given file.
- *
- *	If alloc_type == 0, this request is for an ALLOCSP type
- *	request which will change the file size.  In this case, no
- *	DMAPI event will be generated by the call.  A TRUNCATE event
- *	will be generated later by xfs_setattr.
- *
- *	If alloc_type != 0, this request is for a RESVSP type
- *	request, and a DMAPI DM_EVENT_WRITE will be generated if the
- *	lower block boundary byte address is less than the file's
- *	length.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-STATIC int
+int
 xfs_alloc_file_space(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	xfs_off_t		offset,
 	xfs_off_t		len,
-	int			alloc_type,
-	int			attr_flags)
+	int			alloc_type)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_off_t		count;
@@ -1232,24 +1212,11 @@ xfs_zero_remaining_bytes(
 	return error;
 }
 
-/*
- * xfs_free_file_space()
- *      This routine frees disk space for the given file.
- *
- *	This routine is only called by xfs_change_file_space
- *	for an UNRESVSP type call.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-STATIC int
+int
 xfs_free_file_space(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len,
-	int			attr_flags)
+	xfs_off_t		len)
 {
 	int			committed;
 	int			done;
@@ -1267,7 +1234,6 @@ xfs_free_file_space(
 	int			rt;
 	xfs_fileoff_t		startoffset_fsb;
 	xfs_trans_t		*tp;
-	int			need_iolock = 1;
 
 	mp = ip->i_mount;
 
@@ -1284,20 +1250,15 @@ xfs_free_file_space(
 	startoffset_fsb	= XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
-	if (attr_flags & XFS_ATTR_NOLOCK)
-		need_iolock = 0;
-	if (need_iolock) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		/* wait for the completion of any pending DIOs */
-		inode_dio_wait(VFS_I(ip));
-	}
+	/* wait for the completion of any pending DIOs */
+	inode_dio_wait(VFS_I(ip));
 
 	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
 	ioffset = offset & ~(rounding - 1);
 	error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 					      ioffset, -1);
 	if (error)
-		goto out_unlock_iolock;
+		goto out;
 	truncate_pagecache_range(VFS_I(ip), ioffset, -1);
 
 	/*
@@ -1311,7 +1272,7 @@ xfs_free_file_space(
 		error = xfs_bmapi_read(ip, startoffset_fsb, 1,
 					&imap, &nimap, 0);
 		if (error)
-			goto out_unlock_iolock;
+			goto out;
 		ASSERT(nimap == 0 || nimap == 1);
 		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
 			xfs_daddr_t	block;
@@ -1326,7 +1287,7 @@ xfs_free_file_space(
 		error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
 					&imap, &nimap, 0);
 		if (error)
-			goto out_unlock_iolock;
+			goto out;
 		ASSERT(nimap == 0 || nimap == 1);
 		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
 			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
@@ -1412,27 +1373,23 @@ xfs_free_file_space(
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	}
 
- out_unlock_iolock:
-	if (need_iolock)
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ out:
 	return error;
 
  error0:
 	xfs_bmap_cancel(&free_list);
  error1:
 	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-	xfs_iunlock(ip, need_iolock ? (XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL) :
-		    XFS_ILOCK_EXCL);
-	return error;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	goto out;
 }
 
 
-STATIC int
+int
 xfs_zero_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len,
-	int			attr_flags)
+	xfs_off_t		len)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	uint			granularity;
@@ -1453,9 +1410,6 @@ xfs_zero_file_space(
 	ASSERT(start_boundary >= offset);
 	ASSERT(end_boundary <= offset + len);
 
-	if (!(attr_flags & XFS_ATTR_NOLOCK))
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
 	if (start_boundary < end_boundary - 1) {
 		/* punch out the page cache over the conversion range */
 		truncate_pagecache_range(VFS_I(ip), start_boundary,
@@ -1463,16 +1417,16 @@ xfs_zero_file_space(
 		/* convert the blocks */
 		error = xfs_alloc_file_space(ip, start_boundary,
 					end_boundary - start_boundary - 1,
-					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT,
-					attr_flags);
+					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT);
 		if (error)
-			goto out_unlock;
+			goto out;
 
 		/* We've handled the interior of the range, now for the edges */
-		if (start_boundary != offset)
+		if (start_boundary != offset) {
 			error = xfs_iozero(ip, offset, start_boundary - offset);
-		if (error)
-			goto out_unlock;
+			if (error)
+				goto out;
+		}
 
 		if (end_boundary != offset + len)
 			error = xfs_iozero(ip, end_boundary,
@@ -1486,196 +1440,11 @@ xfs_zero_file_space(
 		error = xfs_iozero(ip, offset, len);
 	}
 
-out_unlock:
-	if (!(attr_flags & XFS_ATTR_NOLOCK))
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+out:
 	return error;
 
 }
 
-/*
- * xfs_change_file_space()
- *      This routine allocates or frees disk space for the given file.
- *      The user specified parameters are checked for alignment and size
- *      limitations.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-int
-xfs_change_file_space(
-	xfs_inode_t	*ip,
-	int		cmd,
-	xfs_flock64_t	*bf,
-	xfs_off_t	offset,
-	int		attr_flags)
-{
-	xfs_mount_t	*mp = ip->i_mount;
-	int		clrprealloc;
-	int		error;
-	xfs_fsize_t	fsize;
-	int		setprealloc;
-	xfs_off_t	startoffset;
-	xfs_trans_t	*tp;
-	struct iattr	iattr;
-
-	if (!S_ISREG(ip->i_d.di_mode))
-		return XFS_ERROR(EINVAL);
-
-	switch (bf->l_whence) {
-	case 0: /*SEEK_SET*/
-		break;
-	case 1: /*SEEK_CUR*/
-		bf->l_start += offset;
-		break;
-	case 2: /*SEEK_END*/
-		bf->l_start += XFS_ISIZE(ip);
-		break;
-	default:
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * length of <= 0 for resv/unresv/zero is invalid.  length for
-	 * alloc/free is ignored completely and we have no idea what userspace
-	 * might have set it to, so set it to zero to allow range
-	 * checks to pass.
-	 */
-	switch (cmd) {
-	case XFS_IOC_ZERO_RANGE:
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_UNRESVSP64:
-		if (bf->l_len <= 0)
-			return XFS_ERROR(EINVAL);
-		break;
-	default:
-		bf->l_len = 0;
-		break;
-	}
-
-	if (bf->l_start < 0 ||
-	    bf->l_start > mp->m_super->s_maxbytes ||
-	    bf->l_start + bf->l_len < 0 ||
-	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
-		return XFS_ERROR(EINVAL);
-
-	bf->l_whence = 0;
-
-	startoffset = bf->l_start;
-	fsize = XFS_ISIZE(ip);
-
-	setprealloc = clrprealloc = 0;
-	switch (cmd) {
-	case XFS_IOC_ZERO_RANGE:
-		error = xfs_zero_file_space(ip, startoffset, bf->l_len,
-						attr_flags);
-		if (error)
-			return error;
-		setprealloc = 1;
-		break;
-
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_RESVSP64:
-		error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
-						XFS_BMAPI_PREALLOC, attr_flags);
-		if (error)
-			return error;
-		setprealloc = 1;
-		break;
-
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_UNRESVSP64:
-		if ((error = xfs_free_file_space(ip, startoffset, bf->l_len,
-								attr_flags)))
-			return error;
-		break;
-
-	case XFS_IOC_ALLOCSP:
-	case XFS_IOC_ALLOCSP64:
-	case XFS_IOC_FREESP:
-	case XFS_IOC_FREESP64:
-		/*
-		 * These operations actually do IO when extending the file, but
-		 * the allocation is done seperately to the zeroing that is
-		 * done. This set of operations need to be serialised against
-		 * other IO operations, such as truncate and buffered IO. We
-		 * need to take the IOLOCK here to serialise the allocation and
-		 * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
-		 * truncate, direct IO) from racing against the transient
-		 * allocated but not written state we can have here.
-		 */
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		if (startoffset > fsize) {
-			error = xfs_alloc_file_space(ip, fsize,
-					startoffset - fsize, 0,
-					attr_flags | XFS_ATTR_NOLOCK);
-			if (error) {
-				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-				break;
-			}
-		}
-
-		iattr.ia_valid = ATTR_SIZE;
-		iattr.ia_size = startoffset;
-
-		error = xfs_setattr_size(ip, &iattr,
-					 attr_flags | XFS_ATTR_NOLOCK);
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-
-		if (error)
-			return error;
-
-		clrprealloc = 1;
-		break;
-
-	default:
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * update the inode timestamp, mode, and prealloc flag bits
-	 */
-	tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
-	if ((attr_flags & XFS_ATTR_DMI) == 0) {
-		ip->i_d.di_mode &= ~S_ISUID;
-
-		/*
-		 * Note that we don't have to worry about mandatory
-		 * file locking being disabled here because we only
-		 * clear the S_ISGID bit if the Group execute bit is
-		 * on, but if it was on then mandatory locking wouldn't
-		 * have been enabled.
-		 */
-		if (ip->i_d.di_mode & S_IXGRP)
-			ip->i_d.di_mode &= ~S_ISGID;
-
-		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	}
-	if (setprealloc)
-		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
-	else if (clrprealloc)
-		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
-
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	if (attr_flags & XFS_ATTR_SYNC)
-		xfs_trans_set_sync(tp);
-	return xfs_trans_commit(tp, 0);
-}
-
 /*
  * We need to check that the format of the data fork in the temporary inode is
  * valid for the target inode before doing the swap. This is not a problem with

fs/xfs/xfs_bmap_util.h

@@ -93,9 +93,12 @@ int	xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 			     int *is_empty);
 
 /* preallocation and hole punch interface */
-int	xfs_change_file_space(struct xfs_inode *ip, int cmd,
-			      xfs_flock64_t *bf, xfs_off_t offset,
-			      int attr_flags);
+int	xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
+			     xfs_off_t len, int alloc_type);
+int	xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
+			    xfs_off_t len);
+int	xfs_zero_file_space(struct xfs_inode *ip, xfs_off_t offset,
+			    xfs_off_t len);
 
 /* EOF block manipulation functions */
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);

fs/xfs/xfs_btree.c

@@ -17,18 +17,16 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_buf_item.h"
 #include "xfs_btree.h"

fs/xfs/xfs_btree.h

@@ -26,73 +26,6 @@ struct xfs_trans;
 
 extern kmem_zone_t	*xfs_btree_cur_zone;
 
-/*
- * This nonsense is to make -wlint happy.
- */
-#define	XFS_LOOKUP_EQ	((xfs_lookup_t)XFS_LOOKUP_EQi)
-#define	XFS_LOOKUP_LE	((xfs_lookup_t)XFS_LOOKUP_LEi)
-#define	XFS_LOOKUP_GE	((xfs_lookup_t)XFS_LOOKUP_GEi)
-
-#define	XFS_BTNUM_BNO	((xfs_btnum_t)XFS_BTNUM_BNOi)
-#define	XFS_BTNUM_CNT	((xfs_btnum_t)XFS_BTNUM_CNTi)
-#define	XFS_BTNUM_BMAP	((xfs_btnum_t)XFS_BTNUM_BMAPi)
-#define	XFS_BTNUM_INO	((xfs_btnum_t)XFS_BTNUM_INOi)
-
-/*
- * Generic btree header.
- *
- * This is a combination of the actual format used on disk for short and long
- * format btrees.  The first three fields are shared by both format, but the
- * pointers are different and should be used with care.
- *
- * To get the size of the actual short or long form headers please use the size
- * macros below.  Never use sizeof(xfs_btree_block).
- *
- * The blkno, crc, lsn, owner and uuid fields are only available in filesystems
- * with the crc feature bit, and all accesses to them must be conditional on
- * that flag.
- */
-struct xfs_btree_block {
-	__be32		bb_magic;	/* magic number for block type */
-	__be16		bb_level;	/* 0 is a leaf */
-	__be16		bb_numrecs;	/* current # of data records */
-	union {
-		struct {
-			__be32		bb_leftsib;
-			__be32		bb_rightsib;
-
-			__be64		bb_blkno;
-			__be64		bb_lsn;
-			uuid_t		bb_uuid;
-			__be32		bb_owner;
-			__le32		bb_crc;
-		} s;			/* short form pointers */
-		struct	{
-			__be64		bb_leftsib;
-			__be64		bb_rightsib;
-
-			__be64		bb_blkno;
-			__be64		bb_lsn;
-			uuid_t		bb_uuid;
-			__be64		bb_owner;
-			__le32		bb_crc;
-			__be32		bb_pad; /* padding for alignment */
-		} l;			/* long form pointers */
-	} bb_u;				/* rest */
-};
-
-#define XFS_BTREE_SBLOCK_LEN	16	/* size of a short form block */
-#define XFS_BTREE_LBLOCK_LEN	24	/* size of a long form block */
-
-/* sizes of CRC enabled btree blocks */
-#define XFS_BTREE_SBLOCK_CRC_LEN	(XFS_BTREE_SBLOCK_LEN + 40)
-#define XFS_BTREE_LBLOCK_CRC_LEN	(XFS_BTREE_LBLOCK_LEN + 48)
-
-#define XFS_BTREE_SBLOCK_CRC_OFF \
-	offsetof(struct xfs_btree_block, bb_u.s.bb_crc)
-#define XFS_BTREE_LBLOCK_CRC_OFF \
-	offsetof(struct xfs_btree_block, bb_u.l.bb_crc)
-
 /*
  * Generic key, ptr and record wrapper structures.
  *
@@ -118,6 +51,18 @@ union xfs_btree_rec {
 	xfs_inobt_rec_t		inobt;
 };
 
+/*
+ * This nonsense is to make -wlint happy.
+ */
+#define	XFS_LOOKUP_EQ	((xfs_lookup_t)XFS_LOOKUP_EQi)
+#define	XFS_LOOKUP_LE	((xfs_lookup_t)XFS_LOOKUP_LEi)
+#define	XFS_LOOKUP_GE	((xfs_lookup_t)XFS_LOOKUP_GEi)
+
+#define	XFS_BTNUM_BNO	((xfs_btnum_t)XFS_BTNUM_BNOi)
+#define	XFS_BTNUM_CNT	((xfs_btnum_t)XFS_BTNUM_CNTi)
+#define	XFS_BTNUM_BMAP	((xfs_btnum_t)XFS_BTNUM_BMAPi)
+#define	XFS_BTNUM_INO	((xfs_btnum_t)XFS_BTNUM_INOi)
+
 /*
  * For logging record fields.
  */

fs/xfs/xfs_buf.c

@@ -34,12 +34,13 @@
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
 
-#include "xfs_sb.h"
+#include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
-#include "xfs_log.h"
+#include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
 
 static kmem_zone_t *xfs_buf_zone;
 
@@ -590,7 +591,7 @@ found:
 		error = _xfs_buf_map_pages(bp, flags);
 		if (unlikely(error)) {
 			xfs_warn(target->bt_mount,
-				"%s: failed to map pages\n", __func__);
+				"%s: failed to map pagesn", __func__);
 			xfs_buf_relse(bp);
 			return NULL;
 		}
@@ -809,7 +810,7 @@ xfs_buf_get_uncached(
 	error = _xfs_buf_map_pages(bp, 0);
 	if (unlikely(error)) {
 		xfs_warn(target->bt_mount,
-			"%s: failed to map pages\n", __func__);
+			"%s: failed to map pages", __func__);
 		goto fail_free_mem;
 	}
 
@@ -1618,7 +1619,7 @@ xfs_setsize_buftarg_flags(
 		bdevname(btp->bt_bdev, name);
 
 		xfs_warn(btp->bt_mount,
-			"Cannot set_blocksize to %u on device %s\n",
+			"Cannot set_blocksize to %u on device %s",
 			sectorsize, name);
 		return EINVAL;
 	}

fs/xfs/xfs_buf_item.c

@@ -17,17 +17,18 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
 
 
 kmem_zone_t	*xfs_buf_item_zone;
@@ -808,7 +809,7 @@ xfs_buf_item_init(
  * Mark bytes first through last inclusive as dirty in the buf
  * item's bitmap.
  */
-void
+static void
 xfs_buf_item_log_segment(
 	struct xfs_buf_log_item	*bip,
 	uint			first,

fs/xfs/xfs_buf_item.h

@@ -71,10 +71,6 @@ void	xfs_buf_attach_iodone(struct xfs_buf *,
 void	xfs_buf_iodone_callbacks(struct xfs_buf *);
 void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
 
-void	xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *,
-			       enum xfs_blft);
-void	xfs_trans_buf_copy_type(struct xfs_buf *dst_bp, struct xfs_buf *src_bp);
-
 extern kmem_zone_t	*xfs_buf_item_zone;
 
 #endif	/* __XFS_BUF_ITEM_H__ */

fs/xfs/xfs_da_btree.c

@@ -18,20 +18,20 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_alloc.h"
 #include "xfs_bmap.h"
@@ -129,56 +129,6 @@ xfs_da_state_free(xfs_da_state_t *state)
 	kmem_zone_free(xfs_da_state_zone, state);
 }
 
-void
-xfs_da3_node_hdr_from_disk(
-	struct xfs_da3_icnode_hdr	*to,
-	struct xfs_da_intnode		*from)
-{
-	ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
-	       from->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
-
-	if (from->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
-		struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)from;
-
-		to->forw = be32_to_cpu(hdr3->info.hdr.forw);
-		to->back = be32_to_cpu(hdr3->info.hdr.back);
-		to->magic = be16_to_cpu(hdr3->info.hdr.magic);
-		to->count = be16_to_cpu(hdr3->__count);
-		to->level = be16_to_cpu(hdr3->__level);
-		return;
-	}
-	to->forw = be32_to_cpu(from->hdr.info.forw);
-	to->back = be32_to_cpu(from->hdr.info.back);
-	to->magic = be16_to_cpu(from->hdr.info.magic);
-	to->count = be16_to_cpu(from->hdr.__count);
-	to->level = be16_to_cpu(from->hdr.__level);
-}
-
-void
-xfs_da3_node_hdr_to_disk(
-	struct xfs_da_intnode		*to,
-	struct xfs_da3_icnode_hdr	*from)
-{
-	ASSERT(from->magic == XFS_DA_NODE_MAGIC ||
-	       from->magic == XFS_DA3_NODE_MAGIC);
-
-	if (from->magic == XFS_DA3_NODE_MAGIC) {
-		struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)to;
-
-		hdr3->info.hdr.forw = cpu_to_be32(from->forw);
-		hdr3->info.hdr.back = cpu_to_be32(from->back);
-		hdr3->info.hdr.magic = cpu_to_be16(from->magic);
-		hdr3->__count = cpu_to_be16(from->count);
-		hdr3->__level = cpu_to_be16(from->level);
-		return;
-	}
-	to->hdr.info.forw = cpu_to_be32(from->forw);
-	to->hdr.info.back = cpu_to_be32(from->back);
-	to->hdr.info.magic = cpu_to_be16(from->magic);
-	to->hdr.__count = cpu_to_be16(from->count);
-	to->hdr.__level = cpu_to_be16(from->level);
-}
-
 static bool
 xfs_da3_node_verify(
 	struct xfs_buf		*bp)
@@ -186,8 +136,11 @@ xfs_da3_node_verify(
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_da_intnode	*hdr = bp->b_addr;
 	struct xfs_da3_icnode_hdr ichdr;
+	const struct xfs_dir_ops *ops;
 
-	xfs_da3_node_hdr_from_disk(&ichdr, hdr);
+	ops = xfs_dir_get_ops(mp, NULL);
+
+	ops->node_hdr_from_disk(&ichdr, hdr);
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
@@ -354,11 +307,12 @@ xfs_da3_node_create(
 	struct xfs_da3_icnode_hdr ichdr = {0};
 	struct xfs_buf		*bp;
 	int			error;
+	struct xfs_inode	*dp = args->dp;
 
 	trace_xfs_da_node_create(args);
 	ASSERT(level <= XFS_DA_NODE_MAXDEPTH);
 
-	error = xfs_da_get_buf(tp, args->dp, blkno, -1, &bp, whichfork);
+	error = xfs_da_get_buf(tp, dp, blkno, -1, &bp, whichfork);
 	if (error)
 		return(error);
 	bp->b_ops = &xfs_da3_node_buf_ops;
@@ -377,9 +331,9 @@ xfs_da3_node_create(
 	}
 	ichdr.level = level;
 
-	xfs_da3_node_hdr_to_disk(node, &ichdr);
+	dp->d_ops->node_hdr_to_disk(node, &ichdr);
 	xfs_trans_log_buf(tp, bp,
-		XFS_DA_LOGRANGE(node, &node->hdr, xfs_da3_node_hdr_size(node)));
+		XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
 
 	*bpp = bp;
 	return(0);
@@ -589,8 +543,8 @@ xfs_da3_root_split(
 	    oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
 		struct xfs_da3_icnode_hdr nodehdr;
 
-		xfs_da3_node_hdr_from_disk(&nodehdr, oldroot);
-		btree = xfs_da3_node_tree_p(oldroot);
+		dp->d_ops->node_hdr_from_disk(&nodehdr, oldroot);
+		btree = dp->d_ops->node_tree_p(oldroot);
 		size = (int)((char *)&btree[nodehdr.count] - (char *)oldroot);
 		level = nodehdr.level;
 
@@ -604,8 +558,8 @@ xfs_da3_root_split(
 		struct xfs_dir2_leaf_entry *ents;
 
 		leaf = (xfs_dir2_leaf_t *)oldroot;
-		xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-		ents = xfs_dir3_leaf_ents_p(leaf);
+		dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+		ents = dp->d_ops->leaf_ents_p(leaf);
 
 		ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
 		       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
@@ -649,14 +603,14 @@ xfs_da3_root_split(
 		return error;
 
 	node = bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
-	btree = xfs_da3_node_tree_p(node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+	btree = dp->d_ops->node_tree_p(node);
 	btree[0].hashval = cpu_to_be32(blk1->hashval);
 	btree[0].before = cpu_to_be32(blk1->blkno);
 	btree[1].hashval = cpu_to_be32(blk2->hashval);
 	btree[1].before = cpu_to_be32(blk2->blkno);
 	nodehdr.count = 2;
-	xfs_da3_node_hdr_to_disk(node, &nodehdr);
+	dp->d_ops->node_hdr_to_disk(node, &nodehdr);
 
 #ifdef DEBUG
 	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
@@ -693,11 +647,12 @@ xfs_da3_node_split(
 	int			newcount;
 	int			error;
 	int			useextra;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_split(state->args);
 
 	node = oldblk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 
 	/*
 	 * With V2 dirs the extra block is data or freespace.
@@ -744,7 +699,7 @@ xfs_da3_node_split(
 	 * If we had double-split op below us, then add the extra block too.
 	 */
 	node = oldblk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 	if (oldblk->index <= nodehdr.count) {
 		oldblk->index++;
 		xfs_da3_node_add(state, oldblk, addblk);
@@ -793,15 +748,16 @@ xfs_da3_node_rebalance(
 	int			count;
 	int			tmp;
 	int			swap = 0;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_rebalance(state->args);
 
 	node1 = blk1->bp->b_addr;
 	node2 = blk2->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr1, node1);
-	xfs_da3_node_hdr_from_disk(&nodehdr2, node2);
-	btree1 = xfs_da3_node_tree_p(node1);
-	btree2 = xfs_da3_node_tree_p(node2);
+	dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+	dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+	btree1 = dp->d_ops->node_tree_p(node1);
+	btree2 = dp->d_ops->node_tree_p(node2);
 
 	/*
 	 * Figure out how many entries need to move, and in which direction.
@@ -814,10 +770,10 @@ xfs_da3_node_rebalance(
 		tmpnode = node1;
 		node1 = node2;
 		node2 = tmpnode;
-		xfs_da3_node_hdr_from_disk(&nodehdr1, node1);
-		xfs_da3_node_hdr_from_disk(&nodehdr2, node2);
-		btree1 = xfs_da3_node_tree_p(node1);
-		btree2 = xfs_da3_node_tree_p(node2);
+		dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+		dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+		btree1 = dp->d_ops->node_tree_p(node1);
+		btree2 = dp->d_ops->node_tree_p(node2);
 		swap = 1;
 	}
 
@@ -879,15 +835,14 @@ xfs_da3_node_rebalance(
 	/*
 	 * Log header of node 1 and all current bits of node 2.
 	 */
-	xfs_da3_node_hdr_to_disk(node1, &nodehdr1);
+	dp->d_ops->node_hdr_to_disk(node1, &nodehdr1);
 	xfs_trans_log_buf(tp, blk1->bp,
-		XFS_DA_LOGRANGE(node1, &node1->hdr,
-				xfs_da3_node_hdr_size(node1)));
+		XFS_DA_LOGRANGE(node1, &node1->hdr, dp->d_ops->node_hdr_size));
 
-	xfs_da3_node_hdr_to_disk(node2, &nodehdr2);
+	dp->d_ops->node_hdr_to_disk(node2, &nodehdr2);
 	xfs_trans_log_buf(tp, blk2->bp,
 		XFS_DA_LOGRANGE(node2, &node2->hdr,
-				xfs_da3_node_hdr_size(node2) +
+				dp->d_ops->node_hdr_size +
 				(sizeof(btree2[0]) * nodehdr2.count)));
 
 	/*
@@ -897,10 +852,10 @@ xfs_da3_node_rebalance(
 	if (swap) {
 		node1 = blk1->bp->b_addr;
 		node2 = blk2->bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr1, node1);
-		xfs_da3_node_hdr_from_disk(&nodehdr2, node2);
-		btree1 = xfs_da3_node_tree_p(node1);
-		btree2 = xfs_da3_node_tree_p(node2);
+		dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+		dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+		btree1 = dp->d_ops->node_tree_p(node1);
+		btree2 = dp->d_ops->node_tree_p(node2);
 	}
 	blk1->hashval = be32_to_cpu(btree1[nodehdr1.count - 1].hashval);
 	blk2->hashval = be32_to_cpu(btree2[nodehdr2.count - 1].hashval);
@@ -927,12 +882,13 @@ xfs_da3_node_add(
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_da_node_entry *btree;
 	int			tmp;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_add(state->args);
 
 	node = oldblk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
-	btree = xfs_da3_node_tree_p(node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+	btree = dp->d_ops->node_tree_p(node);
 
 	ASSERT(oldblk->index >= 0 && oldblk->index <= nodehdr.count);
 	ASSERT(newblk->blkno != 0);
@@ -955,9 +911,9 @@ xfs_da3_node_add(
 				tmp + sizeof(*btree)));
 
 	nodehdr.count += 1;
-	xfs_da3_node_hdr_to_disk(node, &nodehdr);
+	dp->d_ops->node_hdr_to_disk(node, &nodehdr);
 	xfs_trans_log_buf(state->args->trans, oldblk->bp,
-		XFS_DA_LOGRANGE(node, &node->hdr, xfs_da3_node_hdr_size(node)));
+		XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
 
 	/*
 	 * Copy the last hash value from the oldblk to propagate upwards.
@@ -1094,6 +1050,7 @@ xfs_da3_root_join(
 	struct xfs_da3_icnode_hdr oldroothdr;
 	struct xfs_da_node_entry *btree;
 	int			error;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_root_join(state->args);
 
@@ -1101,7 +1058,7 @@ xfs_da3_root_join(
 
 	args = state->args;
 	oldroot = root_blk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&oldroothdr, oldroot);
+	dp->d_ops->node_hdr_from_disk(&oldroothdr, oldroot);
 	ASSERT(oldroothdr.forw == 0);
 	ASSERT(oldroothdr.back == 0);
 
@@ -1115,10 +1072,10 @@ xfs_da3_root_join(
 	 * Read in the (only) child block, then copy those bytes into
 	 * the root block's buffer and free the original child block.
 	 */
-	btree = xfs_da3_node_tree_p(oldroot);
+	btree = dp->d_ops->node_tree_p(oldroot);
 	child = be32_to_cpu(btree[0].before);
 	ASSERT(child != 0);
-	error = xfs_da3_node_read(args->trans, args->dp, child, -1, &bp,
+	error = xfs_da3_node_read(args->trans, dp, child, -1, &bp,
 					     args->whichfork);
 	if (error)
 		return error;
@@ -1168,6 +1125,7 @@ xfs_da3_node_toosmall(
 	int			error;
 	int			retval;
 	int			i;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_toosmall(state->args);
 
@@ -1179,7 +1137,7 @@ xfs_da3_node_toosmall(
 	blk = &state->path.blk[ state->path.active-1 ];
 	info = blk->bp->b_addr;
 	node = (xfs_da_intnode_t *)info;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 	if (nodehdr.count > (state->node_ents >> 1)) {
 		*action = 0;	/* blk over 50%, don't try to join */
 		return(0);	/* blk over 50%, don't try to join */
@@ -1231,13 +1189,13 @@ xfs_da3_node_toosmall(
 			blkno = nodehdr.back;
 		if (blkno == 0)
 			continue;
-		error = xfs_da3_node_read(state->args->trans, state->args->dp,
+		error = xfs_da3_node_read(state->args->trans, dp,
 					blkno, -1, &bp, state->args->whichfork);
 		if (error)
 			return(error);
 
 		node = bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&thdr, node);
+		dp->d_ops->node_hdr_from_disk(&thdr, node);
 		xfs_trans_brelse(state->args->trans, bp);
 
 		if (count - thdr.count >= 0)
@@ -1275,6 +1233,7 @@ xfs_da3_node_toosmall(
  */
 STATIC uint
 xfs_da3_node_lasthash(
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp,
 	int			*count)
 {
@@ -1283,12 +1242,12 @@ xfs_da3_node_lasthash(
 	struct xfs_da3_icnode_hdr nodehdr;
 
 	node = bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 	if (count)
 		*count = nodehdr.count;
 	if (!nodehdr.count)
 		return 0;
-	btree = xfs_da3_node_tree_p(node);
+	btree = dp->d_ops->node_tree_p(node);
 	return be32_to_cpu(btree[nodehdr.count - 1].hashval);
 }
 
@@ -1307,6 +1266,7 @@ xfs_da3_fixhashpath(
 	xfs_dahash_t		lasthash=0;
 	int			level;
 	int			count;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_fixhashpath(state->args);
 
@@ -1319,12 +1279,12 @@ xfs_da3_fixhashpath(
 			return;
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
-		lasthash = xfs_dir2_leafn_lasthash(blk->bp, &count);
+		lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count);
 		if (count == 0)
 			return;
 		break;
 	case XFS_DA_NODE_MAGIC:
-		lasthash = xfs_da3_node_lasthash(blk->bp, &count);
+		lasthash = xfs_da3_node_lasthash(dp, blk->bp, &count);
 		if (count == 0)
 			return;
 		break;
@@ -1333,8 +1293,8 @@ xfs_da3_fixhashpath(
 		struct xfs_da3_icnode_hdr nodehdr;
 
 		node = blk->bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
-		btree = xfs_da3_node_tree_p(node);
+		dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+		btree = dp->d_ops->node_tree_p(node);
 		if (be32_to_cpu(btree->hashval) == lasthash)
 			break;
 		blk->hashval = lasthash;
@@ -1360,11 +1320,12 @@ xfs_da3_node_remove(
 	struct xfs_da_node_entry *btree;
 	int			index;
 	int			tmp;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_remove(state->args);
 
 	node = drop_blk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&nodehdr, node);
+	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 	ASSERT(drop_blk->index < nodehdr.count);
 	ASSERT(drop_blk->index >= 0);
 
@@ -1372,7 +1333,7 @@ xfs_da3_node_remove(
 	 * Copy over the offending entry, or just zero it out.
 	 */
 	index = drop_blk->index;
-	btree = xfs_da3_node_tree_p(node);
+	btree = dp->d_ops->node_tree_p(node);
 	if (index < nodehdr.count - 1) {
 		tmp  = nodehdr.count - index - 1;
 		tmp *= (uint)sizeof(xfs_da_node_entry_t);
@@ -1385,9 +1346,9 @@ xfs_da3_node_remove(
 	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index])));
 	nodehdr.count -= 1;
-	xfs_da3_node_hdr_to_disk(node, &nodehdr);
+	dp->d_ops->node_hdr_to_disk(node, &nodehdr);
 	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
-	    XFS_DA_LOGRANGE(node, &node->hdr, xfs_da3_node_hdr_size(node)));
+	    XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
 
 	/*
 	 * Copy the last hash value from the block to propagate upwards.
@@ -1414,15 +1375,16 @@ xfs_da3_node_unbalance(
 	struct xfs_trans	*tp;
 	int			sindex;
 	int			tmp;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_node_unbalance(state->args);
 
 	drop_node = drop_blk->bp->b_addr;
 	save_node = save_blk->bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&drop_hdr, drop_node);
-	xfs_da3_node_hdr_from_disk(&save_hdr, save_node);
-	drop_btree = xfs_da3_node_tree_p(drop_node);
-	save_btree = xfs_da3_node_tree_p(save_node);
+	dp->d_ops->node_hdr_from_disk(&drop_hdr, drop_node);
+	dp->d_ops->node_hdr_from_disk(&save_hdr, save_node);
+	drop_btree = dp->d_ops->node_tree_p(drop_node);
+	save_btree = dp->d_ops->node_tree_p(save_node);
 	tp = state->args->trans;
 
 	/*
@@ -1456,10 +1418,10 @@ xfs_da3_node_unbalance(
 	memcpy(&save_btree[sindex], &drop_btree[0], tmp);
 	save_hdr.count += drop_hdr.count;
 
-	xfs_da3_node_hdr_to_disk(save_node, &save_hdr);
+	dp->d_ops->node_hdr_to_disk(save_node, &save_hdr);
 	xfs_trans_log_buf(tp, save_blk->bp,
 		XFS_DA_LOGRANGE(save_node, &save_node->hdr,
-				xfs_da3_node_hdr_size(save_node)));
+				dp->d_ops->node_hdr_size));
 
 	/*
 	 * Save the last hashval in the remaining block for upward propagation.
@@ -1501,6 +1463,7 @@ xfs_da3_node_lookup_int(
 	int			max;
 	int			error;
 	int			retval;
+	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
 
@@ -1536,7 +1499,8 @@ xfs_da3_node_lookup_int(
 		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
-			blk->hashval = xfs_dir2_leafn_lasthash(blk->bp, NULL);
+			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
+							       blk->bp, NULL);
 			break;
 		}
 
@@ -1547,8 +1511,8 @@ xfs_da3_node_lookup_int(
 		 * Search an intermediate node for a match.
 		 */
 		node = blk->bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
-		btree = xfs_da3_node_tree_p(node);
+		dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+		btree = dp->d_ops->node_tree_p(node);
 
 		max = nodehdr.count;
 		blk->hashval = be32_to_cpu(btree[max - 1].hashval);
@@ -1643,6 +1607,7 @@ xfs_da3_node_lookup_int(
  */
 STATIC int
 xfs_da3_node_order(
+	struct xfs_inode *dp,
 	struct xfs_buf	*node1_bp,
 	struct xfs_buf	*node2_bp)
 {
@@ -1655,10 +1620,10 @@ xfs_da3_node_order(
 
 	node1 = node1_bp->b_addr;
 	node2 = node2_bp->b_addr;
-	xfs_da3_node_hdr_from_disk(&node1hdr, node1);
-	xfs_da3_node_hdr_from_disk(&node2hdr, node2);
-	btree1 = xfs_da3_node_tree_p(node1);
-	btree2 = xfs_da3_node_tree_p(node2);
+	dp->d_ops->node_hdr_from_disk(&node1hdr, node1);
+	dp->d_ops->node_hdr_from_disk(&node2hdr, node2);
+	btree1 = dp->d_ops->node_tree_p(node1);
+	btree2 = dp->d_ops->node_tree_p(node2);
 
 	if (node1hdr.count > 0 && node2hdr.count > 0 &&
 	    ((be32_to_cpu(btree2[0].hashval) < be32_to_cpu(btree1[0].hashval)) ||
@@ -1685,6 +1650,7 @@ xfs_da3_blk_link(
 	struct xfs_buf		*bp;
 	int			before = 0;
 	int			error;
+	struct xfs_inode	*dp = state->args->dp;
 
 	/*
 	 * Set up environment.
@@ -1702,10 +1668,10 @@ xfs_da3_blk_link(
 		before = xfs_attr_leaf_order(old_blk->bp, new_blk->bp);
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
-		before = xfs_dir2_leafn_order(old_blk->bp, new_blk->bp);
+		before = xfs_dir2_leafn_order(dp, old_blk->bp, new_blk->bp);
 		break;
 	case XFS_DA_NODE_MAGIC:
-		before = xfs_da3_node_order(old_blk->bp, new_blk->bp);
+		before = xfs_da3_node_order(dp, old_blk->bp, new_blk->bp);
 		break;
 	}
 
@@ -1720,7 +1686,7 @@ xfs_da3_blk_link(
 		new_info->forw = cpu_to_be32(old_blk->blkno);
 		new_info->back = old_info->back;
 		if (old_info->back) {
-			error = xfs_da3_node_read(args->trans, args->dp,
+			error = xfs_da3_node_read(args->trans, dp,
 						be32_to_cpu(old_info->back),
 						-1, &bp, args->whichfork);
 			if (error)
@@ -1741,7 +1707,7 @@ xfs_da3_blk_link(
 		new_info->forw = old_info->forw;
 		new_info->back = cpu_to_be32(old_blk->blkno);
 		if (old_info->forw) {
-			error = xfs_da3_node_read(args->trans, args->dp,
+			error = xfs_da3_node_read(args->trans, dp,
 						be32_to_cpu(old_info->forw),
 						-1, &bp, args->whichfork);
 			if (error)
@@ -1861,6 +1827,7 @@ xfs_da3_path_shift(
 	xfs_dablk_t		blkno = 0;
 	int			level;
 	int			error;
+	struct xfs_inode	*dp = state->args->dp;
 
 	trace_xfs_da_path_shift(state->args);
 
@@ -1876,8 +1843,8 @@ xfs_da3_path_shift(
 	level = (path->active-1) - 1;	/* skip bottom layer in path */
 	for (blk = &path->blk[level]; level >= 0; blk--, level--) {
 		node = blk->bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
-		btree = xfs_da3_node_tree_p(node);
+		dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+		btree = dp->d_ops->node_tree_p(node);
 
 		if (forward && (blk->index < nodehdr.count - 1)) {
 			blk->index++;
@@ -1911,7 +1878,7 @@ xfs_da3_path_shift(
 		 * Read the next child block.
 		 */
 		blk->blkno = blkno;
-		error = xfs_da3_node_read(args->trans, args->dp, blkno, -1,
+		error = xfs_da3_node_read(args->trans, dp, blkno, -1,
 					&blk->bp, args->whichfork);
 		if (error)
 			return(error);
@@ -1933,8 +1900,8 @@ xfs_da3_path_shift(
 		case XFS_DA3_NODE_MAGIC:
 			blk->magic = XFS_DA_NODE_MAGIC;
 			node = (xfs_da_intnode_t *)info;
-			xfs_da3_node_hdr_from_disk(&nodehdr, node);
-			btree = xfs_da3_node_tree_p(node);
+			dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+			btree = dp->d_ops->node_tree_p(node);
 			blk->hashval = be32_to_cpu(btree[nodehdr.count - 1].hashval);
 			if (forward)
 				blk->index = 0;
@@ -1947,16 +1914,15 @@ xfs_da3_path_shift(
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
-			blk->hashval = xfs_attr_leaf_lasthash(blk->bp,
-							      NULL);
+			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
 		case XFS_DIR2_LEAFN_MAGIC:
 		case XFS_DIR3_LEAFN_MAGIC:
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
-			blk->hashval = xfs_dir2_leafn_lasthash(blk->bp,
-							       NULL);
+			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
+							       blk->bp, NULL);
 			break;
 		default:
 			ASSERT(0);
@@ -2163,7 +2129,7 @@ xfs_da3_swap_lastblock(
 	struct xfs_dir2_leaf	*dead_leaf2;
 	struct xfs_da_node_entry *btree;
 	struct xfs_da3_icnode_hdr par_hdr;
-	struct xfs_inode	*ip;
+	struct xfs_inode	*dp;
 	struct xfs_trans	*tp;
 	struct xfs_mount	*mp;
 	struct xfs_buf		*dead_buf;
@@ -2187,12 +2153,12 @@ xfs_da3_swap_lastblock(
 	dead_buf = *dead_bufp;
 	dead_blkno = *dead_blknop;
 	tp = args->trans;
-	ip = args->dp;
+	dp = args->dp;
 	w = args->whichfork;
 	ASSERT(w == XFS_DATA_FORK);
-	mp = ip->i_mount;
+	mp = dp->i_mount;
 	lastoff = mp->m_dirfreeblk;
-	error = xfs_bmap_last_before(tp, ip, &lastoff, w);
+	error = xfs_bmap_last_before(tp, dp, &lastoff, w);
 	if (error)
 		return error;
 	if (unlikely(lastoff == 0)) {
@@ -2204,7 +2170,7 @@ xfs_da3_swap_lastblock(
 	 * Read the last block in the btree space.
 	 */
 	last_blkno = (xfs_dablk_t)lastoff - mp->m_dirblkfsbs;
-	error = xfs_da3_node_read(tp, ip, last_blkno, -1, &last_buf, w);
+	error = xfs_da3_node_read(tp, dp, last_blkno, -1, &last_buf, w);
 	if (error)
 		return error;
 	/*
@@ -2222,16 +2188,16 @@ xfs_da3_swap_lastblock(
 		struct xfs_dir2_leaf_entry *ents;
 
 		dead_leaf2 = (xfs_dir2_leaf_t *)dead_info;
-		xfs_dir3_leaf_hdr_from_disk(&leafhdr, dead_leaf2);
-		ents = xfs_dir3_leaf_ents_p(dead_leaf2);
+		dp->d_ops->leaf_hdr_from_disk(&leafhdr, dead_leaf2);
+		ents = dp->d_ops->leaf_ents_p(dead_leaf2);
 		dead_level = 0;
 		dead_hash = be32_to_cpu(ents[leafhdr.count - 1].hashval);
 	} else {
 		struct xfs_da3_icnode_hdr deadhdr;
 
 		dead_node = (xfs_da_intnode_t *)dead_info;
-		xfs_da3_node_hdr_from_disk(&deadhdr, dead_node);
-		btree = xfs_da3_node_tree_p(dead_node);
+		dp->d_ops->node_hdr_from_disk(&deadhdr, dead_node);
+		btree = dp->d_ops->node_tree_p(dead_node);
 		dead_level = deadhdr.level;
 		dead_hash = be32_to_cpu(btree[deadhdr.count - 1].hashval);
 	}
@@ -2240,7 +2206,7 @@ xfs_da3_swap_lastblock(
 	 * If the moved block has a left sibling, fix up the pointers.
 	 */
 	if ((sib_blkno = be32_to_cpu(dead_info->back))) {
-		error = xfs_da3_node_read(tp, ip, sib_blkno, -1, &sib_buf, w);
+		error = xfs_da3_node_read(tp, dp, sib_blkno, -1, &sib_buf, w);
 		if (error)
 			goto done;
 		sib_info = sib_buf->b_addr;
@@ -2262,7 +2228,7 @@ xfs_da3_swap_lastblock(
 	 * If the moved block has a right sibling, fix up the pointers.
 	 */
 	if ((sib_blkno = be32_to_cpu(dead_info->forw))) {
-		error = xfs_da3_node_read(tp, ip, sib_blkno, -1, &sib_buf, w);
+		error = xfs_da3_node_read(tp, dp, sib_blkno, -1, &sib_buf, w);
 		if (error)
 			goto done;
 		sib_info = sib_buf->b_addr;
@@ -2286,11 +2252,11 @@ xfs_da3_swap_lastblock(
 	 * Walk down the tree looking for the parent of the moved block.
 	 */
 	for (;;) {
-		error = xfs_da3_node_read(tp, ip, par_blkno, -1, &par_buf, w);
+		error = xfs_da3_node_read(tp, dp, par_blkno, -1, &par_buf, w);
 		if (error)
 			goto done;
 		par_node = par_buf->b_addr;
-		xfs_da3_node_hdr_from_disk(&par_hdr, par_node);
+		dp->d_ops->node_hdr_from_disk(&par_hdr, par_node);
 		if (level >= 0 && level != par_hdr.level + 1) {
 			XFS_ERROR_REPORT("xfs_da_swap_lastblock(4)",
 					 XFS_ERRLEVEL_LOW, mp);
@@ -2298,7 +2264,7 @@ xfs_da3_swap_lastblock(
 			goto done;
 		}
 		level = par_hdr.level;
-		btree = xfs_da3_node_tree_p(par_node);
+		btree = dp->d_ops->node_tree_p(par_node);
 		for (entno = 0;
 		     entno < par_hdr.count &&
 		     be32_to_cpu(btree[entno].hashval) < dead_hash;
@@ -2337,18 +2303,18 @@ xfs_da3_swap_lastblock(
 			error = XFS_ERROR(EFSCORRUPTED);
 			goto done;
 		}
-		error = xfs_da3_node_read(tp, ip, par_blkno, -1, &par_buf, w);
+		error = xfs_da3_node_read(tp, dp, par_blkno, -1, &par_buf, w);
 		if (error)
 			goto done;
 		par_node = par_buf->b_addr;
-		xfs_da3_node_hdr_from_disk(&par_hdr, par_node);
+		dp->d_ops->node_hdr_from_disk(&par_hdr, par_node);
 		if (par_hdr.level != level) {
 			XFS_ERROR_REPORT("xfs_da_swap_lastblock(7)",
 					 XFS_ERRLEVEL_LOW, mp);
 			error = XFS_ERROR(EFSCORRUPTED);
 			goto done;
 		}
-		btree = xfs_da3_node_tree_p(par_node);
+		btree = dp->d_ops->node_tree_p(par_node);
 		entno = 0;
 	}
 	/*

fs/xfs/xfs_da_btree.h

@@ -23,146 +23,7 @@ struct xfs_bmap_free;
 struct xfs_inode;
 struct xfs_trans;
 struct zone;
-
-/*========================================================================
- * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
-/*
- * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
- *
- * It is used to manage a doubly linked list of all blocks at the same
- * level in the Btree, and to identify which type of block this is.
- */
-#define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
-#define XFS_ATTR_LEAF_MAGIC	0xfbee	/* magic number: attribute leaf blks */
-#define	XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
-
-typedef struct xfs_da_blkinfo {
-	__be32		forw;			/* previous block in list */
-	__be32		back;			/* following block in list */
-	__be16		magic;			/* validity check on block */
-	__be16		pad;			/* unused */
-} xfs_da_blkinfo_t;
-
-/*
- * CRC enabled directory structure types
- *
- * The headers change size for the additional verification information, but
- * otherwise the tree layouts and contents are unchanged. Hence the da btree
- * code can use the struct xfs_da_blkinfo for manipulating the tree links and
- * magic numbers without modification for both v2 and v3 nodes.
- */
-#define XFS_DA3_NODE_MAGIC	0x3ebe	/* magic number: non-leaf blocks */
-#define XFS_ATTR3_LEAF_MAGIC	0x3bee	/* magic number: attribute leaf blks */
-#define	XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v2 dirlf multi blks */
-
-struct xfs_da3_blkinfo {
-	/*
-	 * the node link manipulation code relies on the fact that the first
-	 * element of this structure is the struct xfs_da_blkinfo so it can
-	 * ignore the differences in the rest of the structures.
-	 */
-	struct xfs_da_blkinfo	hdr;
-	__be32			crc;	/* CRC of block */
-	__be64			blkno;	/* first block of the buffer */
-	__be64			lsn;	/* sequence number of last write */
-	uuid_t			uuid;	/* filesystem we belong to */
-	__be64			owner;	/* inode that owns the block */
-};
-
-/*
- * This is the structure of the root and intermediate nodes in the Btree.
- * The leaf nodes are defined above.
- *
- * Entries are not packed.
- *
- * Since we have duplicate keys, use a binary search but always follow
- * all match in the block, not just the first match found.
- */
-#define	XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
-
-typedef struct xfs_da_node_hdr {
-	struct xfs_da_blkinfo	info;	/* block type, links, etc. */
-	__be16			__count; /* count of active entries */
-	__be16			__level; /* level above leaves (leaf == 0) */
-} xfs_da_node_hdr_t;
-
-struct xfs_da3_node_hdr {
-	struct xfs_da3_blkinfo	info;	/* block type, links, etc. */
-	__be16			__count; /* count of active entries */
-	__be16			__level; /* level above leaves (leaf == 0) */
-	__be32			__pad32;
-};
-
-#define XFS_DA3_NODE_CRC_OFF	(offsetof(struct xfs_da3_node_hdr, info.crc))
-
-typedef struct xfs_da_node_entry {
-	__be32	hashval;	/* hash value for this descendant */
-	__be32	before;		/* Btree block before this key */
-} xfs_da_node_entry_t;
-
-typedef struct xfs_da_intnode {
-	struct xfs_da_node_hdr	hdr;
-	struct xfs_da_node_entry __btree[];
-} xfs_da_intnode_t;
-
-struct xfs_da3_intnode {
-	struct xfs_da3_node_hdr	hdr;
-	struct xfs_da_node_entry __btree[];
-};
-
-/*
- * In-core version of the node header to abstract the differences in the v2 and
- * v3 disk format of the headers. Callers need to convert to/from disk format as
- * appropriate.
- */
-struct xfs_da3_icnode_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	level;
-};
-
-extern void xfs_da3_node_hdr_from_disk(struct xfs_da3_icnode_hdr *to,
-				       struct xfs_da_intnode *from);
-extern void xfs_da3_node_hdr_to_disk(struct xfs_da_intnode *to,
-				     struct xfs_da3_icnode_hdr *from);
-
-static inline int
-__xfs_da3_node_hdr_size(bool v3)
-{
-	if (v3)
-		return sizeof(struct xfs_da3_node_hdr);
-	return sizeof(struct xfs_da_node_hdr);
-}
-static inline int
-xfs_da3_node_hdr_size(struct xfs_da_intnode *dap)
-{
-	bool	v3 = dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC);
-
-	return __xfs_da3_node_hdr_size(v3);
-}
-
-static inline struct xfs_da_node_entry *
-xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
-{
-	if (dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
-		struct xfs_da3_intnode *dap3 = (struct xfs_da3_intnode *)dap;
-		return dap3->__btree;
-	}
-	return dap->__btree;
-}
-
-extern void xfs_da3_intnode_from_disk(struct xfs_da3_icnode_hdr *to,
-				      struct xfs_da_intnode *from);
-extern void xfs_da3_intnode_to_disk(struct xfs_da_intnode *to,
-				    struct xfs_da3_icnode_hdr *from);
-
-#define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
+struct xfs_dir_ops;
 
 /*========================================================================
  * Btree searching and modification structure definitions.
@@ -309,8 +170,6 @@ int	xfs_da3_node_read(struct xfs_trans *tp, struct xfs_inode *dp,
 			 xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			 struct xfs_buf **bpp, int which_fork);
 
-extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
-
 /*
  * Utility routines.
  */

fs/xfs/xfs_da_format.c

@@ -0,0 +1,907 @@
+/*
+ * Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_inode.h"
+#include "xfs_dir2.h"
+
+/*
+ * Shortform directory ops
+ */
+static int
+xfs_dir2_sf_entsize(
+	struct xfs_dir2_sf_hdr	*hdr,
+	int			len)
+{
+	int count = sizeof(struct xfs_dir2_sf_entry);	/* namelen + offset */
+
+	count += len;					/* name */
+	count += hdr->i8count ? sizeof(xfs_dir2_ino8_t) :
+				sizeof(xfs_dir2_ino4_t); /* ino # */
+	return count;
+}
+
+static int
+xfs_dir3_sf_entsize(
+	struct xfs_dir2_sf_hdr	*hdr,
+	int			len)
+{
+	return xfs_dir2_sf_entsize(hdr, len) + sizeof(__uint8_t);
+}
+
+static struct xfs_dir2_sf_entry *
+xfs_dir2_sf_nextentry(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return (struct xfs_dir2_sf_entry *)
+		((char *)sfep + xfs_dir2_sf_entsize(hdr, sfep->namelen));
+}
+
+static struct xfs_dir2_sf_entry *
+xfs_dir3_sf_nextentry(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return (struct xfs_dir2_sf_entry *)
+		((char *)sfep + xfs_dir3_sf_entsize(hdr, sfep->namelen));
+}
+
+
+/*
+ * For filetype enabled shortform directories, the file type field is stored at
+ * the end of the name.  Because it's only a single byte, endian conversion is
+ * not necessary. For non-filetype enable directories, the type is always
+ * unknown and we never store the value.
+ */
+static __uint8_t
+xfs_dir2_sfe_get_ftype(
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return XFS_DIR3_FT_UNKNOWN;
+}
+
+static void
+xfs_dir2_sfe_put_ftype(
+	struct xfs_dir2_sf_entry *sfep,
+	__uint8_t		ftype)
+{
+	ASSERT(ftype < XFS_DIR3_FT_MAX);
+}
+
+static __uint8_t
+xfs_dir3_sfe_get_ftype(
+	struct xfs_dir2_sf_entry *sfep)
+{
+	__uint8_t	ftype;
+
+	ftype = sfep->name[sfep->namelen];
+	if (ftype >= XFS_DIR3_FT_MAX)
+		return XFS_DIR3_FT_UNKNOWN;
+	return ftype;
+}
+
+static void
+xfs_dir3_sfe_put_ftype(
+	struct xfs_dir2_sf_entry *sfep,
+	__uint8_t		ftype)
+{
+	ASSERT(ftype < XFS_DIR3_FT_MAX);
+
+	sfep->name[sfep->namelen] = ftype;
+}
+
+/*
+ * Inode numbers in short-form directories can come in two versions,
+ * either 4 bytes or 8 bytes wide.  These helpers deal with the
+ * two forms transparently by looking at the headers i8count field.
+ *
+ * For 64-bit inode number the most significant byte must be zero.
+ */
+static xfs_ino_t
+xfs_dir2_sf_get_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	xfs_dir2_inou_t		*from)
+{
+	if (hdr->i8count)
+		return get_unaligned_be64(&from->i8.i) & 0x00ffffffffffffffULL;
+	else
+		return get_unaligned_be32(&from->i4.i);
+}
+
+static void
+xfs_dir2_sf_put_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	xfs_dir2_inou_t		*to,
+	xfs_ino_t		ino)
+{
+	ASSERT((ino & 0xff00000000000000ULL) == 0);
+
+	if (hdr->i8count)
+		put_unaligned_be64(ino, &to->i8.i);
+	else
+		put_unaligned_be32(ino, &to->i4.i);
+}
+
+static xfs_ino_t
+xfs_dir2_sf_get_parent_ino(
+	struct xfs_dir2_sf_hdr	*hdr)
+{
+	return xfs_dir2_sf_get_ino(hdr, &hdr->parent);
+}
+
+static void
+xfs_dir2_sf_put_parent_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	xfs_ino_t		ino)
+{
+	xfs_dir2_sf_put_ino(hdr, &hdr->parent, ino);
+}
+
+/*
+ * In short-form directory entries the inode numbers are stored at variable
+ * offset behind the entry name. If the entry stores a filetype value, then it
+ * sits between the name and the inode number. Hence the inode numbers may only
+ * be accessed through the helpers below.
+ */
+static xfs_ino_t
+xfs_dir2_sfe_get_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return xfs_dir2_sf_get_ino(hdr,
+				(xfs_dir2_inou_t *)&sfep->name[sfep->namelen]);
+}
+
+static void
+xfs_dir2_sfe_put_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep,
+	xfs_ino_t		ino)
+{
+	xfs_dir2_sf_put_ino(hdr,
+			    (xfs_dir2_inou_t *)&sfep->name[sfep->namelen], ino);
+}
+
+static xfs_ino_t
+xfs_dir3_sfe_get_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return xfs_dir2_sf_get_ino(hdr,
+			(xfs_dir2_inou_t *)&sfep->name[sfep->namelen + 1]);
+}
+
+static void
+xfs_dir3_sfe_put_ino(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep,
+	xfs_ino_t		ino)
+{
+	xfs_dir2_sf_put_ino(hdr,
+			(xfs_dir2_inou_t *)&sfep->name[sfep->namelen + 1], ino);
+}
+
+
+/*
+ * Directory data block operations
+ */
+
+/*
+ * For special situations, the dirent size ends up fixed because we always know
+ * what the size of the entry is. That's true for the "." and "..", and
+ * therefore we know that they are a fixed size and hence their offsets are
+ * constant, as is the first entry.
+ *
+ * Hence, this calculation is written as a macro to be able to be calculated at
+ * compile time and so certain offsets can be calculated directly in the
+ * structure initaliser via the macro. There are two macros - one for dirents
+ * with ftype and without so there are no unresolvable conditionals in the
+ * calculations. We also use round_up() as XFS_DIR2_DATA_ALIGN is always a power
+ * of 2 and the compiler doesn't reject it (unlike roundup()).
+ */
+#define XFS_DIR2_DATA_ENTSIZE(n)					\
+	round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) +	\
+		 sizeof(xfs_dir2_data_off_t)), XFS_DIR2_DATA_ALIGN)
+
+#define XFS_DIR3_DATA_ENTSIZE(n)					\
+	round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) +	\
+		 sizeof(xfs_dir2_data_off_t) + sizeof(__uint8_t)),	\
+		XFS_DIR2_DATA_ALIGN)
+
+static int
+xfs_dir2_data_entsize(
+	int			n)
+{
+	return XFS_DIR2_DATA_ENTSIZE(n);
+}
+
+static int
+xfs_dir3_data_entsize(
+	int			n)
+{
+	return XFS_DIR3_DATA_ENTSIZE(n);
+}
+
+static __uint8_t
+xfs_dir2_data_get_ftype(
+	struct xfs_dir2_data_entry *dep)
+{
+	return XFS_DIR3_FT_UNKNOWN;
+}
+
+static void
+xfs_dir2_data_put_ftype(
+	struct xfs_dir2_data_entry *dep,
+	__uint8_t		ftype)
+{
+	ASSERT(ftype < XFS_DIR3_FT_MAX);
+}
+
+static __uint8_t
+xfs_dir3_data_get_ftype(
+	struct xfs_dir2_data_entry *dep)
+{
+	__uint8_t	ftype = dep->name[dep->namelen];
+
+	ASSERT(ftype < XFS_DIR3_FT_MAX);
+	if (ftype >= XFS_DIR3_FT_MAX)
+		return XFS_DIR3_FT_UNKNOWN;
+	return ftype;
+}
+
+static void
+xfs_dir3_data_put_ftype(
+	struct xfs_dir2_data_entry *dep,
+	__uint8_t		type)
+{
+	ASSERT(type < XFS_DIR3_FT_MAX);
+	ASSERT(dep->namelen != 0);
+
+	dep->name[dep->namelen] = type;
+}
+
+/*
+ * Pointer to an entry's tag word.
+ */
+static __be16 *
+xfs_dir2_data_entry_tag_p(
+	struct xfs_dir2_data_entry *dep)
+{
+	return (__be16 *)((char *)dep +
+		xfs_dir2_data_entsize(dep->namelen) - sizeof(__be16));
+}
+
+static __be16 *
+xfs_dir3_data_entry_tag_p(
+	struct xfs_dir2_data_entry *dep)
+{
+	return (__be16 *)((char *)dep +
+		xfs_dir3_data_entsize(dep->namelen) - sizeof(__be16));
+}
+
+/*
+ * location of . and .. in data space (always block 0)
+ */
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_dot_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_dotdot_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR2_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_first_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR2_DATA_ENTSIZE(1) +
+				XFS_DIR2_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_ftype_data_dotdot_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_ftype_data_first_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1) +
+				XFS_DIR3_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_dot_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_dotdot_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir3_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_first_entry_p(
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir3_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1) +
+				XFS_DIR3_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_free *
+xfs_dir2_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return hdr->bestfree;
+}
+
+static struct xfs_dir2_data_free *
+xfs_dir3_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return ((struct xfs_dir3_data_hdr *)hdr)->best_free;
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_entry_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_unused *
+xfs_dir2_data_unused_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_unused *)
+		((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_entry_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+static struct xfs_dir2_data_unused *
+xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_unused *)
+		((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+
+/*
+ * Directory Leaf block operations
+ */
+static int
+xfs_dir2_max_leaf_ents(struct xfs_mount *mp)
+{
+	return (mp->m_dirblksize - sizeof(struct xfs_dir2_leaf_hdr)) /
+		(uint)sizeof(struct xfs_dir2_leaf_entry);
+}
+
+static struct xfs_dir2_leaf_entry *
+xfs_dir2_leaf_ents_p(struct xfs_dir2_leaf *lp)
+{
+	return lp->__ents;
+}
+
+static int
+xfs_dir3_max_leaf_ents(struct xfs_mount *mp)
+{
+	return (mp->m_dirblksize - sizeof(struct xfs_dir3_leaf_hdr)) /
+		(uint)sizeof(struct xfs_dir2_leaf_entry);
+}
+
+static struct xfs_dir2_leaf_entry *
+xfs_dir3_leaf_ents_p(struct xfs_dir2_leaf *lp)
+{
+	return ((struct xfs_dir3_leaf *)lp)->__ents;
+}
+
+static void
+xfs_dir2_leaf_hdr_from_disk(
+	struct xfs_dir3_icleaf_hdr	*to,
+	struct xfs_dir2_leaf		*from)
+{
+	to->forw = be32_to_cpu(from->hdr.info.forw);
+	to->back = be32_to_cpu(from->hdr.info.back);
+	to->magic = be16_to_cpu(from->hdr.info.magic);
+	to->count = be16_to_cpu(from->hdr.count);
+	to->stale = be16_to_cpu(from->hdr.stale);
+
+	ASSERT(to->magic == XFS_DIR2_LEAF1_MAGIC ||
+	       to->magic == XFS_DIR2_LEAFN_MAGIC);
+}
+
+static void
+xfs_dir2_leaf_hdr_to_disk(
+	struct xfs_dir2_leaf		*to,
+	struct xfs_dir3_icleaf_hdr	*from)
+{
+	ASSERT(from->magic == XFS_DIR2_LEAF1_MAGIC ||
+	       from->magic == XFS_DIR2_LEAFN_MAGIC);
+
+	to->hdr.info.forw = cpu_to_be32(from->forw);
+	to->hdr.info.back = cpu_to_be32(from->back);
+	to->hdr.info.magic = cpu_to_be16(from->magic);
+	to->hdr.count = cpu_to_be16(from->count);
+	to->hdr.stale = cpu_to_be16(from->stale);
+}
+
+static void
+xfs_dir3_leaf_hdr_from_disk(
+	struct xfs_dir3_icleaf_hdr	*to,
+	struct xfs_dir2_leaf		*from)
+{
+	struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)from;
+
+	to->forw = be32_to_cpu(hdr3->info.hdr.forw);
+	to->back = be32_to_cpu(hdr3->info.hdr.back);
+	to->magic = be16_to_cpu(hdr3->info.hdr.magic);
+	to->count = be16_to_cpu(hdr3->count);
+	to->stale = be16_to_cpu(hdr3->stale);
+
+	ASSERT(to->magic == XFS_DIR3_LEAF1_MAGIC ||
+	       to->magic == XFS_DIR3_LEAFN_MAGIC);
+}
+
+static void
+xfs_dir3_leaf_hdr_to_disk(
+	struct xfs_dir2_leaf		*to,
+	struct xfs_dir3_icleaf_hdr	*from)
+{
+	struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)to;
+
+	ASSERT(from->magic == XFS_DIR3_LEAF1_MAGIC ||
+	       from->magic == XFS_DIR3_LEAFN_MAGIC);
+
+	hdr3->info.hdr.forw = cpu_to_be32(from->forw);
+	hdr3->info.hdr.back = cpu_to_be32(from->back);
+	hdr3->info.hdr.magic = cpu_to_be16(from->magic);
+	hdr3->count = cpu_to_be16(from->count);
+	hdr3->stale = cpu_to_be16(from->stale);
+}
+
+
+/*
+ * Directory/Attribute Node block operations
+ */
+static struct xfs_da_node_entry *
+xfs_da2_node_tree_p(struct xfs_da_intnode *dap)
+{
+	return dap->__btree;
+}
+
+static struct xfs_da_node_entry *
+xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
+{
+	return ((struct xfs_da3_intnode *)dap)->__btree;
+}
+
+static void
+xfs_da2_node_hdr_from_disk(
+	struct xfs_da3_icnode_hdr	*to,
+	struct xfs_da_intnode		*from)
+{
+	ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+	to->forw = be32_to_cpu(from->hdr.info.forw);
+	to->back = be32_to_cpu(from->hdr.info.back);
+	to->magic = be16_to_cpu(from->hdr.info.magic);
+	to->count = be16_to_cpu(from->hdr.__count);
+	to->level = be16_to_cpu(from->hdr.__level);
+}
+
+static void
+xfs_da2_node_hdr_to_disk(
+	struct xfs_da_intnode		*to,
+	struct xfs_da3_icnode_hdr	*from)
+{
+	ASSERT(from->magic == XFS_DA_NODE_MAGIC);
+	to->hdr.info.forw = cpu_to_be32(from->forw);
+	to->hdr.info.back = cpu_to_be32(from->back);
+	to->hdr.info.magic = cpu_to_be16(from->magic);
+	to->hdr.__count = cpu_to_be16(from->count);
+	to->hdr.__level = cpu_to_be16(from->level);
+}
+
+static void
+xfs_da3_node_hdr_from_disk(
+	struct xfs_da3_icnode_hdr	*to,
+	struct xfs_da_intnode		*from)
+{
+	struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)from;
+
+	ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
+	to->forw = be32_to_cpu(hdr3->info.hdr.forw);
+	to->back = be32_to_cpu(hdr3->info.hdr.back);
+	to->magic = be16_to_cpu(hdr3->info.hdr.magic);
+	to->count = be16_to_cpu(hdr3->__count);
+	to->level = be16_to_cpu(hdr3->__level);
+}
+
+static void
+xfs_da3_node_hdr_to_disk(
+	struct xfs_da_intnode		*to,
+	struct xfs_da3_icnode_hdr	*from)
+{
+	struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)to;
+
+	ASSERT(from->magic == XFS_DA3_NODE_MAGIC);
+	hdr3->info.hdr.forw = cpu_to_be32(from->forw);
+	hdr3->info.hdr.back = cpu_to_be32(from->back);
+	hdr3->info.hdr.magic = cpu_to_be16(from->magic);
+	hdr3->__count = cpu_to_be16(from->count);
+	hdr3->__level = cpu_to_be16(from->level);
+}
+
+
+/*
+ * Directory free space block operations
+ */
+static int
+xfs_dir2_free_max_bests(struct xfs_mount *mp)
+{
+	return (mp->m_dirblksize - sizeof(struct xfs_dir2_free_hdr)) /
+		sizeof(xfs_dir2_data_off_t);
+}
+
+static __be16 *
+xfs_dir2_free_bests_p(struct xfs_dir2_free *free)
+{
+	return (__be16 *)((char *)free + sizeof(struct xfs_dir2_free_hdr));
+}
+
+/*
+ * Convert data space db to the corresponding free db.
+ */
+static xfs_dir2_db_t
+xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir2_free_max_bests(mp);
+}
+
+/*
+ * Convert data space db to the corresponding index in a free db.
+ */
+static int
+xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return db % xfs_dir2_free_max_bests(mp);
+}
+
+static int
+xfs_dir3_free_max_bests(struct xfs_mount *mp)
+{
+	return (mp->m_dirblksize - sizeof(struct xfs_dir3_free_hdr)) /
+		sizeof(xfs_dir2_data_off_t);
+}
+
+static __be16 *
+xfs_dir3_free_bests_p(struct xfs_dir2_free *free)
+{
+	return (__be16 *)((char *)free + sizeof(struct xfs_dir3_free_hdr));
+}
+
+/*
+ * Convert data space db to the corresponding free db.
+ */
+static xfs_dir2_db_t
+xfs_dir3_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
+}
+
+/*
+ * Convert data space db to the corresponding index in a free db.
+ */
+static int
+xfs_dir3_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return db % xfs_dir3_free_max_bests(mp);
+}
+
+static void
+xfs_dir2_free_hdr_from_disk(
+	struct xfs_dir3_icfree_hdr	*to,
+	struct xfs_dir2_free		*from)
+{
+	to->magic = be32_to_cpu(from->hdr.magic);
+	to->firstdb = be32_to_cpu(from->hdr.firstdb);
+	to->nvalid = be32_to_cpu(from->hdr.nvalid);
+	to->nused = be32_to_cpu(from->hdr.nused);
+	ASSERT(to->magic == XFS_DIR2_FREE_MAGIC);
+}
+
+static void
+xfs_dir2_free_hdr_to_disk(
+	struct xfs_dir2_free		*to,
+	struct xfs_dir3_icfree_hdr	*from)
+{
+	ASSERT(from->magic == XFS_DIR2_FREE_MAGIC);
+
+	to->hdr.magic = cpu_to_be32(from->magic);
+	to->hdr.firstdb = cpu_to_be32(from->firstdb);
+	to->hdr.nvalid = cpu_to_be32(from->nvalid);
+	to->hdr.nused = cpu_to_be32(from->nused);
+}
+
+static void
+xfs_dir3_free_hdr_from_disk(
+	struct xfs_dir3_icfree_hdr	*to,
+	struct xfs_dir2_free		*from)
+{
+	struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)from;
+
+	to->magic = be32_to_cpu(hdr3->hdr.magic);
+	to->firstdb = be32_to_cpu(hdr3->firstdb);
+	to->nvalid = be32_to_cpu(hdr3->nvalid);
+	to->nused = be32_to_cpu(hdr3->nused);
+
+	ASSERT(to->magic == XFS_DIR3_FREE_MAGIC);
+}
+
+static void
+xfs_dir3_free_hdr_to_disk(
+	struct xfs_dir2_free		*to,
+	struct xfs_dir3_icfree_hdr	*from)
+{
+	struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)to;
+
+	ASSERT(from->magic == XFS_DIR3_FREE_MAGIC);
+
+	hdr3->hdr.magic = cpu_to_be32(from->magic);
+	hdr3->firstdb = cpu_to_be32(from->firstdb);
+	hdr3->nvalid = cpu_to_be32(from->nvalid);
+	hdr3->nused = cpu_to_be32(from->nused);
+}
+
+static const struct xfs_dir_ops xfs_dir2_ops = {
+	.sf_entsize = xfs_dir2_sf_entsize,
+	.sf_nextentry = xfs_dir2_sf_nextentry,
+	.sf_get_ftype = xfs_dir2_sfe_get_ftype,
+	.sf_put_ftype = xfs_dir2_sfe_put_ftype,
+	.sf_get_ino = xfs_dir2_sfe_get_ino,
+	.sf_put_ino = xfs_dir2_sfe_put_ino,
+	.sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+	.sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+	.data_entsize = xfs_dir2_data_entsize,
+	.data_get_ftype = xfs_dir2_data_get_ftype,
+	.data_put_ftype = xfs_dir2_data_put_ftype,
+	.data_entry_tag_p = xfs_dir2_data_entry_tag_p,
+	.data_bestfree_p = xfs_dir2_data_bestfree_p,
+
+	.data_dot_offset = sizeof(struct xfs_dir2_data_hdr),
+	.data_dotdot_offset = sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR2_DATA_ENTSIZE(1),
+	.data_first_offset =  sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR2_DATA_ENTSIZE(1) +
+				XFS_DIR2_DATA_ENTSIZE(2),
+	.data_entry_offset = sizeof(struct xfs_dir2_data_hdr),
+
+	.data_dot_entry_p = xfs_dir2_data_dot_entry_p,
+	.data_dotdot_entry_p = xfs_dir2_data_dotdot_entry_p,
+	.data_first_entry_p = xfs_dir2_data_first_entry_p,
+	.data_entry_p = xfs_dir2_data_entry_p,
+	.data_unused_p = xfs_dir2_data_unused_p,
+
+	.leaf_hdr_size = sizeof(struct xfs_dir2_leaf_hdr),
+	.leaf_hdr_to_disk = xfs_dir2_leaf_hdr_to_disk,
+	.leaf_hdr_from_disk = xfs_dir2_leaf_hdr_from_disk,
+	.leaf_max_ents = xfs_dir2_max_leaf_ents,
+	.leaf_ents_p = xfs_dir2_leaf_ents_p,
+
+	.node_hdr_size = sizeof(struct xfs_da_node_hdr),
+	.node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+	.node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+	.node_tree_p = xfs_da2_node_tree_p,
+
+	.free_hdr_size = sizeof(struct xfs_dir2_free_hdr),
+	.free_hdr_to_disk = xfs_dir2_free_hdr_to_disk,
+	.free_hdr_from_disk = xfs_dir2_free_hdr_from_disk,
+	.free_max_bests = xfs_dir2_free_max_bests,
+	.free_bests_p = xfs_dir2_free_bests_p,
+	.db_to_fdb = xfs_dir2_db_to_fdb,
+	.db_to_fdindex = xfs_dir2_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir2_ftype_ops = {
+	.sf_entsize = xfs_dir3_sf_entsize,
+	.sf_nextentry = xfs_dir3_sf_nextentry,
+	.sf_get_ftype = xfs_dir3_sfe_get_ftype,
+	.sf_put_ftype = xfs_dir3_sfe_put_ftype,
+	.sf_get_ino = xfs_dir3_sfe_get_ino,
+	.sf_put_ino = xfs_dir3_sfe_put_ino,
+	.sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+	.sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+	.data_entsize = xfs_dir3_data_entsize,
+	.data_get_ftype = xfs_dir3_data_get_ftype,
+	.data_put_ftype = xfs_dir3_data_put_ftype,
+	.data_entry_tag_p = xfs_dir3_data_entry_tag_p,
+	.data_bestfree_p = xfs_dir2_data_bestfree_p,
+
+	.data_dot_offset = sizeof(struct xfs_dir2_data_hdr),
+	.data_dotdot_offset = sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1),
+	.data_first_offset =  sizeof(struct xfs_dir2_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1) +
+				XFS_DIR3_DATA_ENTSIZE(2),
+	.data_entry_offset = sizeof(struct xfs_dir2_data_hdr),
+
+	.data_dot_entry_p = xfs_dir2_data_dot_entry_p,
+	.data_dotdot_entry_p = xfs_dir2_ftype_data_dotdot_entry_p,
+	.data_first_entry_p = xfs_dir2_ftype_data_first_entry_p,
+	.data_entry_p = xfs_dir2_data_entry_p,
+	.data_unused_p = xfs_dir2_data_unused_p,
+
+	.leaf_hdr_size = sizeof(struct xfs_dir2_leaf_hdr),
+	.leaf_hdr_to_disk = xfs_dir2_leaf_hdr_to_disk,
+	.leaf_hdr_from_disk = xfs_dir2_leaf_hdr_from_disk,
+	.leaf_max_ents = xfs_dir2_max_leaf_ents,
+	.leaf_ents_p = xfs_dir2_leaf_ents_p,
+
+	.node_hdr_size = sizeof(struct xfs_da_node_hdr),
+	.node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+	.node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+	.node_tree_p = xfs_da2_node_tree_p,
+
+	.free_hdr_size = sizeof(struct xfs_dir2_free_hdr),
+	.free_hdr_to_disk = xfs_dir2_free_hdr_to_disk,
+	.free_hdr_from_disk = xfs_dir2_free_hdr_from_disk,
+	.free_max_bests = xfs_dir2_free_max_bests,
+	.free_bests_p = xfs_dir2_free_bests_p,
+	.db_to_fdb = xfs_dir2_db_to_fdb,
+	.db_to_fdindex = xfs_dir2_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir3_ops = {
+	.sf_entsize = xfs_dir3_sf_entsize,
+	.sf_nextentry = xfs_dir3_sf_nextentry,
+	.sf_get_ftype = xfs_dir3_sfe_get_ftype,
+	.sf_put_ftype = xfs_dir3_sfe_put_ftype,
+	.sf_get_ino = xfs_dir3_sfe_get_ino,
+	.sf_put_ino = xfs_dir3_sfe_put_ino,
+	.sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+	.sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+	.data_entsize = xfs_dir3_data_entsize,
+	.data_get_ftype = xfs_dir3_data_get_ftype,
+	.data_put_ftype = xfs_dir3_data_put_ftype,
+	.data_entry_tag_p = xfs_dir3_data_entry_tag_p,
+	.data_bestfree_p = xfs_dir3_data_bestfree_p,
+
+	.data_dot_offset = sizeof(struct xfs_dir3_data_hdr),
+	.data_dotdot_offset = sizeof(struct xfs_dir3_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1),
+	.data_first_offset =  sizeof(struct xfs_dir3_data_hdr) +
+				XFS_DIR3_DATA_ENTSIZE(1) +
+				XFS_DIR3_DATA_ENTSIZE(2),
+	.data_entry_offset = sizeof(struct xfs_dir3_data_hdr),
+
+	.data_dot_entry_p = xfs_dir3_data_dot_entry_p,
+	.data_dotdot_entry_p = xfs_dir3_data_dotdot_entry_p,
+	.data_first_entry_p = xfs_dir3_data_first_entry_p,
+	.data_entry_p = xfs_dir3_data_entry_p,
+	.data_unused_p = xfs_dir3_data_unused_p,
+
+	.leaf_hdr_size = sizeof(struct xfs_dir3_leaf_hdr),
+	.leaf_hdr_to_disk = xfs_dir3_leaf_hdr_to_disk,
+	.leaf_hdr_from_disk = xfs_dir3_leaf_hdr_from_disk,
+	.leaf_max_ents = xfs_dir3_max_leaf_ents,
+	.leaf_ents_p = xfs_dir3_leaf_ents_p,
+
+	.node_hdr_size = sizeof(struct xfs_da3_node_hdr),
+	.node_hdr_to_disk = xfs_da3_node_hdr_to_disk,
+	.node_hdr_from_disk = xfs_da3_node_hdr_from_disk,
+	.node_tree_p = xfs_da3_node_tree_p,
+
+	.free_hdr_size = sizeof(struct xfs_dir3_free_hdr),
+	.free_hdr_to_disk = xfs_dir3_free_hdr_to_disk,
+	.free_hdr_from_disk = xfs_dir3_free_hdr_from_disk,
+	.free_max_bests = xfs_dir3_free_max_bests,
+	.free_bests_p = xfs_dir3_free_bests_p,
+	.db_to_fdb = xfs_dir3_db_to_fdb,
+	.db_to_fdindex = xfs_dir3_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir2_nondir_ops = {
+	.node_hdr_size = sizeof(struct xfs_da_node_hdr),
+	.node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+	.node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+	.node_tree_p = xfs_da2_node_tree_p,
+};
+
+static const struct xfs_dir_ops xfs_dir3_nondir_ops = {
+	.node_hdr_size = sizeof(struct xfs_da3_node_hdr),
+	.node_hdr_to_disk = xfs_da3_node_hdr_to_disk,
+	.node_hdr_from_disk = xfs_da3_node_hdr_from_disk,
+	.node_tree_p = xfs_da3_node_tree_p,
+};
+
+/*
+ * Return the ops structure according to the current config.  If we are passed
+ * an inode, then that overrides the default config we use which is based on
+ * feature bits.
+ */
+const struct xfs_dir_ops *
+xfs_dir_get_ops(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*dp)
+{
+	if (dp)
+		return dp->d_ops;
+	if (mp->m_dir_inode_ops)
+		return mp->m_dir_inode_ops;
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return &xfs_dir3_ops;
+	if (xfs_sb_version_hasftype(&mp->m_sb))
+		return &xfs_dir2_ftype_ops;
+	return &xfs_dir2_ops;
+}
+
+const struct xfs_dir_ops *
+xfs_nondir_get_ops(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*dp)
+{
+	if (dp)
+		return dp->d_ops;
+	if (mp->m_nondir_inode_ops)
+		return mp->m_nondir_inode_ops;
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return &xfs_dir3_nondir_ops;
+	return &xfs_dir2_nondir_ops;
+}

fs/xfs/xfs_dir2_format.h → fs/xfs/xfs_da_format.h

@@ -16,8 +16,113 @@
  * along with this program; if not, write the Free Software Foundation,
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
-#ifndef __XFS_DIR2_FORMAT_H__
-#define __XFS_DIR2_FORMAT_H__
+#ifndef __XFS_DA_FORMAT_H__
+#define __XFS_DA_FORMAT_H__
+
+/*========================================================================
+ * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
+ *========================================================================*/
+
+/*
+ * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
+ *
+ * It is used to manage a doubly linked list of all blocks at the same
+ * level in the Btree, and to identify which type of block this is.
+ */
+#define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
+#define XFS_ATTR_LEAF_MAGIC	0xfbee	/* magic number: attribute leaf blks */
+#define	XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
+#define	XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
+
+typedef struct xfs_da_blkinfo {
+	__be32		forw;			/* previous block in list */
+	__be32		back;			/* following block in list */
+	__be16		magic;			/* validity check on block */
+	__be16		pad;			/* unused */
+} xfs_da_blkinfo_t;
+
+/*
+ * CRC enabled directory structure types
+ *
+ * The headers change size for the additional verification information, but
+ * otherwise the tree layouts and contents are unchanged. Hence the da btree
+ * code can use the struct xfs_da_blkinfo for manipulating the tree links and
+ * magic numbers without modification for both v2 and v3 nodes.
+ */
+#define XFS_DA3_NODE_MAGIC	0x3ebe	/* magic number: non-leaf blocks */
+#define XFS_ATTR3_LEAF_MAGIC	0x3bee	/* magic number: attribute leaf blks */
+#define	XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v2 dirlf single blks */
+#define	XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v2 dirlf multi blks */
+
+struct xfs_da3_blkinfo {
+	/*
+	 * the node link manipulation code relies on the fact that the first
+	 * element of this structure is the struct xfs_da_blkinfo so it can
+	 * ignore the differences in the rest of the structures.
+	 */
+	struct xfs_da_blkinfo	hdr;
+	__be32			crc;	/* CRC of block */
+	__be64			blkno;	/* first block of the buffer */
+	__be64			lsn;	/* sequence number of last write */
+	uuid_t			uuid;	/* filesystem we belong to */
+	__be64			owner;	/* inode that owns the block */
+};
+
+/*
+ * This is the structure of the root and intermediate nodes in the Btree.
+ * The leaf nodes are defined above.
+ *
+ * Entries are not packed.
+ *
+ * Since we have duplicate keys, use a binary search but always follow
+ * all match in the block, not just the first match found.
+ */
+#define	XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
+
+typedef struct xfs_da_node_hdr {
+	struct xfs_da_blkinfo	info;	/* block type, links, etc. */
+	__be16			__count; /* count of active entries */
+	__be16			__level; /* level above leaves (leaf == 0) */
+} xfs_da_node_hdr_t;
+
+struct xfs_da3_node_hdr {
+	struct xfs_da3_blkinfo	info;	/* block type, links, etc. */
+	__be16			__count; /* count of active entries */
+	__be16			__level; /* level above leaves (leaf == 0) */
+	__be32			__pad32;
+};
+
+#define XFS_DA3_NODE_CRC_OFF	(offsetof(struct xfs_da3_node_hdr, info.crc))
+
+typedef struct xfs_da_node_entry {
+	__be32	hashval;	/* hash value for this descendant */
+	__be32	before;		/* Btree block before this key */
+} xfs_da_node_entry_t;
+
+typedef struct xfs_da_intnode {
+	struct xfs_da_node_hdr	hdr;
+	struct xfs_da_node_entry __btree[];
+} xfs_da_intnode_t;
+
+struct xfs_da3_intnode {
+	struct xfs_da3_node_hdr	hdr;
+	struct xfs_da_node_entry __btree[];
+};
+
+/*
+ * In-core version of the node header to abstract the differences in the v2 and
+ * v3 disk format of the headers. Callers need to convert to/from disk format as
+ * appropriate.
+ */
+struct xfs_da3_icnode_hdr {
+	__uint32_t	forw;
+	__uint32_t	back;
+	__uint16_t	magic;
+	__uint16_t	count;
+	__uint16_t	level;
+};
+
+#define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
 
 /*
  * Directory version 2.
@@ -189,79 +294,6 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
 		((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count));
 }
 
-static inline int
-xfs_dir3_sf_entsize(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	int			len)
-{
-	int count = sizeof(struct xfs_dir2_sf_entry); 	/* namelen + offset */
-
-	count += len;					/* name */
-	count += hdr->i8count ? sizeof(xfs_dir2_ino8_t) :
-				sizeof(xfs_dir2_ino4_t); /* ino # */
-	if (xfs_sb_version_hasftype(&mp->m_sb))
-		count += sizeof(__uint8_t);		/* file type */
-	return count;
-}
-
-static inline struct xfs_dir2_sf_entry *
-xfs_dir3_sf_nextentry(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	return (struct xfs_dir2_sf_entry *)
-		((char *)sfep + xfs_dir3_sf_entsize(mp, hdr, sfep->namelen));
-}
-
-/*
- * in dir3 shortform directories, the file type field is stored at a variable
- * offset after the inode number. Because it's only a single byte, endian
- * conversion is not necessary.
- */
-static inline __uint8_t *
-xfs_dir3_sfe_ftypep(
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	return (__uint8_t *)&sfep->name[sfep->namelen];
-}
-
-static inline __uint8_t
-xfs_dir3_sfe_get_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	__uint8_t	*ftp;
-
-	if (!xfs_sb_version_hasftype(&mp->m_sb))
-		return XFS_DIR3_FT_UNKNOWN;
-
-	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
-	if (*ftp >= XFS_DIR3_FT_MAX)
-		return XFS_DIR3_FT_UNKNOWN;
-	return *ftp;
-}
-
-static inline void
-xfs_dir3_sfe_put_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
-{
-	__uint8_t	*ftp;
-
-	ASSERT(ftype < XFS_DIR3_FT_MAX);
-
-	if (!xfs_sb_version_hasftype(&mp->m_sb))
-		return;
-	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
-	*ftp = ftype;
-}
-
 /*
  * Data block structures.
  *
@@ -345,17 +377,6 @@ struct xfs_dir3_data_hdr {
 
 #define XFS_DIR3_DATA_CRC_OFF  offsetof(struct xfs_dir3_data_hdr, hdr.crc)
 
-static inline struct xfs_dir2_data_free *
-xfs_dir3_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
-{
-	if (hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-		struct xfs_dir3_data_hdr *hdr3 = (struct xfs_dir3_data_hdr *)hdr;
-		return hdr3->best_free;
-	}
-	return hdr->bestfree;
-}
-
 /*
  * Active entry in a data block.
  *
@@ -388,72 +409,6 @@ typedef struct xfs_dir2_data_unused {
 	__be16			tag;		/* starting offset of us */
 } xfs_dir2_data_unused_t;
 
-/*
- * Size of a data entry.
- */
-static inline int
-__xfs_dir3_data_entsize(
-	bool	ftype,
-	int	n)
-{
-	int	size = offsetof(struct xfs_dir2_data_entry, name[0]);
-
-	size += n;
-	size += sizeof(xfs_dir2_data_off_t);
-	if (ftype)
-		size += sizeof(__uint8_t);
-	return roundup(size, XFS_DIR2_DATA_ALIGN);
-}
-static inline int
-xfs_dir3_data_entsize(
-	struct xfs_mount	*mp,
-	int			n)
-{
-	bool ftype = xfs_sb_version_hasftype(&mp->m_sb) ? true : false;
-	return __xfs_dir3_data_entsize(ftype, n);
-}
-
-static inline __uint8_t
-xfs_dir3_dirent_get_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep)
-{
-	if (xfs_sb_version_hasftype(&mp->m_sb)) {
-		__uint8_t	type = dep->name[dep->namelen];
-
-		ASSERT(type < XFS_DIR3_FT_MAX);
-		if (type < XFS_DIR3_FT_MAX)
-			return type;
-
-	}
-	return XFS_DIR3_FT_UNKNOWN;
-}
-
-static inline void
-xfs_dir3_dirent_put_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep,
-	__uint8_t		type)
-{
-	ASSERT(type < XFS_DIR3_FT_MAX);
-	ASSERT(dep->namelen != 0);
-
-	if (xfs_sb_version_hasftype(&mp->m_sb))
-		dep->name[dep->namelen] = type;
-}
-
-/*
- * Pointer to an entry's tag word.
- */
-static inline __be16 *
-xfs_dir3_data_entry_tag_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep)
-{
-	return (__be16 *)((char *)dep +
-		xfs_dir3_data_entsize(mp, dep->namelen) - sizeof(__be16));
-}
-
 /*
  * Pointer to a freespace's tag word.
  */
@@ -464,93 +419,6 @@ xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
 			be16_to_cpu(dup->length) - sizeof(__be16));
 }
 
-static inline size_t
-xfs_dir3_data_hdr_size(bool dir3)
-{
-	if (dir3)
-		return sizeof(struct xfs_dir3_data_hdr);
-	return sizeof(struct xfs_dir2_data_hdr);
-}
-
-static inline size_t
-xfs_dir3_data_entry_offset(struct xfs_dir2_data_hdr *hdr)
-{
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_hdr_size(dir3);
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_entry_p(struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
-}
-
-static inline struct xfs_dir2_data_unused *
-xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_unused *)
-		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
-}
-
-/*
- * Offsets of . and .. in data space (always block 0)
- *
- * XXX: there is scope for significant optimisation of the logic here. Right
- * now we are checking for "dir3 format" over and over again. Ideally we should
- * only do it once for each operation.
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dot_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_dot_offset(mp) +
-		xfs_dir3_data_entsize(mp, 1);
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_first_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_dotdot_offset(mp) +
-		xfs_dir3_data_entsize(mp, 2);
-}
-
-/*
- * location of . and .. in data space (always block 0)
- */
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dot_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dot_offset(mp));
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dotdot_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_first_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_first_offset(mp));
-}
-
 /*
  * Leaf block structures.
  *
@@ -645,39 +513,6 @@ struct xfs_dir3_leaf {
 
 #define XFS_DIR3_LEAF_CRC_OFF  offsetof(struct xfs_dir3_leaf_hdr, info.crc)
 
-extern void xfs_dir3_leaf_hdr_from_disk(struct xfs_dir3_icleaf_hdr *to,
-					struct xfs_dir2_leaf *from);
-
-static inline int
-xfs_dir3_leaf_hdr_size(struct xfs_dir2_leaf *lp)
-{
-	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
-	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC))
-		return sizeof(struct xfs_dir3_leaf_hdr);
-	return sizeof(struct xfs_dir2_leaf_hdr);
-}
-
-static inline int
-xfs_dir3_max_leaf_ents(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
-	return (mp->m_dirblksize - xfs_dir3_leaf_hdr_size(lp)) /
-		(uint)sizeof(struct xfs_dir2_leaf_entry);
-}
-
-/*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_entry *
-xfs_dir3_leaf_ents_p(struct xfs_dir2_leaf *lp)
-{
-	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
-	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
-		struct xfs_dir3_leaf *lp3 = (struct xfs_dir3_leaf *)lp;
-		return lp3->__ents;
-	}
-	return lp->__ents;
-}
-
 /*
  * Get address of the bestcount field in the single-leaf block.
  */
@@ -869,48 +704,6 @@ struct xfs_dir3_icfree_hdr {
 
 };
 
-void xfs_dir3_free_hdr_from_disk(struct xfs_dir3_icfree_hdr *to,
-				 struct xfs_dir2_free *from);
-
-static inline int
-xfs_dir3_free_hdr_size(struct xfs_mount *mp)
-{
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		return sizeof(struct xfs_dir3_free_hdr);
-	return sizeof(struct xfs_dir2_free_hdr);
-}
-
-static inline int
-xfs_dir3_free_max_bests(struct xfs_mount *mp)
-{
-	return (mp->m_dirblksize - xfs_dir3_free_hdr_size(mp)) /
-		sizeof(xfs_dir2_data_off_t);
-}
-
-static inline __be16 *
-xfs_dir3_free_bests_p(struct xfs_mount *mp, struct xfs_dir2_free *free)
-{
-	return (__be16 *)((char *)free + xfs_dir3_free_hdr_size(mp));
-}
-
-/*
- * Convert data space db to the corresponding free db.
- */
-static inline xfs_dir2_db_t
-xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
-}
-
-/*
- * Convert data space db to the corresponding index in a free db.
- */
-static inline int
-xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return db % xfs_dir3_free_max_bests(mp);
-}
-
 /*
  * Single block format.
  *
@@ -961,4 +754,262 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
 	return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count);
 }
 
-#endif /* __XFS_DIR2_FORMAT_H__ */
+
+/*
+ * Attribute storage layout
+ *
+ * Attribute lists are structured around Btrees where all the data
+ * elements are in the leaf nodes.  Attribute names are hashed into an int,
+ * then that int is used as the index into the Btree.  Since the hashval
+ * of an attribute name may not be unique, we may have duplicate keys.  The
+ * internal links in the Btree are logical block offsets into the file.
+ *
+ *========================================================================
+ * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
+ *========================================================================
+ *
+ * Struct leaf_entry's are packed from the top.  Name/values grow from the
+ * bottom but are not packed.  The freemap contains run-length-encoded entries
+ * for the free bytes after the leaf_entry's, but only the N largest such,
+ * smaller runs are dropped.  When the freemap doesn't show enough space
+ * for an allocation, we compact the name/value area and try again.  If we
+ * still don't have enough space, then we have to split the block.  The
+ * name/value structs (both local and remote versions) must be 32bit aligned.
+ *
+ * Since we have duplicate hash keys, for each key that matches, compare
+ * the actual name string.  The root and intermediate node search always
+ * takes the first-in-the-block key match found, so we should only have
+ * to work "forw"ard.  If none matches, continue with the "forw"ard leaf
+ * nodes until the hash key changes or the attribute name is found.
+ *
+ * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
+ * the leaf_entry.  The namespaces are independent only because we also look
+ * at the namespace bit when we are looking for a matching attribute name.
+ *
+ * We also store an "incomplete" bit in the leaf_entry.  It shows that an
+ * attribute is in the middle of being created and should not be shown to
+ * the user if we crash during the time that the bit is set.  We clear the
+ * bit when we have finished setting up the attribute.  We do this because
+ * we cannot create some large attributes inside a single transaction, and we
+ * need some indication that we weren't finished if we crash in the middle.
+ */
+#define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
+
+typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
+	__be16	base;			  /* base of free region */
+	__be16	size;			  /* length of free region */
+} xfs_attr_leaf_map_t;
+
+typedef struct xfs_attr_leaf_hdr {	/* constant-structure header block */
+	xfs_da_blkinfo_t info;		/* block type, links, etc. */
+	__be16	count;			/* count of active leaf_entry's */
+	__be16	usedbytes;		/* num bytes of names/values stored */
+	__be16	firstused;		/* first used byte in name area */
+	__u8	holes;			/* != 0 if blk needs compaction */
+	__u8	pad1;
+	xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
+					/* N largest free regions */
+} xfs_attr_leaf_hdr_t;
+
+typedef struct xfs_attr_leaf_entry {	/* sorted on key, not name */
+	__be32	hashval;		/* hash value of name */
+	__be16	nameidx;		/* index into buffer of name/value */
+	__u8	flags;			/* LOCAL/ROOT/SECURE/INCOMPLETE flag */
+	__u8	pad2;			/* unused pad byte */
+} xfs_attr_leaf_entry_t;
+
+typedef struct xfs_attr_leaf_name_local {
+	__be16	valuelen;		/* number of bytes in value */
+	__u8	namelen;		/* length of name bytes */
+	__u8	nameval[1];		/* name/value bytes */
+} xfs_attr_leaf_name_local_t;
+
+typedef struct xfs_attr_leaf_name_remote {
+	__be32	valueblk;		/* block number of value bytes */
+	__be32	valuelen;		/* number of bytes in value */
+	__u8	namelen;		/* length of name bytes */
+	__u8	name[1];		/* name bytes */
+} xfs_attr_leaf_name_remote_t;
+
+typedef struct xfs_attr_leafblock {
+	xfs_attr_leaf_hdr_t	hdr;	/* constant-structure header block */
+	xfs_attr_leaf_entry_t	entries[1];	/* sorted on key, not name */
+	xfs_attr_leaf_name_local_t namelist;	/* grows from bottom of buf */
+	xfs_attr_leaf_name_remote_t valuelist;	/* grows from bottom of buf */
+} xfs_attr_leafblock_t;
+
+/*
+ * CRC enabled leaf structures. Called "version 3" structures to match the
+ * version number of the directory and dablk structures for this feature, and
+ * attr2 is already taken by the variable inode attribute fork size feature.
+ */
+struct xfs_attr3_leaf_hdr {
+	struct xfs_da3_blkinfo	info;
+	__be16			count;
+	__be16			usedbytes;
+	__be16			firstused;
+	__u8			holes;
+	__u8			pad1;
+	struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE];
+	__be32			pad2;		/* 64 bit alignment */
+};
+
+#define XFS_ATTR3_LEAF_CRC_OFF	(offsetof(struct xfs_attr3_leaf_hdr, info.crc))
+
+struct xfs_attr3_leafblock {
+	struct xfs_attr3_leaf_hdr	hdr;
+	struct xfs_attr_leaf_entry	entries[1];
+
+	/*
+	 * The rest of the block contains the following structures after the
+	 * leaf entries, growing from the bottom up. The variables are never
+	 * referenced, the locations accessed purely from helper functions.
+	 *
+	 * struct xfs_attr_leaf_name_local
+	 * struct xfs_attr_leaf_name_remote
+	 */
+};
+
+/*
+ * incore, neutral version of the attribute leaf header
+ */
+struct xfs_attr3_icleaf_hdr {
+	__uint32_t	forw;
+	__uint32_t	back;
+	__uint16_t	magic;
+	__uint16_t	count;
+	__uint16_t	usedbytes;
+	__uint16_t	firstused;
+	__u8		holes;
+	struct {
+		__uint16_t	base;
+		__uint16_t	size;
+	} freemap[XFS_ATTR_LEAF_MAPSIZE];
+};
+
+/*
+ * Flags used in the leaf_entry[i].flags field.
+ * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
+ * on the system call, they are "or"ed together for various operations.
+ */
+#define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
+#define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
+#define	XFS_ATTR_SECURE_BIT	2	/* limit access to secure attrs */
+#define	XFS_ATTR_INCOMPLETE_BIT	7	/* attr in middle of create/delete */
+#define XFS_ATTR_LOCAL		(1 << XFS_ATTR_LOCAL_BIT)
+#define XFS_ATTR_ROOT		(1 << XFS_ATTR_ROOT_BIT)
+#define XFS_ATTR_SECURE		(1 << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_INCOMPLETE	(1 << XFS_ATTR_INCOMPLETE_BIT)
+
+/*
+ * Conversion macros for converting namespace bits from argument flags
+ * to ondisk flags.
+ */
+#define XFS_ATTR_NSP_ARGS_MASK		(ATTR_ROOT | ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK(flags)	((flags) & XFS_ATTR_NSP_ONDISK_MASK)
+#define XFS_ATTR_NSP_ARGS(flags)	((flags) & XFS_ATTR_NSP_ARGS_MASK)
+#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x)	(((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
+					 ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
+#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x)	(((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
+					 ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
+
+/*
+ * Alignment for namelist and valuelist entries (since they are mixed
+ * there can be only one alignment value)
+ */
+#define	XFS_ATTR_LEAF_NAME_ALIGN	((uint)sizeof(xfs_dablk_t))
+
+static inline int
+xfs_attr3_leaf_hdr_size(struct xfs_attr_leafblock *leafp)
+{
+	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+		return sizeof(struct xfs_attr3_leaf_hdr);
+	return sizeof(struct xfs_attr_leaf_hdr);
+}
+
+static inline struct xfs_attr_leaf_entry *
+xfs_attr3_leaf_entryp(xfs_attr_leafblock_t *leafp)
+{
+	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+		return &((struct xfs_attr3_leafblock *)leafp)->entries[0];
+	return &leafp->entries[0];
+}
+
+/*
+ * Cast typed pointers for "local" and "remote" name/value structs.
+ */
+static inline char *
+xfs_attr3_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
+{
+	struct xfs_attr_leaf_entry *entries = xfs_attr3_leaf_entryp(leafp);
+
+	return &((char *)leafp)[be16_to_cpu(entries[idx].nameidx)];
+}
+
+static inline xfs_attr_leaf_name_remote_t *
+xfs_attr3_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
+{
+	return (xfs_attr_leaf_name_remote_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+static inline xfs_attr_leaf_name_local_t *
+xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
+{
+	return (xfs_attr_leaf_name_local_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+/*
+ * Calculate total bytes used (including trailing pad for alignment) for
+ * a "local" name/value structure, a "remote" name/value structure, and
+ * a pointer which might be either.
+ */
+static inline int xfs_attr_leaf_entsize_remote(int nlen)
+{
+	return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
+		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
+{
+	return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
+		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local_max(int bsize)
+{
+	return (((bsize) >> 1) + ((bsize) >> 2));
+}
+
+
+
+/*
+ * Remote attribute block format definition
+ *
+ * There is one of these headers per filesystem block in a remote attribute.
+ * This is done to ensure there is a 1:1 mapping between the attribute value
+ * length and the number of blocks needed to store the attribute. This makes the
+ * verification of a buffer a little more complex, but greatly simplifies the
+ * allocation, reading and writing of these attributes as we don't have to guess
+ * the number of blocks needed to store the attribute data.
+ */
+#define XFS_ATTR3_RMT_MAGIC	0x5841524d	/* XARM */
+
+struct xfs_attr3_rmt_hdr {
+	__be32	rm_magic;
+	__be32	rm_offset;
+	__be32	rm_bytes;
+	__be32	rm_crc;
+	uuid_t	rm_uuid;
+	__be64	rm_owner;
+	__be64	rm_blkno;
+	__be64	rm_lsn;
+};
+
+#define XFS_ATTR3_RMT_CRC_OFF	offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
+
+#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize)	\
+	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
+			sizeof(struct xfs_attr3_rmt_hdr) : 0))
+
+#endif /* __XFS_DA_FORMAT_H__ */

fs/xfs/xfs_dir2.c

@@ -17,25 +17,24 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_dinode.h"
 
 struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
 
@@ -96,13 +95,17 @@ xfs_dir_mount(
 	ASSERT(xfs_sb_version_hasdirv2(&mp->m_sb));
 	ASSERT((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) <=
 	       XFS_MAX_BLOCKSIZE);
+
+	mp->m_dir_inode_ops = xfs_dir_get_ops(mp, NULL);
+	mp->m_nondir_inode_ops = xfs_nondir_get_ops(mp, NULL);
+
 	mp->m_dirblksize = 1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog);
 	mp->m_dirblkfsbs = 1 << mp->m_sb.sb_dirblklog;
 	mp->m_dirdatablk = xfs_dir2_db_to_da(mp, XFS_DIR2_DATA_FIRSTDB(mp));
 	mp->m_dirleafblk = xfs_dir2_db_to_da(mp, XFS_DIR2_LEAF_FIRSTDB(mp));
 	mp->m_dirfreeblk = xfs_dir2_db_to_da(mp, XFS_DIR2_FREE_FIRSTDB(mp));
 
-	nodehdr_size = __xfs_da3_node_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
+	nodehdr_size = mp->m_dir_inode_ops->node_hdr_size;
 	mp->m_attr_node_ents = (mp->m_sb.sb_blocksize - nodehdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
 	mp->m_dir_node_ents = (mp->m_dirblksize - nodehdr_size) /
@@ -113,6 +116,7 @@ xfs_dir_mount(
 		mp->m_dirnameops = &xfs_ascii_ci_nameops;
 	else
 		mp->m_dirnameops = &xfs_default_nameops;
+
 }
 
 /*

fs/xfs/xfs_dir2.h

@@ -31,6 +31,83 @@ struct xfs_dir2_data_unused;
 
 extern struct xfs_name	xfs_name_dotdot;
 
+/*
+ * directory operations vector for encode/decode routines
+ */
+struct xfs_dir_ops {
+	int	(*sf_entsize)(struct xfs_dir2_sf_hdr *hdr, int len);
+	struct xfs_dir2_sf_entry *
+		(*sf_nextentry)(struct xfs_dir2_sf_hdr *hdr,
+				struct xfs_dir2_sf_entry *sfep);
+	__uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
+	void	(*sf_put_ftype)(struct xfs_dir2_sf_entry *sfep,
+				__uint8_t ftype);
+	xfs_ino_t (*sf_get_ino)(struct xfs_dir2_sf_hdr *hdr,
+				struct xfs_dir2_sf_entry *sfep);
+	void	(*sf_put_ino)(struct xfs_dir2_sf_hdr *hdr,
+			      struct xfs_dir2_sf_entry *sfep,
+			      xfs_ino_t ino);
+	xfs_ino_t (*sf_get_parent_ino)(struct xfs_dir2_sf_hdr *hdr);
+	void	(*sf_put_parent_ino)(struct xfs_dir2_sf_hdr *hdr,
+				     xfs_ino_t ino);
+
+	int	(*data_entsize)(int len);
+	__uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
+	void	(*data_put_ftype)(struct xfs_dir2_data_entry *dep,
+				__uint8_t ftype);
+	__be16 * (*data_entry_tag_p)(struct xfs_dir2_data_entry *dep);
+	struct xfs_dir2_data_free *
+		(*data_bestfree_p)(struct xfs_dir2_data_hdr *hdr);
+
+	xfs_dir2_data_aoff_t data_dot_offset;
+	xfs_dir2_data_aoff_t data_dotdot_offset;
+	xfs_dir2_data_aoff_t data_first_offset;
+	size_t	data_entry_offset;
+
+	struct xfs_dir2_data_entry *
+		(*data_dot_entry_p)(struct xfs_dir2_data_hdr *hdr);
+	struct xfs_dir2_data_entry *
+		(*data_dotdot_entry_p)(struct xfs_dir2_data_hdr *hdr);
+	struct xfs_dir2_data_entry *
+		(*data_first_entry_p)(struct xfs_dir2_data_hdr *hdr);
+	struct xfs_dir2_data_entry *
+		(*data_entry_p)(struct xfs_dir2_data_hdr *hdr);
+	struct xfs_dir2_data_unused *
+		(*data_unused_p)(struct xfs_dir2_data_hdr *hdr);
+
+	int	leaf_hdr_size;
+	void	(*leaf_hdr_to_disk)(struct xfs_dir2_leaf *to,
+				    struct xfs_dir3_icleaf_hdr *from);
+	void	(*leaf_hdr_from_disk)(struct xfs_dir3_icleaf_hdr *to,
+				      struct xfs_dir2_leaf *from);
+	int	(*leaf_max_ents)(struct xfs_mount *mp);
+	struct xfs_dir2_leaf_entry *
+		(*leaf_ents_p)(struct xfs_dir2_leaf *lp);
+
+	int	node_hdr_size;
+	void	(*node_hdr_to_disk)(struct xfs_da_intnode *to,
+				    struct xfs_da3_icnode_hdr *from);
+	void	(*node_hdr_from_disk)(struct xfs_da3_icnode_hdr *to,
+				      struct xfs_da_intnode *from);
+	struct xfs_da_node_entry *
+		(*node_tree_p)(struct xfs_da_intnode *dap);
+
+	int	free_hdr_size;
+	void	(*free_hdr_to_disk)(struct xfs_dir2_free *to,
+				    struct xfs_dir3_icfree_hdr *from);
+	void	(*free_hdr_from_disk)(struct xfs_dir3_icfree_hdr *to,
+				      struct xfs_dir2_free *from);
+	int	(*free_max_bests)(struct xfs_mount *mp);
+	__be16 * (*free_bests_p)(struct xfs_dir2_free *free);
+	xfs_dir2_db_t (*db_to_fdb)(struct xfs_mount *mp, xfs_dir2_db_t db);
+	int	(*db_to_fdindex)(struct xfs_mount *mp, xfs_dir2_db_t db);
+};
+
+extern const struct xfs_dir_ops *
+	xfs_dir_get_ops(struct xfs_mount *mp, struct xfs_inode *dp);
+extern const struct xfs_dir_ops *
+	xfs_nondir_get_ops(struct xfs_mount *mp, struct xfs_inode *dp);
+
 /*
  * Generic directory interface routines
  */
@@ -65,37 +142,30 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
 /*
  * Interface routines used by userspace utilities
  */
-extern xfs_ino_t xfs_dir2_sf_get_parent_ino(struct xfs_dir2_sf_hdr *sfp);
-extern void xfs_dir2_sf_put_parent_ino(struct xfs_dir2_sf_hdr *sfp,
-		xfs_ino_t ino);
-extern xfs_ino_t xfs_dir3_sfe_get_ino(struct xfs_mount *mp,
-		struct xfs_dir2_sf_hdr *sfp, struct xfs_dir2_sf_entry *sfep);
-extern void xfs_dir3_sfe_put_ino(struct xfs_mount *mp,
-		struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep,
-		xfs_ino_t ino);
-
 extern int xfs_dir2_isblock(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
 extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
 				struct xfs_buf *bp);
 
-extern void xfs_dir2_data_freescan(struct xfs_mount *mp,
+extern void xfs_dir2_data_freescan(struct xfs_inode *dp,
 		struct xfs_dir2_data_hdr *hdr, int *loghead);
-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,
+extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_inode *dp,
+		struct xfs_buf *bp, struct xfs_dir2_data_entry *dep);
+extern void xfs_dir2_data_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
 		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_buf *bp,
+extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_inode *dp,
+		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_inode *dp,
+		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);
-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);
 
 extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
-		struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_unused *dup);
+		struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf,
+		struct xfs_dir2_data_unused *dup);
 
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;

fs/xfs/xfs_dir2_block.c

@@ -18,25 +18,25 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_buf_item.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_dinode.h"
 
 /*
  * Local function prototypes.
@@ -168,6 +168,7 @@ xfs_dir3_block_init(
 
 static void
 xfs_dir2_block_need_space(
+	struct xfs_inode		*dp,
 	struct xfs_dir2_data_hdr	*hdr,
 	struct xfs_dir2_block_tail	*btp,
 	struct xfs_dir2_leaf_entry	*blp,
@@ -183,7 +184,7 @@ xfs_dir2_block_need_space(
 	struct xfs_dir2_data_unused	*enddup = NULL;
 
 	*compact = 0;
-	bf = xfs_dir3_data_bestfree_p(hdr);
+	bf = dp->d_ops->data_bestfree_p(hdr);
 
 	/*
 	 * If there are stale entries we'll use one for the leaf.
@@ -280,6 +281,7 @@ out:
 static void
 xfs_dir2_block_compact(
 	struct xfs_trans		*tp,
+	struct xfs_inode		*dp,
 	struct xfs_buf			*bp,
 	struct xfs_dir2_data_hdr	*hdr,
 	struct xfs_dir2_block_tail	*btp,
@@ -312,7 +314,7 @@ xfs_dir2_block_compact(
 	*lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
 	*lfloghigh -= be32_to_cpu(btp->stale) - 1;
 	be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
-	xfs_dir2_data_make_free(tp, bp,
+	xfs_dir2_data_make_free(tp, dp, bp,
 		(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
 		(xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
 		needlog, &needscan);
@@ -323,7 +325,7 @@ xfs_dir2_block_compact(
 	 * This needs to happen before the next call to use_free.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(tp->t_mountp, hdr, needlog);
+		xfs_dir2_data_freescan(dp, hdr, needlog);
 }
 
 /*
@@ -369,7 +371,7 @@ xfs_dir2_block_addname(
 	if (error)
 		return error;
 
-	len = xfs_dir3_data_entsize(mp, args->namelen);
+	len = dp->d_ops->data_entsize(args->namelen);
 
 	/*
 	 * Set up pointers to parts of the block.
@@ -382,7 +384,7 @@ xfs_dir2_block_addname(
 	 * Find out if we can reuse stale entries or whether we need extra
 	 * space for entry and new leaf.
 	 */
-	xfs_dir2_block_need_space(hdr, btp, blp, &tagp, &dup,
+	xfs_dir2_block_need_space(dp, hdr, btp, blp, &tagp, &dup,
 				  &enddup, &compact, len);
 
 	/*
@@ -418,7 +420,7 @@ xfs_dir2_block_addname(
 	 * If need to compact the leaf entries, do it now.
 	 */
 	if (compact) {
-		xfs_dir2_block_compact(tp, bp, hdr, btp, blp, &needlog,
+		xfs_dir2_block_compact(tp, dp, bp, hdr, btp, blp, &needlog,
 				      &lfloghigh, &lfloglow);
 		/* recalculate blp post-compaction */
 		blp = xfs_dir2_block_leaf_p(btp);
@@ -453,7 +455,7 @@ xfs_dir2_block_addname(
 		/*
 		 * Mark the space needed for the new leaf entry, now in use.
 		 */
-		xfs_dir2_data_use_free(tp, bp, enddup,
+		xfs_dir2_data_use_free(tp, dp, bp, enddup,
 			(xfs_dir2_data_aoff_t)
 			((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
 			 sizeof(*blp)),
@@ -468,7 +470,7 @@ xfs_dir2_block_addname(
 		 * This needs to happen before the next call to use_free.
 		 */
 		if (needscan) {
-			xfs_dir2_data_freescan(mp, hdr, &needlog);
+			xfs_dir2_data_freescan(dp, hdr, &needlog);
 			needscan = 0;
 		}
 		/*
@@ -540,7 +542,7 @@ xfs_dir2_block_addname(
 	/*
 	 * Mark space for the data entry used.
 	 */
-	xfs_dir2_data_use_free(tp, bp, dup,
+	xfs_dir2_data_use_free(tp, dp, bp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
 		(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
 	/*
@@ -549,18 +551,18 @@ xfs_dir2_block_addname(
 	dep->inumber = cpu_to_be64(args->inumber);
 	dep->namelen = args->namelen;
 	memcpy(dep->name, args->name, args->namelen);
-	xfs_dir3_dirent_put_ftype(mp, dep, args->filetype);
-	tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+	dp->d_ops->data_put_ftype(dep, args->filetype);
+	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
 	/*
 	 * Clean up the bestfree array and log the header, tail, and entry.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, bp);
+		xfs_dir2_data_log_header(tp, dp, bp);
 	xfs_dir2_block_log_tail(tp, bp);
-	xfs_dir2_data_log_entry(tp, bp, dep);
+	xfs_dir2_data_log_entry(tp, dp, bp, dep);
 	xfs_dir3_data_check(dp, bp);
 	return 0;
 }
@@ -642,7 +644,7 @@ xfs_dir2_block_lookup(
 	 * Fill in inode number, CI name if appropriate, release the block.
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
-	args->filetype = xfs_dir3_dirent_get_ftype(mp, dep);
+	args->filetype = dp->d_ops->data_get_ftype(dep);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
 	xfs_trans_brelse(args->trans, bp);
 	return XFS_ERROR(error);
@@ -799,9 +801,9 @@ xfs_dir2_block_removename(
 	 * Mark the data entry's space free.
 	 */
 	needlog = needscan = 0;
-	xfs_dir2_data_make_free(tp, bp,
+	xfs_dir2_data_make_free(tp, dp, bp,
 		(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
-		xfs_dir3_data_entsize(mp, dep->namelen), &needlog, &needscan);
+		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
 	 * Fix up the block tail.
 	 */
@@ -816,9 +818,9 @@ xfs_dir2_block_removename(
 	 * Fix up bestfree, log the header if necessary.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, bp);
+		xfs_dir2_data_log_header(tp, dp, bp);
 	xfs_dir3_data_check(dp, bp);
 	/*
 	 * See if the size as a shortform is good enough.
@@ -875,8 +877,8 @@ xfs_dir2_block_replace(
 	 * Change the inode number to the new value.
 	 */
 	dep->inumber = cpu_to_be64(args->inumber);
-	xfs_dir3_dirent_put_ftype(mp, dep, args->filetype);
-	xfs_dir2_data_log_entry(args->trans, bp, dep);
+	dp->d_ops->data_put_ftype(dep, args->filetype);
+	xfs_dir2_data_log_entry(args->trans, dp, bp, dep);
 	xfs_dir3_data_check(dp, bp);
 	return 0;
 }
@@ -934,8 +936,8 @@ xfs_dir2_leaf_to_block(
 	tp = args->trans;
 	mp = dp->i_mount;
 	leaf = lbp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
@@ -949,7 +951,7 @@ xfs_dir2_leaf_to_block(
 	while (dp->i_d.di_size > mp->m_dirblksize) {
 		int hdrsz;
 
-		hdrsz = xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
+		hdrsz = dp->d_ops->data_entry_offset;
 		bestsp = xfs_dir2_leaf_bests_p(ltp);
 		if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) ==
 					    mp->m_dirblksize - hdrsz) {
@@ -999,7 +1001,7 @@ xfs_dir2_leaf_to_block(
 	/*
 	 * Use up the space at the end of the block (blp/btp).
 	 */
-	xfs_dir2_data_use_free(tp, dbp, dup, mp->m_dirblksize - size, size,
+	xfs_dir2_data_use_free(tp, dp, dbp, dup, mp->m_dirblksize - size, size,
 		&needlog, &needscan);
 	/*
 	 * Initialize the block tail.
@@ -1023,9 +1025,9 @@ xfs_dir2_leaf_to_block(
 	 * Scan the bestfree if we need it and log the data block header.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
+		xfs_dir2_data_log_header(tp, dp, dbp);
 	/*
 	 * Pitch the old leaf block.
 	 */
@@ -1136,9 +1138,9 @@ xfs_dir2_sf_to_block(
 	 * The whole thing is initialized to free by the init routine.
 	 * Say we're using the leaf and tail area.
 	 */
-	dup = xfs_dir3_data_unused_p(hdr);
+	dup = dp->d_ops->data_unused_p(hdr);
 	needlog = needscan = 0;
-	xfs_dir2_data_use_free(tp, bp, dup, mp->m_dirblksize - i, i, &needlog,
+	xfs_dir2_data_use_free(tp, dp, bp, dup, mp->m_dirblksize - i, i, &needlog,
 		&needscan);
 	ASSERT(needscan == 0);
 	/*
@@ -1152,38 +1154,38 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Remove the freespace, we'll manage it.
 	 */
-	xfs_dir2_data_use_free(tp, bp, dup,
+	xfs_dir2_data_use_free(tp, dp, bp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
 		be16_to_cpu(dup->length), &needlog, &needscan);
 	/*
 	 * Create entry for .
 	 */
-	dep = xfs_dir3_data_dot_entry_p(mp, hdr);
+	dep = dp->d_ops->data_dot_entry_p(hdr);
 	dep->inumber = cpu_to_be64(dp->i_ino);
 	dep->namelen = 1;
 	dep->name[0] = '.';
-	xfs_dir3_dirent_put_ftype(mp, dep, XFS_DIR3_FT_DIR);
-	tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+	dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
+	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, bp, dep);
+	xfs_dir2_data_log_entry(tp, dp, bp, dep);
 	blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
 	blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
 				(char *)dep - (char *)hdr));
 	/*
 	 * Create entry for ..
 	 */
-	dep = xfs_dir3_data_dotdot_entry_p(mp, hdr);
-	dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
+	dep = dp->d_ops->data_dotdot_entry_p(hdr);
+	dep->inumber = cpu_to_be64(dp->d_ops->sf_get_parent_ino(sfp));
 	dep->namelen = 2;
 	dep->name[0] = dep->name[1] = '.';
-	xfs_dir3_dirent_put_ftype(mp, dep, XFS_DIR3_FT_DIR);
-	tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+	dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
+	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, bp, dep);
+	xfs_dir2_data_log_entry(tp, dp, bp, dep);
 	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
 	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
 				(char *)dep - (char *)hdr));
-	offset = xfs_dir3_data_first_offset(mp);
+	offset = dp->d_ops->data_first_offset;
 	/*
 	 * Loop over existing entries, stuff them in.
 	 */
@@ -1214,7 +1216,9 @@ xfs_dir2_sf_to_block(
 			*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
 				((char *)dup - (char *)hdr));
 			xfs_dir2_data_log_unused(tp, bp, dup);
-			xfs_dir2_data_freeinsert(hdr, dup, &dummy);
+			xfs_dir2_data_freeinsert(hdr,
+						 dp->d_ops->data_bestfree_p(hdr),
+						 dup, &dummy);
 			offset += be16_to_cpu(dup->length);
 			continue;
 		}
@@ -1222,14 +1226,13 @@ xfs_dir2_sf_to_block(
 		 * Copy a real entry.
 		 */
 		dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset);
-		dep->inumber = cpu_to_be64(xfs_dir3_sfe_get_ino(mp, sfp, sfep));
+		dep->inumber = cpu_to_be64(dp->d_ops->sf_get_ino(sfp, sfep));
 		dep->namelen = sfep->namelen;
-		xfs_dir3_dirent_put_ftype(mp, dep,
-					xfs_dir3_sfe_get_ftype(mp, sfp, sfep));
+		dp->d_ops->data_put_ftype(dep, dp->d_ops->sf_get_ftype(sfep));
 		memcpy(dep->name, sfep->name, dep->namelen);
-		tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+		tagp = dp->d_ops->data_entry_tag_p(dep);
 		*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-		xfs_dir2_data_log_entry(tp, bp, dep);
+		xfs_dir2_data_log_entry(tp, dp, bp, dep);
 		name.name = sfep->name;
 		name.len = sfep->namelen;
 		blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
@@ -1240,7 +1243,7 @@ xfs_dir2_sf_to_block(
 		if (++i == sfp->count)
 			sfep = NULL;
 		else
-			sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+			sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 	}
 	/* Done with the temporary buffer */
 	kmem_free(sfp);

fs/xfs/xfs_dir2_data.c

@@ -18,20 +18,19 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
 
@@ -63,11 +62,18 @@ __xfs_dir3_data_check(
 	char			*p;		/* current data position */
 	int			stale;		/* count of stale leaves */
 	struct xfs_name		name;
+	const struct xfs_dir_ops *ops;
 
 	mp = bp->b_target->bt_mount;
+
+	/*
+	 * We can be passed a null dp here from a verifier, so we need to go the
+	 * hard way to get them.
+	 */
+	ops = xfs_dir_get_ops(mp, dp);
+
 	hdr = bp->b_addr;
-	bf = xfs_dir3_data_bestfree_p(hdr);
-	p = (char *)xfs_dir3_data_entry_p(hdr);
+	p = (char *)ops->data_entry_p(hdr);
 
 	switch (hdr->magic) {
 	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
@@ -75,6 +81,16 @@ __xfs_dir3_data_check(
 		btp = xfs_dir2_block_tail_p(mp, hdr);
 		lep = xfs_dir2_block_leaf_p(btp);
 		endp = (char *)lep;
+
+		/*
+		 * The number of leaf entries is limited by the size of the
+		 * block and the amount of space used by the data entries.
+		 * We don't know how much space is used by the data entries yet,
+		 * so just ensure that the count falls somewhere inside the
+		 * block right now.
+		 */
+		XFS_WANT_CORRUPTED_RETURN(be32_to_cpu(btp->count) <
+			((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry));
 		break;
 	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
 	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
@@ -85,10 +101,11 @@ __xfs_dir3_data_check(
 		return EFSCORRUPTED;
 	}
 
-	count = lastfree = freeseen = 0;
 	/*
 	 * Account for zero bestfree entries.
 	 */
+	bf = ops->data_bestfree_p(hdr);
+	count = lastfree = freeseen = 0;
 	if (!bf[0].length) {
 		XFS_WANT_CORRUPTED_RETURN(!bf[0].offset);
 		freeseen |= 1 << 0;
@@ -121,7 +138,7 @@ __xfs_dir3_data_check(
 			XFS_WANT_CORRUPTED_RETURN(
 				be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
 					       (char *)dup - (char *)hdr);
-			dfp = xfs_dir2_data_freefind(hdr, dup);
+			dfp = xfs_dir2_data_freefind(hdr, bf, dup);
 			if (dfp) {
 				i = (int)(dfp - bf);
 				XFS_WANT_CORRUPTED_RETURN(
@@ -147,10 +164,10 @@ __xfs_dir3_data_check(
 		XFS_WANT_CORRUPTED_RETURN(
 			!xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
 		XFS_WANT_CORRUPTED_RETURN(
-			be16_to_cpu(*xfs_dir3_data_entry_tag_p(mp, dep)) ==
+			be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
 					       (char *)dep - (char *)hdr);
 		XFS_WANT_CORRUPTED_RETURN(
-			xfs_dir3_dirent_get_ftype(mp, dep) < XFS_DIR3_FT_MAX);
+				ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX);
 		count++;
 		lastfree = 0;
 		if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
@@ -168,7 +185,7 @@ __xfs_dir3_data_check(
 			}
 			XFS_WANT_CORRUPTED_RETURN(i < be32_to_cpu(btp->count));
 		}
-		p += xfs_dir3_data_entsize(mp, dep->namelen);
+		p += ops->data_entsize(dep->namelen);
 	}
 	/*
 	 * Need to have seen all the entries and all the bestfree slots.
@@ -327,19 +344,18 @@ xfs_dir3_data_readahead(
  */
 xfs_dir2_data_free_t *
 xfs_dir2_data_freefind(
-	xfs_dir2_data_hdr_t	*hdr,		/* data block */
-	xfs_dir2_data_unused_t	*dup)		/* data unused entry */
+	struct xfs_dir2_data_hdr *hdr,		/* data block header */
+	struct xfs_dir2_data_free *bf,		/* bestfree table pointer */
+	struct xfs_dir2_data_unused *dup)	/* unused space */
 {
 	xfs_dir2_data_free_t	*dfp;		/* bestfree entry */
 	xfs_dir2_data_aoff_t	off;		/* offset value needed */
-	struct xfs_dir2_data_free *bf;
 #ifdef DEBUG
 	int			matched;	/* matched the value */
 	int			seenzero;	/* saw a 0 bestfree entry */
 #endif
 
 	off = (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr);
-	bf = xfs_dir3_data_bestfree_p(hdr);
 
 #ifdef DEBUG
 	/*
@@ -399,11 +415,11 @@ xfs_dir2_data_freefind(
  */
 xfs_dir2_data_free_t *				/* entry inserted */
 xfs_dir2_data_freeinsert(
-	xfs_dir2_data_hdr_t	*hdr,		/* data block pointer */
-	xfs_dir2_data_unused_t	*dup,		/* unused space */
+	struct xfs_dir2_data_hdr *hdr,		/* data block pointer */
+	struct xfs_dir2_data_free *dfp,		/* bestfree table pointer */
+	struct xfs_dir2_data_unused *dup,	/* unused space */
 	int			*loghead)	/* log the data header (out) */
 {
-	xfs_dir2_data_free_t	*dfp;		/* bestfree table pointer */
 	xfs_dir2_data_free_t	new;		/* new bestfree entry */
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
@@ -411,7 +427,6 @@ xfs_dir2_data_freeinsert(
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
 
-	dfp = xfs_dir3_data_bestfree_p(hdr);
 	new.length = dup->length;
 	new.offset = cpu_to_be16((char *)dup - (char *)hdr);
 
@@ -444,11 +459,11 @@ xfs_dir2_data_freeinsert(
  */
 STATIC void
 xfs_dir2_data_freeremove(
-	xfs_dir2_data_hdr_t	*hdr,		/* data block header */
-	xfs_dir2_data_free_t	*dfp,		/* bestfree entry pointer */
+	struct xfs_dir2_data_hdr *hdr,		/* data block header */
+	struct xfs_dir2_data_free *bf,		/* bestfree table pointer */
+	struct xfs_dir2_data_free *dfp,		/* bestfree entry pointer */
 	int			*loghead)	/* out: log data header */
 {
-	struct xfs_dir2_data_free *bf;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
@@ -458,7 +473,6 @@ xfs_dir2_data_freeremove(
 	/*
 	 * It's the first entry, slide the next 2 up.
 	 */
-	bf = xfs_dir3_data_bestfree_p(hdr);
 	if (dfp == &bf[0]) {
 		bf[0] = bf[1];
 		bf[1] = bf[2];
@@ -486,9 +500,9 @@ xfs_dir2_data_freeremove(
  */
 void
 xfs_dir2_data_freescan(
-	xfs_mount_t		*mp,		/* filesystem mount point */
-	xfs_dir2_data_hdr_t	*hdr,		/* data block header */
-	int			*loghead)	/* out: log data header */
+	struct xfs_inode	*dp,
+	struct xfs_dir2_data_hdr *hdr,
+	int			*loghead)
 {
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* active data entry */
@@ -505,19 +519,19 @@ xfs_dir2_data_freescan(
 	/*
 	 * Start by clearing the table.
 	 */
-	bf = xfs_dir3_data_bestfree_p(hdr);
+	bf = dp->d_ops->data_bestfree_p(hdr);
 	memset(bf, 0, sizeof(*bf) * XFS_DIR2_DATA_FD_COUNT);
 	*loghead = 1;
 	/*
 	 * Set up pointers.
 	 */
-	p = (char *)xfs_dir3_data_entry_p(hdr);
+	p = (char *)dp->d_ops->data_entry_p(hdr);
 	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-		btp = xfs_dir2_block_tail_p(mp, hdr);
+		btp = xfs_dir2_block_tail_p(dp->i_mount, hdr);
 		endp = (char *)xfs_dir2_block_leaf_p(btp);
 	} else
-		endp = (char *)hdr + mp->m_dirblksize;
+		endp = (char *)hdr + dp->i_mount->m_dirblksize;
 	/*
 	 * Loop over the block's entries.
 	 */
@@ -529,7 +543,7 @@ xfs_dir2_data_freescan(
 		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
 			ASSERT((char *)dup - (char *)hdr ==
 			       be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)));
-			xfs_dir2_data_freeinsert(hdr, dup, loghead);
+			xfs_dir2_data_freeinsert(hdr, bf, dup, loghead);
 			p += be16_to_cpu(dup->length);
 		}
 		/*
@@ -538,8 +552,8 @@ xfs_dir2_data_freescan(
 		else {
 			dep = (xfs_dir2_data_entry_t *)p;
 			ASSERT((char *)dep - (char *)hdr ==
-			       be16_to_cpu(*xfs_dir3_data_entry_tag_p(mp, dep)));
-			p += xfs_dir3_data_entsize(mp, dep->namelen);
+			       be16_to_cpu(*dp->d_ops->data_entry_tag_p(dep)));
+			p += dp->d_ops->data_entsize(dep->namelen);
 		}
 	}
 }
@@ -594,8 +608,8 @@ xfs_dir3_data_init(
 	} else
 		hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
 
-	bf = xfs_dir3_data_bestfree_p(hdr);
-	bf[0].offset = cpu_to_be16(xfs_dir3_data_entry_offset(hdr));
+	bf = dp->d_ops->data_bestfree_p(hdr);
+	bf[0].offset = cpu_to_be16(dp->d_ops->data_entry_offset);
 	for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
 		bf[i].length = 0;
 		bf[i].offset = 0;
@@ -604,17 +618,17 @@ xfs_dir3_data_init(
 	/*
 	 * Set up an unused entry for the block's body.
 	 */
-	dup = xfs_dir3_data_unused_p(hdr);
+	dup = dp->d_ops->data_unused_p(hdr);
 	dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
 
-	t = mp->m_dirblksize - (uint)xfs_dir3_data_entry_offset(hdr);
+	t = mp->m_dirblksize - (uint)dp->d_ops->data_entry_offset;
 	bf[0].length = cpu_to_be16(t);
 	dup->length = cpu_to_be16(t);
 	*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr);
 	/*
 	 * Log it and return it.
 	 */
-	xfs_dir2_data_log_header(tp, bp);
+	xfs_dir2_data_log_header(tp, dp, bp);
 	xfs_dir2_data_log_unused(tp, bp, dup);
 	*bpp = bp;
 	return 0;
@@ -626,11 +640,11 @@ xfs_dir3_data_init(
 void
 xfs_dir2_data_log_entry(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
 {
 	struct xfs_dir2_data_hdr *hdr = bp->b_addr;
-	struct xfs_mount	*mp = tp->t_mountp;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
@@ -638,7 +652,7 @@ xfs_dir2_data_log_entry(
 	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
 
 	xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
-		(uint)((char *)(xfs_dir3_data_entry_tag_p(mp, dep) + 1) -
+		(uint)((char *)(dp->d_ops->data_entry_tag_p(dep) + 1) -
 		       (char *)hdr - 1));
 }
 
@@ -648,16 +662,19 @@ xfs_dir2_data_log_entry(
 void
 xfs_dir2_data_log_header(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp)
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
+#ifdef DEBUG
+	struct xfs_dir2_data_hdr *hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+#endif
 
-	xfs_trans_log_buf(tp, bp, 0, xfs_dir3_data_entry_offset(hdr) - 1);
+	xfs_trans_log_buf(tp, bp, 0, dp->d_ops->data_entry_offset - 1);
 }
 
 /*
@@ -698,6 +715,7 @@ xfs_dir2_data_log_unused(
 void
 xfs_dir2_data_make_free(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
 	xfs_dir2_data_aoff_t	len,		/* length in bytes */
@@ -735,7 +753,7 @@ xfs_dir2_data_make_free(
 	 * If this isn't the start of the block, then back up to
 	 * the previous entry and see if it's free.
 	 */
-	if (offset > xfs_dir3_data_entry_offset(hdr)) {
+	if (offset > dp->d_ops->data_entry_offset) {
 		__be16			*tagp;	/* tag just before us */
 
 		tagp = (__be16 *)((char *)hdr + offset) - 1;
@@ -761,15 +779,15 @@ xfs_dir2_data_make_free(
 	 * Previous and following entries are both free,
 	 * merge everything into a single free entry.
 	 */
-	bf = xfs_dir3_data_bestfree_p(hdr);
+	bf = dp->d_ops->data_bestfree_p(hdr);
 	if (prevdup && postdup) {
 		xfs_dir2_data_free_t	*dfp2;	/* another bestfree pointer */
 
 		/*
 		 * See if prevdup and/or postdup are in bestfree table.
 		 */
-		dfp = xfs_dir2_data_freefind(hdr, prevdup);
-		dfp2 = xfs_dir2_data_freefind(hdr, postdup);
+		dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
+		dfp2 = xfs_dir2_data_freefind(hdr, bf, postdup);
 		/*
 		 * We need a rescan unless there are exactly 2 free entries
 		 * namely our two.  Then we know what's happening, otherwise
@@ -797,12 +815,13 @@ xfs_dir2_data_make_free(
 				ASSERT(dfp2 == dfp);
 				dfp2 = &bf[1];
 			}
-			xfs_dir2_data_freeremove(hdr, dfp2, needlogp);
-			xfs_dir2_data_freeremove(hdr, dfp, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp2, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
 			/*
 			 * Now insert the new entry.
 			 */
-			dfp = xfs_dir2_data_freeinsert(hdr, prevdup, needlogp);
+			dfp = xfs_dir2_data_freeinsert(hdr, bf, prevdup,
+						       needlogp);
 			ASSERT(dfp == &bf[0]);
 			ASSERT(dfp->length == prevdup->length);
 			ASSERT(!dfp[1].length);
@@ -813,7 +832,7 @@ xfs_dir2_data_make_free(
 	 * The entry before us is free, merge with it.
 	 */
 	else if (prevdup) {
-		dfp = xfs_dir2_data_freefind(hdr, prevdup);
+		dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
 		be16_add_cpu(&prevdup->length, len);
 		*xfs_dir2_data_unused_tag_p(prevdup) =
 			cpu_to_be16((char *)prevdup - (char *)hdr);
@@ -824,8 +843,8 @@ xfs_dir2_data_make_free(
 		 * the old one and add the new one.
 		 */
 		if (dfp) {
-			xfs_dir2_data_freeremove(hdr, dfp, needlogp);
-			xfs_dir2_data_freeinsert(hdr, prevdup, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+			xfs_dir2_data_freeinsert(hdr, bf, prevdup, needlogp);
 		}
 		/*
 		 * Otherwise we need a scan if the new entry is big enough.
@@ -839,7 +858,7 @@ xfs_dir2_data_make_free(
 	 * The following entry is free, merge with it.
 	 */
 	else if (postdup) {
-		dfp = xfs_dir2_data_freefind(hdr, postdup);
+		dfp = xfs_dir2_data_freefind(hdr, bf, postdup);
 		newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
 		newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
 		newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length));
@@ -852,8 +871,8 @@ xfs_dir2_data_make_free(
 		 * the old one and add the new one.
 		 */
 		if (dfp) {
-			xfs_dir2_data_freeremove(hdr, dfp, needlogp);
-			xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+			xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
 		}
 		/*
 		 * Otherwise we need a scan if the new entry is big enough.
@@ -873,7 +892,7 @@ xfs_dir2_data_make_free(
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
 		xfs_dir2_data_log_unused(tp, bp, newdup);
-		xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+		xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
 	}
 	*needscanp = needscan;
 }
@@ -884,6 +903,7 @@ xfs_dir2_data_make_free(
 void
 xfs_dir2_data_use_free(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup,		/* unused entry */
 	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
@@ -913,9 +933,9 @@ xfs_dir2_data_use_free(
 	/*
 	 * Look up the entry in the bestfree table.
 	 */
-	dfp = xfs_dir2_data_freefind(hdr, dup);
 	oldlen = be16_to_cpu(dup->length);
-	bf = xfs_dir3_data_bestfree_p(hdr);
+	bf = dp->d_ops->data_bestfree_p(hdr);
+	dfp = xfs_dir2_data_freefind(hdr, bf, dup);
 	ASSERT(dfp || oldlen <= be16_to_cpu(bf[2].length));
 	/*
 	 * Check for alignment with front and back of the entry.
@@ -932,7 +952,8 @@ xfs_dir2_data_use_free(
 		if (dfp) {
 			needscan = (bf[2].offset != 0);
 			if (!needscan)
-				xfs_dir2_data_freeremove(hdr, dfp, needlogp);
+				xfs_dir2_data_freeremove(hdr, bf, dfp,
+							 needlogp);
 		}
 	}
 	/*
@@ -950,8 +971,9 @@ xfs_dir2_data_use_free(
 		 * If it was in the table, remove it and add the new one.
 		 */
 		if (dfp) {
-			xfs_dir2_data_freeremove(hdr, dfp, needlogp);
-			dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+			dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
+						       needlogp);
 			ASSERT(dfp != NULL);
 			ASSERT(dfp->length == newdup->length);
 			ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
@@ -977,8 +999,9 @@ xfs_dir2_data_use_free(
 		 * If it was in the table, remove it and add the new one.
 		 */
 		if (dfp) {
-			xfs_dir2_data_freeremove(hdr, dfp, needlogp);
-			dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+			dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
+						       needlogp);
 			ASSERT(dfp != NULL);
 			ASSERT(dfp->length == newdup->length);
 			ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
@@ -1017,9 +1040,11 @@ xfs_dir2_data_use_free(
 		if (dfp) {
 			needscan = (bf[2].length != 0);
 			if (!needscan) {
-				xfs_dir2_data_freeremove(hdr, dfp, needlogp);
-				xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
-				xfs_dir2_data_freeinsert(hdr, newdup2,
+				xfs_dir2_data_freeremove(hdr, bf, dfp,
+							 needlogp);
+				xfs_dir2_data_freeinsert(hdr, bf, newdup,
+							 needlogp);
+				xfs_dir2_data_freeinsert(hdr, bf, newdup2,
 							 needlogp);
 			}
 		}

fs/xfs/xfs_dir2_leaf.c

@@ -18,23 +18,21 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
 
@@ -52,21 +50,21 @@ static void xfs_dir3_leaf_log_tail(struct xfs_trans *tp, struct xfs_buf *bp);
  * Pop an assert if something is wrong.
  */
 #ifdef DEBUG
-#define	xfs_dir3_leaf_check(mp, bp) \
+#define	xfs_dir3_leaf_check(dp, bp) \
 do { \
-	if (!xfs_dir3_leaf1_check((mp), (bp))) \
+	if (!xfs_dir3_leaf1_check((dp), (bp))) \
 		ASSERT(0); \
 } while (0);
 
 STATIC bool
 xfs_dir3_leaf1_check(
-	struct xfs_mount	*mp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 	struct xfs_dir3_icleaf_hdr leafhdr;
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	if (leafhdr.magic == XFS_DIR3_LEAF1_MAGIC) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
@@ -75,71 +73,16 @@ xfs_dir3_leaf1_check(
 	} else if (leafhdr.magic != XFS_DIR2_LEAF1_MAGIC)
 		return false;
 
-	return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
+	return xfs_dir3_leaf_check_int(dp->i_mount, dp, &leafhdr, leaf);
 }
 #else
-#define	xfs_dir3_leaf_check(mp, bp)
+#define	xfs_dir3_leaf_check(dp, bp)
 #endif
 
-void
-xfs_dir3_leaf_hdr_from_disk(
-	struct xfs_dir3_icleaf_hdr	*to,
-	struct xfs_dir2_leaf		*from)
-{
-	if (from->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
-	    from->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)) {
-		to->forw = be32_to_cpu(from->hdr.info.forw);
-		to->back = be32_to_cpu(from->hdr.info.back);
-		to->magic = be16_to_cpu(from->hdr.info.magic);
-		to->count = be16_to_cpu(from->hdr.count);
-		to->stale = be16_to_cpu(from->hdr.stale);
-	} else {
-		struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)from;
-
-		to->forw = be32_to_cpu(hdr3->info.hdr.forw);
-		to->back = be32_to_cpu(hdr3->info.hdr.back);
-		to->magic = be16_to_cpu(hdr3->info.hdr.magic);
-		to->count = be16_to_cpu(hdr3->count);
-		to->stale = be16_to_cpu(hdr3->stale);
-	}
-
-	ASSERT(to->magic == XFS_DIR2_LEAF1_MAGIC ||
-	       to->magic == XFS_DIR3_LEAF1_MAGIC ||
-	       to->magic == XFS_DIR2_LEAFN_MAGIC ||
-	       to->magic == XFS_DIR3_LEAFN_MAGIC);
-}
-
-void
-xfs_dir3_leaf_hdr_to_disk(
-	struct xfs_dir2_leaf		*to,
-	struct xfs_dir3_icleaf_hdr	*from)
-{
-	ASSERT(from->magic == XFS_DIR2_LEAF1_MAGIC ||
-	       from->magic == XFS_DIR3_LEAF1_MAGIC ||
-	       from->magic == XFS_DIR2_LEAFN_MAGIC ||
-	       from->magic == XFS_DIR3_LEAFN_MAGIC);
-
-	if (from->magic == XFS_DIR2_LEAF1_MAGIC ||
-	    from->magic == XFS_DIR2_LEAFN_MAGIC) {
-		to->hdr.info.forw = cpu_to_be32(from->forw);
-		to->hdr.info.back = cpu_to_be32(from->back);
-		to->hdr.info.magic = cpu_to_be16(from->magic);
-		to->hdr.count = cpu_to_be16(from->count);
-		to->hdr.stale = cpu_to_be16(from->stale);
-	} else {
-		struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)to;
-
-		hdr3->info.hdr.forw = cpu_to_be32(from->forw);
-		hdr3->info.hdr.back = cpu_to_be32(from->back);
-		hdr3->info.hdr.magic = cpu_to_be16(from->magic);
-		hdr3->count = cpu_to_be16(from->count);
-		hdr3->stale = cpu_to_be16(from->stale);
-	}
-}
-
 bool
 xfs_dir3_leaf_check_int(
 	struct xfs_mount	*mp,
+	struct xfs_inode	*dp,
 	struct xfs_dir3_icleaf_hdr *hdr,
 	struct xfs_dir2_leaf	*leaf)
 {
@@ -147,8 +90,21 @@ xfs_dir3_leaf_check_int(
 	xfs_dir2_leaf_tail_t	*ltp;
 	int			stale;
 	int			i;
+	const struct xfs_dir_ops *ops;
+	struct xfs_dir3_icleaf_hdr leafhdr;
 
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	/*
+	 * we can be passed a null dp here from a verifier, so we need to go the
+	 * hard way to get them.
+	 */
+	ops = xfs_dir_get_ops(mp, dp);
+
+	if (!hdr) {
+		ops->leaf_hdr_from_disk(&leafhdr, leaf);
+		hdr = &leafhdr;
+	}
+
+	ents = ops->leaf_ents_p(leaf);
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 
 	/*
@@ -156,7 +112,7 @@ xfs_dir3_leaf_check_int(
 	 * Should factor in the size of the bests table as well.
 	 * We can deduce a value for that from di_size.
 	 */
-	if (hdr->count > xfs_dir3_max_leaf_ents(mp, leaf))
+	if (hdr->count > ops->leaf_max_ents(mp))
 		return false;
 
 	/* Leaves and bests don't overlap in leaf format. */
@@ -192,7 +148,6 @@ xfs_dir3_leaf_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
-	struct xfs_dir3_icleaf_hdr leafhdr;
 
 	ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
 
@@ -214,8 +169,7 @@ xfs_dir3_leaf_verify(
 			return false;
 	}
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
+	return xfs_dir3_leaf_check_int(mp, NULL, NULL, leaf);
 }
 
 static void
@@ -401,7 +355,7 @@ xfs_dir3_leaf_get_buf(
 		return error;
 
 	xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
-	xfs_dir3_leaf_log_header(tp, bp);
+	xfs_dir3_leaf_log_header(tp, dp, bp);
 	if (magic == XFS_DIR2_LEAF1_MAGIC)
 		xfs_dir3_leaf_log_tail(tp, bp);
 	*bpp = bp;
@@ -462,31 +416,31 @@ xfs_dir2_block_to_leaf(
 	xfs_dir3_data_check(dp, dbp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
-	bf = xfs_dir3_data_bestfree_p(hdr);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	bf = dp->d_ops->data_bestfree_p(hdr);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 
 	/*
 	 * Set the counts in the leaf header.
 	 */
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 	leafhdr.count = be32_to_cpu(btp->count);
 	leafhdr.stale = be32_to_cpu(btp->stale);
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, lbp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, lbp);
 
 	/*
 	 * Could compact these but I think we always do the conversion
 	 * after squeezing out stale entries.
 	 */
 	memcpy(ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
-	xfs_dir3_leaf_log_ents(tp, lbp, 0, leafhdr.count - 1);
+	xfs_dir3_leaf_log_ents(tp, dp, lbp, 0, leafhdr.count - 1);
 	needscan = 0;
 	needlog = 1;
 	/*
 	 * Make the space formerly occupied by the leaf entries and block
 	 * tail be free.
 	 */
-	xfs_dir2_data_make_free(tp, dbp,
+	xfs_dir2_data_make_free(tp, dp, dbp,
 		(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
 		(xfs_dir2_data_aoff_t)((char *)hdr + mp->m_dirblksize -
 				       (char *)blp),
@@ -502,7 +456,7 @@ xfs_dir2_block_to_leaf(
 		hdr->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
 
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	/*
 	 * Set up leaf tail and bests table.
 	 */
@@ -514,8 +468,8 @@ xfs_dir2_block_to_leaf(
 	 * Log the data header and leaf bests table.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
-	xfs_dir3_leaf_check(mp, lbp);
+		xfs_dir2_data_log_header(tp, dp, dbp);
+	xfs_dir3_leaf_check(dp, lbp);
 	xfs_dir3_data_check(dp, dbp);
 	xfs_dir3_leaf_log_bests(tp, lbp, 0, 0);
 	return 0;
@@ -699,10 +653,10 @@ xfs_dir2_leaf_addname(
 	index = xfs_dir2_leaf_search_hash(args, lbp);
 	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
-	length = xfs_dir3_data_entsize(mp, args->namelen);
+	length = dp->d_ops->data_entsize(args->namelen);
 
 	/*
 	 * See if there are any entries with the same hash value
@@ -864,7 +818,7 @@ xfs_dir2_leaf_addname(
 		else
 			xfs_dir3_leaf_log_bests(tp, lbp, use_block, use_block);
 		hdr = dbp->b_addr;
-		bf = xfs_dir3_data_bestfree_p(hdr);
+		bf = dp->d_ops->data_bestfree_p(hdr);
 		bestsp[use_block] = bf[0].length;
 		grown = 1;
 	} else {
@@ -880,7 +834,7 @@ xfs_dir2_leaf_addname(
 			return error;
 		}
 		hdr = dbp->b_addr;
-		bf = xfs_dir3_data_bestfree_p(hdr);
+		bf = dp->d_ops->data_bestfree_p(hdr);
 		grown = 0;
 	}
 	/*
@@ -893,7 +847,7 @@ xfs_dir2_leaf_addname(
 	/*
 	 * Mark the initial part of our freespace in use for the new entry.
 	 */
-	xfs_dir2_data_use_free(tp, dbp, dup,
+	xfs_dir2_data_use_free(tp, dp, dbp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
 		&needlog, &needscan);
 	/*
@@ -903,20 +857,20 @@ xfs_dir2_leaf_addname(
 	dep->inumber = cpu_to_be64(args->inumber);
 	dep->namelen = args->namelen;
 	memcpy(dep->name, args->name, dep->namelen);
-	xfs_dir3_dirent_put_ftype(mp, dep, args->filetype);
-	tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+	dp->d_ops->data_put_ftype(dep, args->filetype);
+	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
 	/*
 	 * Need to scan fix up the bestfree table.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	/*
 	 * Need to log the data block's header.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
-	xfs_dir2_data_log_entry(tp, dbp, dep);
+		xfs_dir2_data_log_header(tp, dp, dbp);
+	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
 	/*
 	 * If the bests table needs to be changed, do it.
 	 * Log the change unless we've already done that.
@@ -939,10 +893,10 @@ xfs_dir2_leaf_addname(
 	/*
 	 * Log the leaf fields and give up the buffers.
 	 */
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, lbp);
-	xfs_dir3_leaf_log_ents(tp, lbp, lfloglow, lfloghigh);
-	xfs_dir3_leaf_check(mp, lbp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, lbp);
+	xfs_dir3_leaf_log_ents(tp, dp, lbp, lfloglow, lfloghigh);
+	xfs_dir3_leaf_check(dp, lbp);
 	xfs_dir3_data_check(dp, dbp);
 	return 0;
 }
@@ -962,6 +916,7 @@ xfs_dir3_leaf_compact(
 	int		loglow;		/* first leaf entry to log */
 	int		to;		/* target leaf index */
 	struct xfs_dir2_leaf_entry *ents;
+	struct xfs_inode *dp = args->dp;
 
 	leaf = bp->b_addr;
 	if (!leafhdr->stale)
@@ -970,7 +925,7 @@ xfs_dir3_leaf_compact(
 	/*
 	 * Compress out the stale entries in place.
 	 */
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	for (from = to = 0, loglow = -1; from < leafhdr->count; from++) {
 		if (ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 			continue;
@@ -991,10 +946,10 @@ xfs_dir3_leaf_compact(
 	leafhdr->count -= leafhdr->stale;
 	leafhdr->stale = 0;
 
-	xfs_dir3_leaf_hdr_to_disk(leaf, leafhdr);
-	xfs_dir3_leaf_log_header(args->trans, bp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, leafhdr);
+	xfs_dir3_leaf_log_header(args->trans, dp, bp);
 	if (loglow != -1)
-		xfs_dir3_leaf_log_ents(args->trans, bp, loglow, to - 1);
+		xfs_dir3_leaf_log_ents(args->trans, dp, bp, loglow, to - 1);
 }
 
 /*
@@ -1121,10 +1076,11 @@ xfs_dir3_leaf_log_bests(
  */
 void
 xfs_dir3_leaf_log_ents(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	struct xfs_buf		*bp,		/* leaf buffer */
-	int			first,		/* first entry to log */
-	int			last)		/* last entry to log */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_buf		*bp,
+	int			first,
+	int			last)
 {
 	xfs_dir2_leaf_entry_t	*firstlep;	/* pointer to first entry */
 	xfs_dir2_leaf_entry_t	*lastlep;	/* pointer to last entry */
@@ -1136,7 +1092,7 @@ xfs_dir3_leaf_log_ents(
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
 
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	firstlep = &ents[first];
 	lastlep = &ents[last];
 	xfs_trans_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
@@ -1149,6 +1105,7 @@ xfs_dir3_leaf_log_ents(
 void
 xfs_dir3_leaf_log_header(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
@@ -1159,7 +1116,7 @@ xfs_dir3_leaf_log_header(
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
 
 	xfs_trans_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
-			  xfs_dir3_leaf_hdr_size(leaf) - 1);
+			  dp->d_ops->leaf_hdr_size - 1);
 }
 
 /*
@@ -1214,9 +1171,9 @@ xfs_dir2_leaf_lookup(
 	}
 	tp = args->trans;
 	dp = args->dp;
-	xfs_dir3_leaf_check(dp->i_mount, lbp);
+	xfs_dir3_leaf_check(dp, lbp);
 	leaf = lbp->b_addr;
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	/*
 	 * Get to the leaf entry and contained data entry address.
 	 */
@@ -1232,7 +1189,7 @@ xfs_dir2_leaf_lookup(
 	 * Return the found inode number & CI name if appropriate
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
-	args->filetype = xfs_dir3_dirent_get_ftype(dp->i_mount, dep);
+	args->filetype = dp->d_ops->data_get_ftype(dep);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
 	xfs_trans_brelse(tp, dbp);
 	xfs_trans_brelse(tp, lbp);
@@ -1279,9 +1236,9 @@ xfs_dir2_leaf_lookup_int(
 
 	*lbpp = lbp;
 	leaf = lbp->b_addr;
-	xfs_dir3_leaf_check(mp, lbp);
-	ents = xfs_dir3_leaf_ents_p(leaf);
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	xfs_dir3_leaf_check(dp, lbp);
+	ents = dp->d_ops->leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	/*
 	 * Look for the first leaf entry with our hash value.
@@ -1415,9 +1372,9 @@ xfs_dir2_leaf_removename(
 	leaf = lbp->b_addr;
 	hdr = dbp->b_addr;
 	xfs_dir3_data_check(dp, dbp);
-	bf = xfs_dir3_data_bestfree_p(hdr);
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	bf = dp->d_ops->data_bestfree_p(hdr);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	/*
 	 * Point to the leaf entry, use that to point to the data entry.
 	 */
@@ -1433,27 +1390,27 @@ xfs_dir2_leaf_removename(
 	/*
 	 * Mark the former data entry unused.
 	 */
-	xfs_dir2_data_make_free(tp, dbp,
+	xfs_dir2_data_make_free(tp, dp, dbp,
 		(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
-		xfs_dir3_data_entsize(mp, dep->namelen), &needlog, &needscan);
+		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
 	 * We just mark the leaf entry stale by putting a null in it.
 	 */
 	leafhdr.stale++;
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, lbp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, lbp);
 
 	lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
-	xfs_dir3_leaf_log_ents(tp, lbp, index, index);
+	xfs_dir3_leaf_log_ents(tp, dp, lbp, index, index);
 
 	/*
 	 * Scan the freespace in the data block again if necessary,
 	 * log the data block header if necessary.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
+		xfs_dir2_data_log_header(tp, dp, dbp);
 	/*
 	 * If the longest freespace in the data block has changed,
 	 * put the new value in the bests table and log that.
@@ -1467,7 +1424,7 @@ xfs_dir2_leaf_removename(
 	 * If the data block is now empty then get rid of the data block.
 	 */
 	if (be16_to_cpu(bf[0].length) ==
-			mp->m_dirblksize - xfs_dir3_data_entry_offset(hdr)) {
+			mp->m_dirblksize - dp->d_ops->data_entry_offset) {
 		ASSERT(db != mp->m_dirdatablk);
 		if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
 			/*
@@ -1478,7 +1435,7 @@ xfs_dir2_leaf_removename(
 			 */
 			if (error == ENOSPC && args->total == 0)
 				error = 0;
-			xfs_dir3_leaf_check(mp, lbp);
+			xfs_dir3_leaf_check(dp, lbp);
 			return error;
 		}
 		dbp = NULL;
@@ -1512,7 +1469,7 @@ xfs_dir2_leaf_removename(
 	else if (db != mp->m_dirdatablk)
 		dbp = NULL;
 
-	xfs_dir3_leaf_check(mp, lbp);
+	xfs_dir3_leaf_check(dp, lbp);
 	/*
 	 * See if we can convert to block form.
 	 */
@@ -1547,7 +1504,7 @@ xfs_dir2_leaf_replace(
 	}
 	dp = args->dp;
 	leaf = lbp->b_addr;
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	/*
 	 * Point to the leaf entry, get data address from it.
 	 */
@@ -1563,10 +1520,10 @@ xfs_dir2_leaf_replace(
 	 * Put the new inode number in, log it.
 	 */
 	dep->inumber = cpu_to_be64(args->inumber);
-	xfs_dir3_dirent_put_ftype(dp->i_mount, dep, args->filetype);
+	dp->d_ops->data_put_ftype(dep, args->filetype);
 	tp = args->trans;
-	xfs_dir2_data_log_entry(tp, dbp, dep);
-	xfs_dir3_leaf_check(dp->i_mount, lbp);
+	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+	xfs_dir3_leaf_check(dp, lbp);
 	xfs_trans_brelse(tp, lbp);
 	return 0;
 }
@@ -1592,8 +1549,8 @@ xfs_dir2_leaf_search_hash(
 	struct xfs_dir3_icleaf_hdr leafhdr;
 
 	leaf = lbp->b_addr;
-	ents = xfs_dir3_leaf_ents_p(leaf);
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = args->dp->d_ops->leaf_ents_p(leaf);
+	args->dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	/*
 	 * Note, the table cannot be empty, so we have to go through the loop.
@@ -1661,12 +1618,12 @@ xfs_dir2_leaf_trim_data(
 #ifdef DEBUG
 {
 	struct xfs_dir2_data_hdr *hdr = dbp->b_addr;
-	struct xfs_dir2_data_free *bf = xfs_dir3_data_bestfree_p(hdr);
+	struct xfs_dir2_data_free *bf = dp->d_ops->data_bestfree_p(hdr);
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
 	ASSERT(be16_to_cpu(bf[0].length) ==
-	       mp->m_dirblksize - xfs_dir3_data_entry_offset(hdr));
+	       mp->m_dirblksize - dp->d_ops->data_entry_offset);
 	ASSERT(db == be32_to_cpu(ltp->bestcount) - 1);
 }
 #endif
@@ -1782,7 +1739,7 @@ xfs_dir2_node_to_leaf(
 		return 0;
 	lbp = state->path.blk[0].bp;
 	leaf = lbp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
 	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
@@ -1794,7 +1751,7 @@ xfs_dir2_node_to_leaf(
 	if (error)
 		return error;
 	free = fbp->b_addr;
-	xfs_dir3_free_hdr_from_disk(&freehdr, free);
+	dp->d_ops->free_hdr_from_disk(&freehdr, free);
 
 	ASSERT(!freehdr.firstdb);
 
@@ -1828,14 +1785,14 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Set up the leaf bests table.
 	 */
-	memcpy(xfs_dir2_leaf_bests_p(ltp), xfs_dir3_free_bests_p(mp, free),
+	memcpy(xfs_dir2_leaf_bests_p(ltp), dp->d_ops->free_bests_p(free),
 		freehdr.nvalid * sizeof(xfs_dir2_data_off_t));
 
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, lbp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, lbp);
 	xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
 	xfs_dir3_leaf_log_tail(tp, lbp);
-	xfs_dir3_leaf_check(mp, lbp);
+	xfs_dir3_leaf_check(dp, lbp);
 
 	/*
 	 * Get rid of the freespace block.

fs/xfs/xfs_dir2_node.c

@@ -18,22 +18,21 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
 
@@ -55,21 +54,21 @@ static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
  * Check internal consistency of a leafn block.
  */
 #ifdef DEBUG
-#define	xfs_dir3_leaf_check(mp, bp) \
+#define	xfs_dir3_leaf_check(dp, bp) \
 do { \
-	if (!xfs_dir3_leafn_check((mp), (bp))) \
+	if (!xfs_dir3_leafn_check((dp), (bp))) \
 		ASSERT(0); \
 } while (0);
 
 static bool
 xfs_dir3_leafn_check(
-	struct xfs_mount	*mp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 	struct xfs_dir3_icleaf_hdr leafhdr;
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	if (leafhdr.magic == XFS_DIR3_LEAFN_MAGIC) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
@@ -78,10 +77,10 @@ xfs_dir3_leafn_check(
 	} else if (leafhdr.magic != XFS_DIR2_LEAFN_MAGIC)
 		return false;
 
-	return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
+	return xfs_dir3_leaf_check_int(dp->i_mount, dp, &leafhdr, leaf);
 }
 #else
-#define	xfs_dir3_leaf_check(mp, bp)
+#define	xfs_dir3_leaf_check(dp, bp)
 #endif
 
 static bool
@@ -193,53 +192,6 @@ xfs_dir2_free_try_read(
 	return __xfs_dir3_free_read(tp, dp, fbno, -2, bpp);
 }
 
-
-void
-xfs_dir3_free_hdr_from_disk(
-	struct xfs_dir3_icfree_hdr	*to,
-	struct xfs_dir2_free		*from)
-{
-	if (from->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)) {
-		to->magic = be32_to_cpu(from->hdr.magic);
-		to->firstdb = be32_to_cpu(from->hdr.firstdb);
-		to->nvalid = be32_to_cpu(from->hdr.nvalid);
-		to->nused = be32_to_cpu(from->hdr.nused);
-	} else {
-		struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)from;
-
-		to->magic = be32_to_cpu(hdr3->hdr.magic);
-		to->firstdb = be32_to_cpu(hdr3->firstdb);
-		to->nvalid = be32_to_cpu(hdr3->nvalid);
-		to->nused = be32_to_cpu(hdr3->nused);
-	}
-
-	ASSERT(to->magic == XFS_DIR2_FREE_MAGIC ||
-	       to->magic == XFS_DIR3_FREE_MAGIC);
-}
-
-static void
-xfs_dir3_free_hdr_to_disk(
-	struct xfs_dir2_free		*to,
-	struct xfs_dir3_icfree_hdr	*from)
-{
-	ASSERT(from->magic == XFS_DIR2_FREE_MAGIC ||
-	       from->magic == XFS_DIR3_FREE_MAGIC);
-
-	if (from->magic == XFS_DIR2_FREE_MAGIC) {
-		to->hdr.magic = cpu_to_be32(from->magic);
-		to->hdr.firstdb = cpu_to_be32(from->firstdb);
-		to->hdr.nvalid = cpu_to_be32(from->nvalid);
-		to->hdr.nused = cpu_to_be32(from->nused);
-	} else {
-		struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)to;
-
-		hdr3->hdr.magic = cpu_to_be32(from->magic);
-		hdr3->firstdb = cpu_to_be32(from->firstdb);
-		hdr3->nvalid = cpu_to_be32(from->nvalid);
-		hdr3->nused = cpu_to_be32(from->nused);
-	}
-}
-
 static int
 xfs_dir3_free_get_buf(
 	struct xfs_trans	*tp,
@@ -277,7 +229,7 @@ xfs_dir3_free_get_buf(
 		uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_uuid);
 	} else
 		hdr.magic = XFS_DIR2_FREE_MAGIC;
-	xfs_dir3_free_hdr_to_disk(bp->b_addr, &hdr);
+	dp->d_ops->free_hdr_to_disk(bp->b_addr, &hdr);
 	*bpp = bp;
 	return 0;
 }
@@ -288,6 +240,7 @@ xfs_dir3_free_get_buf(
 STATIC void
 xfs_dir2_free_log_bests(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp,
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
@@ -296,7 +249,7 @@ xfs_dir2_free_log_bests(
 	__be16			*bests;
 
 	free = bp->b_addr;
-	bests = xfs_dir3_free_bests_p(tp->t_mountp, free);
+	bests = dp->d_ops->free_bests_p(free);
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
 	       free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
 	xfs_trans_log_buf(tp, bp,
@@ -311,6 +264,7 @@ xfs_dir2_free_log_bests(
 static void
 xfs_dir2_free_log_header(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_buf		*bp)
 {
 #ifdef DEBUG
@@ -320,7 +274,7 @@ xfs_dir2_free_log_header(
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
 	       free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
 #endif
-	xfs_trans_log_buf(tp, bp, 0, xfs_dir3_free_hdr_size(tp->t_mountp) - 1);
+	xfs_trans_log_buf(tp, bp, 0, dp->d_ops->free_hdr_size - 1);
 }
 
 /*
@@ -369,7 +323,7 @@ xfs_dir2_leaf_to_node(
 		return error;
 
 	free = fbp->b_addr;
-	xfs_dir3_free_hdr_from_disk(&freehdr, free);
+	dp->d_ops->free_hdr_from_disk(&freehdr, free);
 	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	ASSERT(be32_to_cpu(ltp->bestcount) <=
@@ -380,7 +334,7 @@ xfs_dir2_leaf_to_node(
 	 * Count active entries.
 	 */
 	from = xfs_dir2_leaf_bests_p(ltp);
-	to = xfs_dir3_free_bests_p(mp, free);
+	to = dp->d_ops->free_bests_p(free);
 	for (i = n = 0; i < be32_to_cpu(ltp->bestcount); i++, from++, to++) {
 		if ((off = be16_to_cpu(*from)) != NULLDATAOFF)
 			n++;
@@ -393,9 +347,9 @@ xfs_dir2_leaf_to_node(
 	freehdr.nused = n;
 	freehdr.nvalid = be32_to_cpu(ltp->bestcount);
 
-	xfs_dir3_free_hdr_to_disk(fbp->b_addr, &freehdr);
-	xfs_dir2_free_log_bests(tp, fbp, 0, freehdr.nvalid - 1);
-	xfs_dir2_free_log_header(tp, fbp);
+	dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
+	xfs_dir2_free_log_bests(tp, dp, fbp, 0, freehdr.nvalid - 1);
+	xfs_dir2_free_log_header(tp, dp, fbp);
 
 	/*
 	 * Converting the leaf to a leafnode is just a matter of changing the
@@ -409,8 +363,8 @@ xfs_dir2_leaf_to_node(
 		leaf->hdr.info.magic = cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
 	lbp->b_ops = &xfs_dir3_leafn_buf_ops;
 	xfs_trans_buf_set_type(tp, lbp, XFS_BLFT_DIR_LEAFN_BUF);
-	xfs_dir3_leaf_log_header(tp, lbp);
-	xfs_dir3_leaf_check(mp, lbp);
+	xfs_dir3_leaf_log_header(tp, dp, lbp);
+	xfs_dir3_leaf_check(dp, lbp);
 	return 0;
 }
 
@@ -443,8 +397,8 @@ xfs_dir2_leafn_add(
 	mp = dp->i_mount;
 	tp = args->trans;
 	leaf = bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 
 	/*
 	 * Quick check just to make sure we are not going to index
@@ -460,7 +414,7 @@ xfs_dir2_leafn_add(
 	 * a compact.
 	 */
 
-	if (leafhdr.count == xfs_dir3_max_leaf_ents(mp, leaf)) {
+	if (leafhdr.count == dp->d_ops->leaf_max_ents(mp)) {
 		if (!leafhdr.stale)
 			return XFS_ERROR(ENOSPC);
 		compact = leafhdr.stale > 1;
@@ -498,30 +452,30 @@ xfs_dir2_leafn_add(
 	lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp,
 				args->blkno, args->index));
 
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, bp);
-	xfs_dir3_leaf_log_ents(tp, bp, lfloglow, lfloghigh);
-	xfs_dir3_leaf_check(mp, bp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, bp);
+	xfs_dir3_leaf_log_ents(tp, dp, bp, lfloglow, lfloghigh);
+	xfs_dir3_leaf_check(dp, bp);
 	return 0;
 }
 
 #ifdef DEBUG
 static void
 xfs_dir2_free_hdr_check(
-	struct xfs_mount *mp,
+	struct xfs_inode *dp,
 	struct xfs_buf	*bp,
 	xfs_dir2_db_t	db)
 {
 	struct xfs_dir3_icfree_hdr hdr;
 
-	xfs_dir3_free_hdr_from_disk(&hdr, bp->b_addr);
+	dp->d_ops->free_hdr_from_disk(&hdr, bp->b_addr);
 
-	ASSERT((hdr.firstdb % xfs_dir3_free_max_bests(mp)) == 0);
+	ASSERT((hdr.firstdb % dp->d_ops->free_max_bests(dp->i_mount)) == 0);
 	ASSERT(hdr.firstdb <= db);
 	ASSERT(db < hdr.firstdb + hdr.nvalid);
 }
 #else
-#define xfs_dir2_free_hdr_check(mp, dp, db)
+#define xfs_dir2_free_hdr_check(dp, bp, db)
 #endif	/* DEBUG */
 
 /*
@@ -530,6 +484,7 @@ xfs_dir2_free_hdr_check(
  */
 xfs_dahash_t					/* hash value */
 xfs_dir2_leafn_lasthash(
+	struct xfs_inode *dp,
 	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
 {
@@ -537,7 +492,7 @@ xfs_dir2_leafn_lasthash(
 	struct xfs_dir2_leaf_entry *ents;
 	struct xfs_dir3_icleaf_hdr leafhdr;
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
 	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
@@ -547,7 +502,7 @@ xfs_dir2_leafn_lasthash(
 	if (!leafhdr.count)
 		return 0;
 
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 	return be32_to_cpu(ents[leafhdr.count - 1].hashval);
 }
 
@@ -584,10 +539,10 @@ xfs_dir2_leafn_lookup_for_addname(
 	tp = args->trans;
 	mp = dp->i_mount;
 	leaf = bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 
-	xfs_dir3_leaf_check(mp, bp);
+	xfs_dir3_leaf_check(dp, bp);
 	ASSERT(leafhdr.count > 0);
 
 	/*
@@ -605,7 +560,7 @@ xfs_dir2_leafn_lookup_for_addname(
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
 		       free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
 	}
-	length = xfs_dir3_data_entsize(mp, args->namelen);
+	length = dp->d_ops->data_entsize(args->namelen);
 	/*
 	 * Loop over leaf entries with the right hash value.
 	 */
@@ -637,7 +592,7 @@ xfs_dir2_leafn_lookup_for_addname(
 			 * Convert the data block to the free block
 			 * holding its freespace information.
 			 */
-			newfdb = xfs_dir2_db_to_fdb(mp, newdb);
+			newfdb = dp->d_ops->db_to_fdb(mp, newdb);
 			/*
 			 * If it's not the one we have in hand, read it in.
 			 */
@@ -655,16 +610,16 @@ xfs_dir2_leafn_lookup_for_addname(
 					return error;
 				free = curbp->b_addr;
 
-				xfs_dir2_free_hdr_check(mp, curbp, curdb);
+				xfs_dir2_free_hdr_check(dp, curbp, curdb);
 			}
 			/*
 			 * Get the index for our entry.
 			 */
-			fi = xfs_dir2_db_to_fdindex(mp, curdb);
+			fi = dp->d_ops->db_to_fdindex(mp, curdb);
 			/*
 			 * If it has room, return it.
 			 */
-			bests = xfs_dir3_free_bests_p(mp, free);
+			bests = dp->d_ops->free_bests_p(free);
 			if (unlikely(bests[fi] == cpu_to_be16(NULLDATAOFF))) {
 				XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
 							XFS_ERRLEVEL_LOW, mp);
@@ -734,10 +689,10 @@ xfs_dir2_leafn_lookup_for_entry(
 	tp = args->trans;
 	mp = dp->i_mount;
 	leaf = bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 
-	xfs_dir3_leaf_check(mp, bp);
+	xfs_dir3_leaf_check(dp, bp);
 	ASSERT(leafhdr.count > 0);
 
 	/*
@@ -816,7 +771,7 @@ xfs_dir2_leafn_lookup_for_entry(
 				xfs_trans_brelse(tp, state->extrablk.bp);
 			args->cmpresult = cmp;
 			args->inumber = be64_to_cpu(dep->inumber);
-			args->filetype = xfs_dir3_dirent_get_ftype(mp, dep);
+			args->filetype = dp->d_ops->data_get_ftype(dep);
 			*indexp = index;
 			state->extravalid = 1;
 			state->extrablk.bp = curbp;
@@ -907,7 +862,7 @@ xfs_dir3_leafn_moveents(
 	if (start_d < dhdr->count) {
 		memmove(&dents[start_d + count], &dents[start_d],
 			(dhdr->count - start_d) * sizeof(xfs_dir2_leaf_entry_t));
-		xfs_dir3_leaf_log_ents(tp, bp_d, start_d + count,
+		xfs_dir3_leaf_log_ents(tp, args->dp, bp_d, start_d + count,
 				       count + dhdr->count - 1);
 	}
 	/*
@@ -929,7 +884,8 @@ xfs_dir3_leafn_moveents(
 	 */
 	memcpy(&dents[start_d], &sents[start_s],
 		count * sizeof(xfs_dir2_leaf_entry_t));
-	xfs_dir3_leaf_log_ents(tp, bp_d, start_d, start_d + count - 1);
+	xfs_dir3_leaf_log_ents(tp, args->dp, bp_d,
+			       start_d, start_d + count - 1);
 
 	/*
 	 * If there are source entries after the ones we copied,
@@ -938,7 +894,8 @@ xfs_dir3_leafn_moveents(
 	if (start_s + count < shdr->count) {
 		memmove(&sents[start_s], &sents[start_s + count],
 			count * sizeof(xfs_dir2_leaf_entry_t));
-		xfs_dir3_leaf_log_ents(tp, bp_s, start_s, start_s + count - 1);
+		xfs_dir3_leaf_log_ents(tp, args->dp, bp_s,
+				       start_s, start_s + count - 1);
 	}
 
 	/*
@@ -956,6 +913,7 @@ xfs_dir3_leafn_moveents(
  */
 int						/* sort order */
 xfs_dir2_leafn_order(
+	struct xfs_inode	*dp,
 	struct xfs_buf		*leaf1_bp,		/* leaf1 buffer */
 	struct xfs_buf		*leaf2_bp)		/* leaf2 buffer */
 {
@@ -966,10 +924,10 @@ xfs_dir2_leafn_order(
 	struct xfs_dir3_icleaf_hdr hdr1;
 	struct xfs_dir3_icleaf_hdr hdr2;
 
-	xfs_dir3_leaf_hdr_from_disk(&hdr1, leaf1);
-	xfs_dir3_leaf_hdr_from_disk(&hdr2, leaf2);
-	ents1 = xfs_dir3_leaf_ents_p(leaf1);
-	ents2 = xfs_dir3_leaf_ents_p(leaf2);
+	dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
+	dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf2);
+	ents1 = dp->d_ops->leaf_ents_p(leaf1);
+	ents2 = dp->d_ops->leaf_ents_p(leaf2);
 
 	if (hdr1.count > 0 && hdr2.count > 0 &&
 	    (be32_to_cpu(ents2[0].hashval) < be32_to_cpu(ents1[0].hashval) ||
@@ -1007,12 +965,13 @@ xfs_dir2_leafn_rebalance(
 	struct xfs_dir2_leaf_entry *ents2;
 	struct xfs_dir3_icleaf_hdr hdr1;
 	struct xfs_dir3_icleaf_hdr hdr2;
+	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
 	/*
 	 * If the block order is wrong, swap the arguments.
 	 */
-	if ((swap = xfs_dir2_leafn_order(blk1->bp, blk2->bp))) {
+	if ((swap = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp))) {
 		xfs_da_state_blk_t	*tmp;	/* temp for block swap */
 
 		tmp = blk1;
@@ -1021,10 +980,10 @@ xfs_dir2_leafn_rebalance(
 	}
 	leaf1 = blk1->bp->b_addr;
 	leaf2 = blk2->bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&hdr1, leaf1);
-	xfs_dir3_leaf_hdr_from_disk(&hdr2, leaf2);
-	ents1 = xfs_dir3_leaf_ents_p(leaf1);
-	ents2 = xfs_dir3_leaf_ents_p(leaf2);
+	dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
+	dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf2);
+	ents1 = dp->d_ops->leaf_ents_p(leaf1);
+	ents2 = dp->d_ops->leaf_ents_p(leaf2);
 
 	oldsum = hdr1.count + hdr2.count;
 #if defined(DEBUG) || defined(XFS_WARN)
@@ -1070,13 +1029,13 @@ xfs_dir2_leafn_rebalance(
 	ASSERT(hdr1.stale + hdr2.stale == oldstale);
 
 	/* log the changes made when moving the entries */
-	xfs_dir3_leaf_hdr_to_disk(leaf1, &hdr1);
-	xfs_dir3_leaf_hdr_to_disk(leaf2, &hdr2);
-	xfs_dir3_leaf_log_header(args->trans, blk1->bp);
-	xfs_dir3_leaf_log_header(args->trans, blk2->bp);
+	dp->d_ops->leaf_hdr_to_disk(leaf1, &hdr1);
+	dp->d_ops->leaf_hdr_to_disk(leaf2, &hdr2);
+	xfs_dir3_leaf_log_header(args->trans, dp, blk1->bp);
+	xfs_dir3_leaf_log_header(args->trans, dp, blk2->bp);
 
-	xfs_dir3_leaf_check(args->dp->i_mount, blk1->bp);
-	xfs_dir3_leaf_check(args->dp->i_mount, blk2->bp);
+	xfs_dir3_leaf_check(dp, blk1->bp);
+	xfs_dir3_leaf_check(dp, blk2->bp);
 
 	/*
 	 * Mark whether we're inserting into the old or new leaf.
@@ -1097,11 +1056,11 @@ xfs_dir2_leafn_rebalance(
 	 * Finally sanity check just to make sure we are not returning a
 	 * negative index
 	 */
-	if(blk2->index < 0) {
+	if (blk2->index < 0) {
 		state->inleaf = 1;
 		blk2->index = 0;
-		xfs_alert(args->dp->i_mount,
-	"%s: picked the wrong leaf? reverting original leaf: blk1->index %d\n",
+		xfs_alert(dp->i_mount,
+	"%s: picked the wrong leaf? reverting original leaf: blk1->index %d",
 			__func__, blk1->index);
 	}
 }
@@ -1120,17 +1079,17 @@ xfs_dir3_data_block_free(
 	int			logfree = 0;
 	__be16			*bests;
 	struct xfs_dir3_icfree_hdr freehdr;
+	struct xfs_inode	*dp = args->dp;
 
-	xfs_dir3_free_hdr_from_disk(&freehdr, free);
-
-	bests = xfs_dir3_free_bests_p(tp->t_mountp, free);
+	dp->d_ops->free_hdr_from_disk(&freehdr, free);
+	bests = dp->d_ops->free_bests_p(free);
 	if (hdr) {
 		/*
 		 * Data block is not empty, just set the free entry to the new
 		 * value.
 		 */
 		bests[findex] = cpu_to_be16(longest);
-		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
 		return 0;
 	}
 
@@ -1157,8 +1116,8 @@ xfs_dir3_data_block_free(
 		logfree = 1;
 	}
 
-	xfs_dir3_free_hdr_to_disk(free, &freehdr);
-	xfs_dir2_free_log_header(tp, fbp);
+	dp->d_ops->free_hdr_to_disk(free, &freehdr);
+	xfs_dir2_free_log_header(tp, dp, fbp);
 
 	/*
 	 * If there are no useful entries left in the block, get rid of the
@@ -1182,7 +1141,7 @@ xfs_dir3_data_block_free(
 
 	/* Log the free entry that changed, unless we got rid of it.  */
 	if (logfree)
-		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
 	return 0;
 }
 
@@ -1222,8 +1181,8 @@ xfs_dir2_leafn_remove(
 	tp = args->trans;
 	mp = dp->i_mount;
 	leaf = bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
 
 	/*
 	 * Point to the entry we're removing.
@@ -1243,11 +1202,11 @@ xfs_dir2_leafn_remove(
 	 * Log the leaf block changes.
 	 */
 	leafhdr.stale++;
-	xfs_dir3_leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, bp);
+	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+	xfs_dir3_leaf_log_header(tp, dp, bp);
 
 	lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
-	xfs_dir3_leaf_log_ents(tp, bp, index, index);
+	xfs_dir3_leaf_log_ents(tp, dp, bp, index, index);
 
 	/*
 	 * Make the data entry free.  Keep track of the longest freespace
@@ -1256,19 +1215,19 @@ xfs_dir2_leafn_remove(
 	dbp = dblk->bp;
 	hdr = dbp->b_addr;
 	dep = (xfs_dir2_data_entry_t *)((char *)hdr + off);
-	bf = xfs_dir3_data_bestfree_p(hdr);
+	bf = dp->d_ops->data_bestfree_p(hdr);
 	longest = be16_to_cpu(bf[0].length);
 	needlog = needscan = 0;
-	xfs_dir2_data_make_free(tp, dbp, off,
-		xfs_dir3_data_entsize(mp, dep->namelen), &needlog, &needscan);
+	xfs_dir2_data_make_free(tp, dp, dbp, off,
+		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
 	 * Rescan the data block freespaces for bestfree.
 	 * Log the data block header if needed.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
+		xfs_dir2_data_log_header(tp, dp, dbp);
 	xfs_dir3_data_check(dp, dbp);
 	/*
 	 * If the longest data block freespace changes, need to update
@@ -1285,7 +1244,7 @@ xfs_dir2_leafn_remove(
 		 * Convert the data block number to a free block,
 		 * read in the free block.
 		 */
-		fdb = xfs_dir2_db_to_fdb(mp, db);
+		fdb = dp->d_ops->db_to_fdb(mp, db);
 		error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(mp, fdb),
 					   &fbp);
 		if (error)
@@ -1294,22 +1253,22 @@ xfs_dir2_leafn_remove(
 #ifdef DEBUG
 	{
 		struct xfs_dir3_icfree_hdr freehdr;
-		xfs_dir3_free_hdr_from_disk(&freehdr, free);
-		ASSERT(freehdr.firstdb == xfs_dir3_free_max_bests(mp) *
+		dp->d_ops->free_hdr_from_disk(&freehdr, free);
+		ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(mp) *
 					  (fdb - XFS_DIR2_FREE_FIRSTDB(mp)));
 	}
 #endif
 		/*
 		 * Calculate which entry we need to fix.
 		 */
-		findex = xfs_dir2_db_to_fdindex(mp, db);
+		findex = dp->d_ops->db_to_fdindex(mp, db);
 		longest = be16_to_cpu(bf[0].length);
 		/*
 		 * If the data block is now empty we can get rid of it
 		 * (usually).
 		 */
 		if (longest == mp->m_dirblksize -
-			       xfs_dir3_data_entry_offset(hdr)) {
+			       dp->d_ops->data_entry_offset) {
 			/*
 			 * Try to punch out the data block.
 			 */
@@ -1336,12 +1295,12 @@ xfs_dir2_leafn_remove(
 			return error;
 	}
 
-	xfs_dir3_leaf_check(mp, bp);
+	xfs_dir3_leaf_check(dp, bp);
 	/*
 	 * Return indication of whether this leaf block is empty enough
 	 * to justify trying to join it with a neighbor.
 	 */
-	*rval = (xfs_dir3_leaf_hdr_size(leaf) +
+	*rval = (dp->d_ops->leaf_hdr_size +
 		 (uint)sizeof(ents[0]) * (leafhdr.count - leafhdr.stale)) <
 		mp->m_dir_magicpct;
 	return 0;
@@ -1360,13 +1319,14 @@ xfs_dir2_leafn_split(
 	xfs_dablk_t		blkno;		/* new leaf block number */
 	int			error;		/* error return value */
 	xfs_mount_t		*mp;		/* filesystem mount point */
+	struct xfs_inode	*dp;
 
 	/*
 	 * Allocate space for a new leaf node.
 	 */
 	args = state->args;
-	mp = args->dp->i_mount;
-	ASSERT(args != NULL);
+	dp = args->dp;
+	mp = dp->i_mount;
 	ASSERT(oldblk->magic == XFS_DIR2_LEAFN_MAGIC);
 	error = xfs_da_grow_inode(args, &blkno);
 	if (error) {
@@ -1401,10 +1361,10 @@ xfs_dir2_leafn_split(
 	/*
 	 * Update last hashval in each block since we added the name.
 	 */
-	oldblk->hashval = xfs_dir2_leafn_lasthash(oldblk->bp, NULL);
-	newblk->hashval = xfs_dir2_leafn_lasthash(newblk->bp, NULL);
-	xfs_dir3_leaf_check(mp, oldblk->bp);
-	xfs_dir3_leaf_check(mp, newblk->bp);
+	oldblk->hashval = xfs_dir2_leafn_lasthash(dp, oldblk->bp, NULL);
+	newblk->hashval = xfs_dir2_leafn_lasthash(dp, newblk->bp, NULL);
+	xfs_dir3_leaf_check(dp, oldblk->bp);
+	xfs_dir3_leaf_check(dp, newblk->bp);
 	return error;
 }
 
@@ -1434,6 +1394,7 @@ xfs_dir2_leafn_toosmall(
 	int			rval;		/* result from path_shift */
 	struct xfs_dir3_icleaf_hdr leafhdr;
 	struct xfs_dir2_leaf_entry *ents;
+	struct xfs_inode	*dp = state->args->dp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -1442,12 +1403,12 @@ xfs_dir2_leafn_toosmall(
 	 */
 	blk = &state->path.blk[state->path.active - 1];
 	leaf = blk->bp->b_addr;
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
-	ents = xfs_dir3_leaf_ents_p(leaf);
-	xfs_dir3_leaf_check(state->args->dp->i_mount, blk->bp);
+	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+	ents = dp->d_ops->leaf_ents_p(leaf);
+	xfs_dir3_leaf_check(dp, blk->bp);
 
 	count = leafhdr.count - leafhdr.stale;
-	bytes = xfs_dir3_leaf_hdr_size(leaf) + count * sizeof(ents[0]);
+	bytes = dp->d_ops->leaf_hdr_size + count * sizeof(ents[0]);
 	if (bytes > (state->blocksize >> 1)) {
 		/*
 		 * Blk over 50%, don't try to join.
@@ -1492,7 +1453,7 @@ xfs_dir2_leafn_toosmall(
 		/*
 		 * Read the sibling leaf block.
 		 */
-		error = xfs_dir3_leafn_read(state->args->trans, state->args->dp,
+		error = xfs_dir3_leafn_read(state->args->trans, dp,
 					    blkno, -1, &bp);
 		if (error)
 			return error;
@@ -1504,8 +1465,8 @@ xfs_dir2_leafn_toosmall(
 		bytes = state->blocksize - (state->blocksize >> 2);
 
 		leaf = bp->b_addr;
-		xfs_dir3_leaf_hdr_from_disk(&hdr2, leaf);
-		ents = xfs_dir3_leaf_ents_p(leaf);
+		dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf);
+		ents = dp->d_ops->leaf_ents_p(leaf);
 		count += hdr2.count - hdr2.stale;
 		bytes -= count * sizeof(ents[0]);
 
@@ -1559,6 +1520,7 @@ xfs_dir2_leafn_unbalance(
 	struct xfs_dir3_icleaf_hdr drophdr;
 	struct xfs_dir2_leaf_entry *sents;
 	struct xfs_dir2_leaf_entry *dents;
+	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
 	ASSERT(drop_blk->magic == XFS_DIR2_LEAFN_MAGIC);
@@ -1566,10 +1528,10 @@ xfs_dir2_leafn_unbalance(
 	drop_leaf = drop_blk->bp->b_addr;
 	save_leaf = save_blk->bp->b_addr;
 
-	xfs_dir3_leaf_hdr_from_disk(&savehdr, save_leaf);
-	xfs_dir3_leaf_hdr_from_disk(&drophdr, drop_leaf);
-	sents = xfs_dir3_leaf_ents_p(save_leaf);
-	dents = xfs_dir3_leaf_ents_p(drop_leaf);
+	dp->d_ops->leaf_hdr_from_disk(&savehdr, save_leaf);
+	dp->d_ops->leaf_hdr_from_disk(&drophdr, drop_leaf);
+	sents = dp->d_ops->leaf_ents_p(save_leaf);
+	dents = dp->d_ops->leaf_ents_p(drop_leaf);
 
 	/*
 	 * If there are any stale leaf entries, take this opportunity
@@ -1584,7 +1546,7 @@ xfs_dir2_leafn_unbalance(
 	 * Move the entries from drop to the appropriate end of save.
 	 */
 	drop_blk->hashval = be32_to_cpu(dents[drophdr.count - 1].hashval);
-	if (xfs_dir2_leafn_order(save_blk->bp, drop_blk->bp))
+	if (xfs_dir2_leafn_order(dp, save_blk->bp, drop_blk->bp))
 		xfs_dir3_leafn_moveents(args, drop_blk->bp, &drophdr, dents, 0,
 					save_blk->bp, &savehdr, sents, 0,
 					drophdr.count);
@@ -1595,13 +1557,13 @@ xfs_dir2_leafn_unbalance(
 	save_blk->hashval = be32_to_cpu(sents[savehdr.count - 1].hashval);
 
 	/* log the changes made when moving the entries */
-	xfs_dir3_leaf_hdr_to_disk(save_leaf, &savehdr);
-	xfs_dir3_leaf_hdr_to_disk(drop_leaf, &drophdr);
-	xfs_dir3_leaf_log_header(args->trans, save_blk->bp);
-	xfs_dir3_leaf_log_header(args->trans, drop_blk->bp);
+	dp->d_ops->leaf_hdr_to_disk(save_leaf, &savehdr);
+	dp->d_ops->leaf_hdr_to_disk(drop_leaf, &drophdr);
+	xfs_dir3_leaf_log_header(args->trans, dp, save_blk->bp);
+	xfs_dir3_leaf_log_header(args->trans, dp, drop_blk->bp);
 
-	xfs_dir3_leaf_check(args->dp->i_mount, save_blk->bp);
-	xfs_dir3_leaf_check(args->dp->i_mount, drop_blk->bp);
+	xfs_dir3_leaf_check(dp, save_blk->bp);
+	xfs_dir3_leaf_check(dp, drop_blk->bp);
 }
 
 /*
@@ -1712,7 +1674,7 @@ xfs_dir2_node_addname_int(
 	dp = args->dp;
 	mp = dp->i_mount;
 	tp = args->trans;
-	length = xfs_dir3_data_entsize(mp, args->namelen);
+	length = dp->d_ops->data_entsize(args->namelen);
 	/*
 	 * If we came in with a freespace block that means that lookup
 	 * found an entry with our hash value.  This is the freespace
@@ -1726,8 +1688,8 @@ xfs_dir2_node_addname_int(
 		ifbno = fblk->blkno;
 		free = fbp->b_addr;
 		findex = fblk->index;
-		bests = xfs_dir3_free_bests_p(mp, free);
-		xfs_dir3_free_hdr_from_disk(&freehdr, free);
+		bests = dp->d_ops->free_bests_p(free);
+		dp->d_ops->free_hdr_from_disk(&freehdr, free);
 
 		/*
 		 * This means the free entry showed that the data block had
@@ -1819,8 +1781,8 @@ xfs_dir2_node_addname_int(
 		 * and the freehdr are actually initialised if they are placed
 		 * there, so we have to do it here to avoid warnings. Blech.
 		 */
-		bests = xfs_dir3_free_bests_p(mp, free);
-		xfs_dir3_free_hdr_from_disk(&freehdr, free);
+		bests = dp->d_ops->free_bests_p(free);
+		dp->d_ops->free_hdr_from_disk(&freehdr, free);
 		if (be16_to_cpu(bests[findex]) != NULLDATAOFF &&
 		    be16_to_cpu(bests[findex]) >= length)
 			dbno = freehdr.firstdb + findex;
@@ -1871,7 +1833,7 @@ xfs_dir2_node_addname_int(
 		 * Get the freespace block corresponding to the data block
 		 * that was just allocated.
 		 */
-		fbno = xfs_dir2_db_to_fdb(mp, dbno);
+		fbno = dp->d_ops->db_to_fdb(mp, dbno);
 		error = xfs_dir2_free_try_read(tp, dp,
 					       xfs_dir2_db_to_da(mp, fbno),
 					       &fbp);
@@ -1888,12 +1850,12 @@ xfs_dir2_node_addname_int(
 			if (error)
 				return error;
 
-			if (unlikely(xfs_dir2_db_to_fdb(mp, dbno) != fbno)) {
+			if (unlikely(dp->d_ops->db_to_fdb(mp, dbno) != fbno)) {
 				xfs_alert(mp,
 			"%s: dir ino %llu needed freesp block %lld for\n"
 			"  data block %lld, got %lld ifbno %llu lastfbno %d",
 					__func__, (unsigned long long)dp->i_ino,
-					(long long)xfs_dir2_db_to_fdb(mp, dbno),
+					(long long)dp->d_ops->db_to_fdb(mp, dbno),
 					(long long)dbno, (long long)fbno,
 					(unsigned long long)ifbno, lastfbno);
 				if (fblk) {
@@ -1918,30 +1880,30 @@ xfs_dir2_node_addname_int(
 			if (error)
 				return error;
 			free = fbp->b_addr;
-			bests = xfs_dir3_free_bests_p(mp, free);
-			xfs_dir3_free_hdr_from_disk(&freehdr, free);
+			bests = dp->d_ops->free_bests_p(free);
+			dp->d_ops->free_hdr_from_disk(&freehdr, free);
 
 			/*
 			 * Remember the first slot as our empty slot.
 			 */
 			freehdr.firstdb = (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
-					xfs_dir3_free_max_bests(mp);
+					dp->d_ops->free_max_bests(mp);
 		} else {
 			free = fbp->b_addr;
-			bests = xfs_dir3_free_bests_p(mp, free);
-			xfs_dir3_free_hdr_from_disk(&freehdr, free);
+			bests = dp->d_ops->free_bests_p(free);
+			dp->d_ops->free_hdr_from_disk(&freehdr, free);
 		}
 
 		/*
 		 * Set the freespace block index from the data block number.
 		 */
-		findex = xfs_dir2_db_to_fdindex(mp, dbno);
+		findex = dp->d_ops->db_to_fdindex(mp, dbno);
 		/*
 		 * If it's after the end of the current entries in the
 		 * freespace block, extend that table.
 		 */
 		if (findex >= freehdr.nvalid) {
-			ASSERT(findex < xfs_dir3_free_max_bests(mp));
+			ASSERT(findex < dp->d_ops->free_max_bests(mp));
 			freehdr.nvalid = findex + 1;
 			/*
 			 * Tag new entry so nused will go up.
@@ -1954,8 +1916,8 @@ xfs_dir2_node_addname_int(
 		 */
 		if (bests[findex] == cpu_to_be16(NULLDATAOFF)) {
 			freehdr.nused++;
-			xfs_dir3_free_hdr_to_disk(fbp->b_addr, &freehdr);
-			xfs_dir2_free_log_header(tp, fbp);
+			dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
+			xfs_dir2_free_log_header(tp, dp, fbp);
 		}
 		/*
 		 * Update the real value in the table.
@@ -1963,7 +1925,7 @@ xfs_dir2_node_addname_int(
 		 * change again.
 		 */
 		hdr = dbp->b_addr;
-		bf = xfs_dir3_data_bestfree_p(hdr);
+		bf = dp->d_ops->data_bestfree_p(hdr);
 		bests[findex] = bf[0].length;
 		logfree = 1;
 	}
@@ -1985,7 +1947,7 @@ xfs_dir2_node_addname_int(
 		if (error)
 			return error;
 		hdr = dbp->b_addr;
-		bf = xfs_dir3_data_bestfree_p(hdr);
+		bf = dp->d_ops->data_bestfree_p(hdr);
 		logfree = 0;
 	}
 	ASSERT(be16_to_cpu(bf[0].length) >= length);
@@ -1998,7 +1960,7 @@ xfs_dir2_node_addname_int(
 	/*
 	 * Mark the first part of the unused space, inuse for us.
 	 */
-	xfs_dir2_data_use_free(tp, dbp, dup,
+	xfs_dir2_data_use_free(tp, dp, dbp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
 		&needlog, &needscan);
 	/*
@@ -2008,24 +1970,24 @@ xfs_dir2_node_addname_int(
 	dep->inumber = cpu_to_be64(args->inumber);
 	dep->namelen = args->namelen;
 	memcpy(dep->name, args->name, dep->namelen);
-	xfs_dir3_dirent_put_ftype(mp, dep, args->filetype);
-	tagp = xfs_dir3_data_entry_tag_p(mp, dep);
+	dp->d_ops->data_put_ftype(dep, args->filetype);
+	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, dbp, dep);
+	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
 	/*
 	 * Rescan the block for bestfree if needed.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(mp, hdr, &needlog);
+		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	/*
 	 * Log the data block header if needed.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dbp);
+		xfs_dir2_data_log_header(tp, dp, dbp);
 	/*
 	 * If the freespace entry is now wrong, update it.
 	 */
-	bests = xfs_dir3_free_bests_p(mp, free); /* gcc is so stupid */
+	bests = dp->d_ops->free_bests_p(free); /* gcc is so stupid */
 	if (be16_to_cpu(bests[findex]) != be16_to_cpu(bf[0].length)) {
 		bests[findex] = bf[0].length;
 		logfree = 1;
@@ -2034,7 +1996,7 @@ xfs_dir2_node_addname_int(
 	 * Log the freespace entry if needed.
 	 */
 	if (logfree)
-		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
 	/*
 	 * Return the data block and offset in args, then drop the data block.
 	 */
@@ -2212,7 +2174,7 @@ xfs_dir2_node_replace(
 		blk = &state->path.blk[state->path.active - 1];
 		ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
 		leaf = blk->bp->b_addr;
-		ents = xfs_dir3_leaf_ents_p(leaf);
+		ents = args->dp->d_ops->leaf_ents_p(leaf);
 		lep = &ents[blk->index];
 		ASSERT(state->extravalid);
 		/*
@@ -2229,8 +2191,9 @@ xfs_dir2_node_replace(
 		 * Fill in the new inode number and log the entry.
 		 */
 		dep->inumber = cpu_to_be64(inum);
-		xfs_dir3_dirent_put_ftype(state->mp, dep, args->filetype);
-		xfs_dir2_data_log_entry(args->trans, state->extrablk.bp, dep);
+		args->dp->d_ops->data_put_ftype(dep, args->filetype);
+		xfs_dir2_data_log_entry(args->trans, args->dp,
+					state->extrablk.bp, dep);
 		rval = 0;
 	}
 	/*
@@ -2285,7 +2248,7 @@ xfs_dir2_node_trim_free(
 	if (!bp)
 		return 0;
 	free = bp->b_addr;
-	xfs_dir3_free_hdr_from_disk(&freehdr, free);
+	dp->d_ops->free_hdr_from_disk(&freehdr, free);
 
 	/*
 	 * If there are used entries, there's nothing to do.

fs/xfs/xfs_dir2_priv.h

@@ -59,7 +59,8 @@ extern int xfs_dir3_data_readahead(struct xfs_trans *tp, struct xfs_inode *dp,
 
 extern struct xfs_dir2_data_free *
 xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
-		struct xfs_dir2_data_unused *dup, int *loghead);
+		struct xfs_dir2_data_free *bf, struct xfs_dir2_data_unused *dup,
+		int *loghead);
 extern int xfs_dir3_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
 		struct xfs_buf **bpp);
 
@@ -76,9 +77,9 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno,
 		struct xfs_buf **bpp, __uint16_t magic);
-extern void xfs_dir3_leaf_log_ents(struct xfs_trans *tp, struct xfs_buf *bp,
-		int first, int last);
-extern void xfs_dir3_leaf_log_header(struct xfs_trans *tp,
+extern void xfs_dir3_leaf_log_ents(struct xfs_trans *tp, struct xfs_inode *dp,
+		struct xfs_buf *bp, int first, int last);
+extern void xfs_dir3_leaf_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
 		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);
@@ -93,21 +94,18 @@ xfs_dir3_leaf_find_entry(struct xfs_dir3_icleaf_hdr *leafhdr,
 		int lowstale, int highstale, int *lfloglow, int *lfloghigh);
 extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
-extern void xfs_dir3_leaf_hdr_from_disk(struct xfs_dir3_icleaf_hdr *to,
-		struct xfs_dir2_leaf *from);
-extern void xfs_dir3_leaf_hdr_to_disk(struct xfs_dir2_leaf *to,
-		struct xfs_dir3_icleaf_hdr *from);
-extern bool xfs_dir3_leaf_check_int(struct xfs_mount *mp,
+extern bool xfs_dir3_leaf_check_int(struct xfs_mount *mp, struct xfs_inode *dp,
 		struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf);
 
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
 		struct xfs_buf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_buf *bp, int *count);
+extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_inode *dp,
+		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_buf *leaf1_bp,
+extern int xfs_dir2_leafn_order(struct xfs_inode *dp, 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);

fs/xfs/xfs_dir2_readdir.c

@@ -18,23 +18,23 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
+#include "xfs_trans.h"
+#include "xfs_dinode.h"
 
 /*
  * Directory file type support functions
@@ -119,9 +119,9 @@ xfs_dir2_sf_getdents(
 	 * mp->m_dirdatablk.
 	 */
 	dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
-					     xfs_dir3_data_dot_offset(mp));
+						dp->d_ops->data_dot_offset);
 	dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
-						xfs_dir3_data_dotdot_offset(mp));
+						dp->d_ops->data_dotdot_offset);
 
 	/*
 	 * Put . entry unless we're starting past it.
@@ -136,7 +136,7 @@ xfs_dir2_sf_getdents(
 	 * Put .. entry unless we're starting past it.
 	 */
 	if (ctx->pos <= dotdot_offset) {
-		ino = xfs_dir2_sf_get_parent_ino(sfp);
+		ino = dp->d_ops->sf_get_parent_ino(sfp);
 		ctx->pos = dotdot_offset & 0x7fffffff;
 		if (!dir_emit(ctx, "..", 2, ino, DT_DIR))
 			return 0;
@@ -153,17 +153,17 @@ xfs_dir2_sf_getdents(
 				xfs_dir2_sf_get_offset(sfep));
 
 		if (ctx->pos > off) {
-			sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+			sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 			continue;
 		}
 
-		ino = xfs_dir3_sfe_get_ino(mp, sfp, sfep);
-		filetype = xfs_dir3_sfe_get_ftype(mp, sfp, sfep);
+		ino = dp->d_ops->sf_get_ino(sfp, sfep);
+		filetype = dp->d_ops->sf_get_ftype(sfep);
 		ctx->pos = off & 0x7fffffff;
 		if (!dir_emit(ctx, (char *)sfep->name, sfep->namelen, ino,
 			    xfs_dir3_get_dtype(mp, filetype)))
 			return 0;
-		sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+		sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 	}
 
 	ctx->pos = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
@@ -213,7 +213,7 @@ xfs_dir2_block_getdents(
 	 * Set up values for the loop.
 	 */
 	btp = xfs_dir2_block_tail_p(mp, hdr);
-	ptr = (char *)xfs_dir3_data_entry_p(hdr);
+	ptr = (char *)dp->d_ops->data_entry_p(hdr);
 	endptr = (char *)xfs_dir2_block_leaf_p(btp);
 
 	/*
@@ -237,7 +237,7 @@ xfs_dir2_block_getdents(
 		/*
 		 * Bump pointer for the next iteration.
 		 */
-		ptr += xfs_dir3_data_entsize(mp, dep->namelen);
+		ptr += dp->d_ops->data_entsize(dep->namelen);
 		/*
 		 * The entry is before the desired starting point, skip it.
 		 */
@@ -248,7 +248,7 @@ xfs_dir2_block_getdents(
 					    (char *)dep - (char *)hdr);
 
 		ctx->pos = cook & 0x7fffffff;
-		filetype = xfs_dir3_dirent_get_ftype(mp, dep);
+		filetype = dp->d_ops->data_get_ftype(dep);
 		/*
 		 * If it didn't fit, set the final offset to here & return.
 		 */
@@ -578,13 +578,13 @@ xfs_dir2_leaf_getdents(
 			/*
 			 * Find our position in the block.
 			 */
-			ptr = (char *)xfs_dir3_data_entry_p(hdr);
+			ptr = (char *)dp->d_ops->data_entry_p(hdr);
 			byteoff = xfs_dir2_byte_to_off(mp, curoff);
 			/*
 			 * Skip past the header.
 			 */
 			if (byteoff == 0)
-				curoff += xfs_dir3_data_entry_offset(hdr);
+				curoff += dp->d_ops->data_entry_offset;
 			/*
 			 * Skip past entries until we reach our offset.
 			 */
@@ -601,7 +601,7 @@ xfs_dir2_leaf_getdents(
 					}
 					dep = (xfs_dir2_data_entry_t *)ptr;
 					length =
-					   xfs_dir3_data_entsize(mp, dep->namelen);
+					   dp->d_ops->data_entsize(dep->namelen);
 					ptr += length;
 				}
 				/*
@@ -632,8 +632,8 @@ xfs_dir2_leaf_getdents(
 		}
 
 		dep = (xfs_dir2_data_entry_t *)ptr;
-		length = xfs_dir3_data_entsize(mp, dep->namelen);
-		filetype = xfs_dir3_dirent_get_ftype(mp, dep);
+		length = dp->d_ops->data_entsize(dep->namelen);
+		filetype = dp->d_ops->data_get_ftype(dep);
 
 		ctx->pos = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
 		if (!dir_emit(ctx, (char *)dep->name, dep->namelen,

fs/xfs/xfs_dir2_sf.c

@@ -17,22 +17,22 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_error.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_trace.h"
+#include "xfs_dinode.h"
 
 /*
  * Prototypes for internal functions.
@@ -56,89 +56,6 @@ static void xfs_dir2_sf_toino4(xfs_da_args_t *args);
 static void xfs_dir2_sf_toino8(xfs_da_args_t *args);
 #endif /* XFS_BIG_INUMS */
 
-/*
- * Inode numbers in short-form directories can come in two versions,
- * either 4 bytes or 8 bytes wide.  These helpers deal with the
- * two forms transparently by looking at the headers i8count field.
- *
- * For 64-bit inode number the most significant byte must be zero.
- */
-static xfs_ino_t
-xfs_dir2_sf_get_ino(
-	struct xfs_dir2_sf_hdr	*hdr,
-	xfs_dir2_inou_t		*from)
-{
-	if (hdr->i8count)
-		return get_unaligned_be64(&from->i8.i) & 0x00ffffffffffffffULL;
-	else
-		return get_unaligned_be32(&from->i4.i);
-}
-
-static void
-xfs_dir2_sf_put_ino(
-	struct xfs_dir2_sf_hdr	*hdr,
-	xfs_dir2_inou_t		*to,
-	xfs_ino_t		ino)
-{
-	ASSERT((ino & 0xff00000000000000ULL) == 0);
-
-	if (hdr->i8count)
-		put_unaligned_be64(ino, &to->i8.i);
-	else
-		put_unaligned_be32(ino, &to->i4.i);
-}
-
-xfs_ino_t
-xfs_dir2_sf_get_parent_ino(
-	struct xfs_dir2_sf_hdr	*hdr)
-{
-	return xfs_dir2_sf_get_ino(hdr, &hdr->parent);
-}
-
-void
-xfs_dir2_sf_put_parent_ino(
-	struct xfs_dir2_sf_hdr	*hdr,
-	xfs_ino_t		ino)
-{
-	xfs_dir2_sf_put_ino(hdr, &hdr->parent, ino);
-}
-
-/*
- * In short-form directory entries the inode numbers are stored at variable
- * offset behind the entry name. If the entry stores a filetype value, then it
- * sits between the name and the inode number. Hence the inode numbers may only
- * be accessed through the helpers below.
- */
-static xfs_dir2_inou_t *
-xfs_dir3_sfe_inop(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	__uint8_t	*ptr = &sfep->name[sfep->namelen];
-	if (xfs_sb_version_hasftype(&mp->m_sb))
-		ptr++;
-	return (xfs_dir2_inou_t *)ptr;
-}
-
-xfs_ino_t
-xfs_dir3_sfe_get_ino(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	return xfs_dir2_sf_get_ino(hdr, xfs_dir3_sfe_inop(mp, sfep));
-}
-
-void
-xfs_dir3_sfe_put_ino(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep,
-	xfs_ino_t		ino)
-{
-	xfs_dir2_sf_put_ino(hdr, xfs_dir3_sfe_inop(mp, sfep), ino);
-}
-
 /*
  * Given a block directory (dp/block), calculate its size as a shortform (sf)
  * directory and a header for the sf directory, if it will fit it the
@@ -226,7 +143,7 @@ xfs_dir2_block_sfsize(
 	 */
 	sfhp->count = count;
 	sfhp->i8count = i8count;
-	xfs_dir2_sf_put_parent_ino(sfhp, parent);
+	dp->d_ops->sf_put_parent_ino(sfhp, parent);
 	return size;
 }
 
@@ -293,7 +210,7 @@ xfs_dir2_block_to_sf(
 	 * Set up to loop over the block's entries.
 	 */
 	btp = xfs_dir2_block_tail_p(mp, hdr);
-	ptr = (char *)xfs_dir3_data_entry_p(hdr);
+	ptr = (char *)dp->d_ops->data_entry_p(hdr);
 	endptr = (char *)xfs_dir2_block_leaf_p(btp);
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	/*
@@ -321,7 +238,7 @@ xfs_dir2_block_to_sf(
 		else if (dep->namelen == 2 &&
 			 dep->name[0] == '.' && dep->name[1] == '.')
 			ASSERT(be64_to_cpu(dep->inumber) ==
-			       xfs_dir2_sf_get_parent_ino(sfp));
+			       dp->d_ops->sf_get_parent_ino(sfp));
 		/*
 		 * Normal entry, copy it into shortform.
 		 */
@@ -331,14 +248,14 @@ xfs_dir2_block_to_sf(
 				(xfs_dir2_data_aoff_t)
 				((char *)dep - (char *)hdr));
 			memcpy(sfep->name, dep->name, dep->namelen);
-			xfs_dir3_sfe_put_ino(mp, sfp, sfep,
-					     be64_to_cpu(dep->inumber));
-			xfs_dir3_sfe_put_ftype(mp, sfp, sfep,
-					xfs_dir3_dirent_get_ftype(mp, dep));
+			dp->d_ops->sf_put_ino(sfp, sfep,
+					      be64_to_cpu(dep->inumber));
+			dp->d_ops->sf_put_ftype(sfep,
+					dp->d_ops->data_get_ftype(dep));
 
-			sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+			sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 		}
-		ptr += xfs_dir3_data_entsize(mp, dep->namelen);
+		ptr += dp->d_ops->data_entsize(dep->namelen);
 	}
 	ASSERT((char *)sfep - (char *)sfp == size);
 	xfs_dir2_sf_check(args);
@@ -389,7 +306,7 @@ xfs_dir2_sf_addname(
 	/*
 	 * Compute entry (and change in) size.
 	 */
-	add_entsize = xfs_dir3_sf_entsize(dp->i_mount, sfp, args->namelen);
+	add_entsize = dp->d_ops->sf_entsize(sfp, args->namelen);
 	incr_isize = add_entsize;
 	objchange = 0;
 #if XFS_BIG_INUMS
@@ -483,8 +400,7 @@ xfs_dir2_sf_addname_easy(
 	/*
 	 * Grow the in-inode space.
 	 */
-	xfs_idata_realloc(dp,
-			  xfs_dir3_sf_entsize(dp->i_mount, sfp, args->namelen),
+	xfs_idata_realloc(dp, dp->d_ops->sf_entsize(sfp, args->namelen),
 			  XFS_DATA_FORK);
 	/*
 	 * Need to set up again due to realloc of the inode data.
@@ -497,8 +413,8 @@ xfs_dir2_sf_addname_easy(
 	sfep->namelen = args->namelen;
 	xfs_dir2_sf_put_offset(sfep, offset);
 	memcpy(sfep->name, args->name, sfep->namelen);
-	xfs_dir3_sfe_put_ino(dp->i_mount, sfp, sfep, args->inumber);
-	xfs_dir3_sfe_put_ftype(dp->i_mount, sfp, sfep, args->filetype);
+	dp->d_ops->sf_put_ino(sfp, sfep, args->inumber);
+	dp->d_ops->sf_put_ftype(sfep, args->filetype);
 
 	/*
 	 * Update the header and inode.
@@ -557,13 +473,13 @@ xfs_dir2_sf_addname_hard(
 	 * to insert the new entry.
 	 * If it's going to end up at the end then oldsfep will point there.
 	 */
-	for (offset = xfs_dir3_data_first_offset(mp),
+	for (offset = dp->d_ops->data_first_offset,
 	      oldsfep = xfs_dir2_sf_firstentry(oldsfp),
-	      add_datasize = xfs_dir3_data_entsize(mp, args->namelen),
+	      add_datasize = dp->d_ops->data_entsize(args->namelen),
 	      eof = (char *)oldsfep == &buf[old_isize];
 	     !eof;
-	     offset = new_offset + xfs_dir3_data_entsize(mp, oldsfep->namelen),
-	      oldsfep = xfs_dir3_sf_nextentry(mp, oldsfp, oldsfep),
+	     offset = new_offset + dp->d_ops->data_entsize(oldsfep->namelen),
+	      oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep),
 	      eof = (char *)oldsfep == &buf[old_isize]) {
 		new_offset = xfs_dir2_sf_get_offset(oldsfep);
 		if (offset + add_datasize <= new_offset)
@@ -592,8 +508,8 @@ xfs_dir2_sf_addname_hard(
 	sfep->namelen = args->namelen;
 	xfs_dir2_sf_put_offset(sfep, offset);
 	memcpy(sfep->name, args->name, sfep->namelen);
-	xfs_dir3_sfe_put_ino(mp, sfp, sfep, args->inumber);
-	xfs_dir3_sfe_put_ftype(mp, sfp, sfep, args->filetype);
+	dp->d_ops->sf_put_ino(sfp, sfep, args->inumber);
+	dp->d_ops->sf_put_ftype(sfep, args->filetype);
 	sfp->count++;
 #if XFS_BIG_INUMS
 	if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && !objchange)
@@ -603,7 +519,7 @@ xfs_dir2_sf_addname_hard(
 	 * If there's more left to copy, do that.
 	 */
 	if (!eof) {
-		sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+		sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 		memcpy(sfep, oldsfep, old_isize - nbytes);
 	}
 	kmem_free(buf);
@@ -639,8 +555,8 @@ xfs_dir2_sf_addname_pick(
 	mp = dp->i_mount;
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	size = xfs_dir3_data_entsize(mp, args->namelen);
-	offset = xfs_dir3_data_first_offset(mp);
+	size = dp->d_ops->data_entsize(args->namelen);
+	offset = dp->d_ops->data_first_offset;
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	holefit = 0;
 	/*
@@ -652,8 +568,8 @@ xfs_dir2_sf_addname_pick(
 		if (!holefit)
 			holefit = offset + size <= xfs_dir2_sf_get_offset(sfep);
 		offset = xfs_dir2_sf_get_offset(sfep) +
-			 xfs_dir3_data_entsize(mp, sfep->namelen);
-		sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep);
+			 dp->d_ops->data_entsize(sfep->namelen);
+		sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 	}
 	/*
 	 * Calculate data bytes used excluding the new entry, if this
@@ -713,21 +629,20 @@ xfs_dir2_sf_check(
 	mp = dp->i_mount;
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	offset = xfs_dir3_data_first_offset(mp);
-	ino = xfs_dir2_sf_get_parent_ino(sfp);
+	offset = dp->d_ops->data_first_offset;
+	ino = dp->d_ops->sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
 
 	for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp);
 	     i < sfp->count;
-	     i++, sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep)) {
+	     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) {
 		ASSERT(xfs_dir2_sf_get_offset(sfep) >= offset);
-		ino = xfs_dir3_sfe_get_ino(mp, sfp, sfep);
+		ino = dp->d_ops->sf_get_ino(sfp, sfep);
 		i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
 		offset =
 			xfs_dir2_sf_get_offset(sfep) +
-			xfs_dir3_data_entsize(mp, sfep->namelen);
-		ASSERT(xfs_dir3_sfe_get_ftype(mp, sfp, sfep) <
-							XFS_DIR3_FT_MAX);
+			dp->d_ops->data_entsize(sfep->namelen);
+		ASSERT(dp->d_ops->sf_get_ftype(sfep) < XFS_DIR3_FT_MAX);
 	}
 	ASSERT(i8count == sfp->i8count);
 	ASSERT(XFS_BIG_INUMS || i8count == 0);
@@ -783,7 +698,7 @@ xfs_dir2_sf_create(
 	/*
 	 * Now can put in the inode number, since i8count is set.
 	 */
-	xfs_dir2_sf_put_parent_ino(sfp, pino);
+	dp->d_ops->sf_put_parent_ino(sfp, pino);
 	sfp->count = 0;
 	dp->i_d.di_size = size;
 	xfs_dir2_sf_check(args);
@@ -838,7 +753,7 @@ xfs_dir2_sf_lookup(
 	 */
 	if (args->namelen == 2 &&
 	    args->name[0] == '.' && args->name[1] == '.') {
-		args->inumber = xfs_dir2_sf_get_parent_ino(sfp);
+		args->inumber = dp->d_ops->sf_get_parent_ino(sfp);
 		args->cmpresult = XFS_CMP_EXACT;
 		args->filetype = XFS_DIR3_FT_DIR;
 		return XFS_ERROR(EEXIST);
@@ -848,7 +763,7 @@ xfs_dir2_sf_lookup(
 	 */
 	ci_sfep = NULL;
 	for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count;
-	     i++, sfep = xfs_dir3_sf_nextentry(dp->i_mount, sfp, sfep)) {
+	     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) {
 		/*
 		 * Compare name and if it's an exact match, return the inode
 		 * number. If it's the first case-insensitive match, store the
@@ -858,10 +773,8 @@ xfs_dir2_sf_lookup(
 								sfep->namelen);
 		if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
 			args->cmpresult = cmp;
-			args->inumber = xfs_dir3_sfe_get_ino(dp->i_mount,
-							     sfp, sfep);
-			args->filetype = xfs_dir3_sfe_get_ftype(dp->i_mount,
-								sfp, sfep);
+			args->inumber = dp->d_ops->sf_get_ino(sfp, sfep);
+			args->filetype = dp->d_ops->sf_get_ftype(sfep);
 			if (cmp == XFS_CMP_EXACT)
 				return XFS_ERROR(EEXIST);
 			ci_sfep = sfep;
@@ -917,10 +830,10 @@ xfs_dir2_sf_removename(
 	 * Find the one we're deleting.
 	 */
 	for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count;
-	     i++, sfep = xfs_dir3_sf_nextentry(dp->i_mount, sfp, sfep)) {
+	     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) {
 		if (xfs_da_compname(args, sfep->name, sfep->namelen) ==
 								XFS_CMP_EXACT) {
-			ASSERT(xfs_dir3_sfe_get_ino(dp->i_mount, sfp, sfep) ==
+			ASSERT(dp->d_ops->sf_get_ino(sfp, sfep) ==
 			       args->inumber);
 			break;
 		}
@@ -934,7 +847,7 @@ xfs_dir2_sf_removename(
 	 * Calculate sizes.
 	 */
 	byteoff = (int)((char *)sfep - (char *)sfp);
-	entsize = xfs_dir3_sf_entsize(dp->i_mount, sfp, args->namelen);
+	entsize = dp->d_ops->sf_entsize(sfp, args->namelen);
 	newsize = oldsize - entsize;
 	/*
 	 * Copy the part if any after the removed entry, sliding it down.
@@ -1041,28 +954,25 @@ xfs_dir2_sf_replace(
 	if (args->namelen == 2 &&
 	    args->name[0] == '.' && args->name[1] == '.') {
 #if XFS_BIG_INUMS || defined(DEBUG)
-		ino = xfs_dir2_sf_get_parent_ino(sfp);
+		ino = dp->d_ops->sf_get_parent_ino(sfp);
 		ASSERT(args->inumber != ino);
 #endif
-		xfs_dir2_sf_put_parent_ino(sfp, args->inumber);
+		dp->d_ops->sf_put_parent_ino(sfp, args->inumber);
 	}
 	/*
 	 * Normal entry, look for the name.
 	 */
 	else {
 		for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count;
-		     i++, sfep = xfs_dir3_sf_nextentry(dp->i_mount, sfp, sfep)) {
+		     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) {
 			if (xfs_da_compname(args, sfep->name, sfep->namelen) ==
 								XFS_CMP_EXACT) {
 #if XFS_BIG_INUMS || defined(DEBUG)
-				ino = xfs_dir3_sfe_get_ino(dp->i_mount,
-							   sfp, sfep);
+				ino = dp->d_ops->sf_get_ino(sfp, sfep);
 				ASSERT(args->inumber != ino);
 #endif
-				xfs_dir3_sfe_put_ino(dp->i_mount, sfp, sfep,
-						     args->inumber);
-				xfs_dir3_sfe_put_ftype(dp->i_mount, sfp, sfep,
-						       args->filetype);
+				dp->d_ops->sf_put_ino(sfp, sfep, args->inumber);
+				dp->d_ops->sf_put_ftype(sfep, args->filetype);
 				break;
 			}
 		}
@@ -1165,22 +1075,21 @@ xfs_dir2_sf_toino4(
 	 */
 	sfp->count = oldsfp->count;
 	sfp->i8count = 0;
-	xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp));
+	dp->d_ops->sf_put_parent_ino(sfp, dp->d_ops->sf_get_parent_ino(oldsfp));
 	/*
 	 * Copy the entries field by field.
 	 */
 	for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp),
 		    oldsfep = xfs_dir2_sf_firstentry(oldsfp);
 	     i < sfp->count;
-	     i++, sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep),
-		  oldsfep = xfs_dir3_sf_nextentry(mp, oldsfp, oldsfep)) {
+	     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep),
+		  oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep)) {
 		sfep->namelen = oldsfep->namelen;
 		sfep->offset = oldsfep->offset;
 		memcpy(sfep->name, oldsfep->name, sfep->namelen);
-		xfs_dir3_sfe_put_ino(mp, sfp, sfep,
-			xfs_dir3_sfe_get_ino(mp, oldsfp, oldsfep));
-		xfs_dir3_sfe_put_ftype(mp, sfp, sfep,
-			xfs_dir3_sfe_get_ftype(mp, oldsfp, oldsfep));
+		dp->d_ops->sf_put_ino(sfp, sfep,
+				      dp->d_ops->sf_get_ino(oldsfp, oldsfep));
+		dp->d_ops->sf_put_ftype(sfep, dp->d_ops->sf_get_ftype(oldsfep));
 	}
 	/*
 	 * Clean up the inode.
@@ -1244,22 +1153,21 @@ xfs_dir2_sf_toino8(
 	 */
 	sfp->count = oldsfp->count;
 	sfp->i8count = 1;
-	xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp));
+	dp->d_ops->sf_put_parent_ino(sfp, dp->d_ops->sf_get_parent_ino(oldsfp));
 	/*
 	 * Copy the entries field by field.
 	 */
 	for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp),
 		    oldsfep = xfs_dir2_sf_firstentry(oldsfp);
 	     i < sfp->count;
-	     i++, sfep = xfs_dir3_sf_nextentry(mp, sfp, sfep),
-		  oldsfep = xfs_dir3_sf_nextentry(mp, oldsfp, oldsfep)) {
+	     i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep),
+		  oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep)) {
 		sfep->namelen = oldsfep->namelen;
 		sfep->offset = oldsfep->offset;
 		memcpy(sfep->name, oldsfep->name, sfep->namelen);
-		xfs_dir3_sfe_put_ino(mp, sfp, sfep,
-			xfs_dir3_sfe_get_ino(mp, oldsfp, oldsfep));
-		xfs_dir3_sfe_put_ftype(mp, sfp, sfep,
-			xfs_dir3_sfe_get_ftype(mp, oldsfp, oldsfep));
+		dp->d_ops->sf_put_ino(sfp, sfep,
+				      dp->d_ops->sf_get_ino(oldsfp, oldsfep));
+		dp->d_ops->sf_put_ftype(sfep, dp->d_ops->sf_get_ftype(oldsfep));
 	}
 	/*
 	 * Clean up the inode.

fs/xfs/xfs_discard.c

@@ -17,22 +17,21 @@
  */
 #include "xfs.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_quota.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_btree.h"
 #include "xfs_inode.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 #include "xfs_extent_busy.h"
 #include "xfs_discard.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
 
 STATIC int
 xfs_trim_extents(

fs/xfs/xfs_dquot.c

@@ -18,28 +18,28 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_rtalloc.h"
+#include "xfs_alloc.h"
+#include "xfs_quota.h"
 #include "xfs_error.h"
-#include "xfs_itable.h"
-#include "xfs_attr.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_space.h"
 #include "xfs_trans_priv.h"
 #include "xfs_qm.h"
 #include "xfs_cksum.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
+#include "xfs_bmap_btree.h"
 
 /*
  * Lock order:
@@ -292,118 +292,6 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
 	dqp->q_low_space[XFS_QLOWSP_5_PCNT] = space * 5;
 }
 
-STATIC bool
-xfs_dquot_buf_verify_crc(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
-{
-	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
-	int			ndquots;
-	int			i;
-
-	if (!xfs_sb_version_hascrc(&mp->m_sb))
-		return true;
-
-	/*
-	 * if we are in log recovery, the quota subsystem has not been
-	 * initialised so we have no quotainfo structure. In that case, we need
-	 * to manually calculate the number of dquots in the buffer.
-	 */
-	if (mp->m_quotainfo)
-		ndquots = mp->m_quotainfo->qi_dqperchunk;
-	else
-		ndquots = xfs_qm_calc_dquots_per_chunk(mp,
-					XFS_BB_TO_FSB(mp, bp->b_length));
-
-	for (i = 0; i < ndquots; i++, d++) {
-		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
-				 XFS_DQUOT_CRC_OFF))
-			return false;
-		if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_uuid))
-			return false;
-	}
-	return true;
-}
-
-STATIC bool
-xfs_dquot_buf_verify(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
-{
-	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
-	xfs_dqid_t		id = 0;
-	int			ndquots;
-	int			i;
-
-	/*
-	 * if we are in log recovery, the quota subsystem has not been
-	 * initialised so we have no quotainfo structure. In that case, we need
-	 * to manually calculate the number of dquots in the buffer.
-	 */
-	if (mp->m_quotainfo)
-		ndquots = mp->m_quotainfo->qi_dqperchunk;
-	else
-		ndquots = xfs_qm_calc_dquots_per_chunk(mp, bp->b_length);
-
-	/*
-	 * On the first read of the buffer, verify that each dquot is valid.
-	 * We don't know what the id of the dquot is supposed to be, just that
-	 * they should be increasing monotonically within the buffer. If the
-	 * first id is corrupt, then it will fail on the second dquot in the
-	 * buffer so corruptions could point to the wrong dquot in this case.
-	 */
-	for (i = 0; i < ndquots; i++) {
-		struct xfs_disk_dquot	*ddq;
-		int			error;
-
-		ddq = &d[i].dd_diskdq;
-
-		if (i == 0)
-			id = be32_to_cpu(ddq->d_id);
-
-		error = xfs_qm_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
-				       "xfs_dquot_buf_verify");
-		if (error)
-			return false;
-	}
-	return true;
-}
-
-static void
-xfs_dquot_buf_read_verify(
-	struct xfs_buf	*bp)
-{
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
-
-	if (!xfs_dquot_buf_verify_crc(mp, bp) || !xfs_dquot_buf_verify(mp, bp)) {
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-		xfs_buf_ioerror(bp, EFSCORRUPTED);
-	}
-}
-
-/*
- * we don't calculate the CRC here as that is done when the dquot is flushed to
- * the buffer after the update is done. This ensures that the dquot in the
- * buffer always has an up-to-date CRC value.
- */
-void
-xfs_dquot_buf_write_verify(
-	struct xfs_buf	*bp)
-{
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
-
-	if (!xfs_dquot_buf_verify(mp, bp)) {
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-		xfs_buf_ioerror(bp, EFSCORRUPTED);
-		return;
-	}
-}
-
-const struct xfs_buf_ops xfs_dquot_buf_ops = {
-	.verify_read = xfs_dquot_buf_read_verify,
-	.verify_write = xfs_dquot_buf_write_verify,
-};
-
 /*
  * Allocate a block and fill it with dquots.
  * This is called when the bmapi finds a hole.
@@ -514,6 +402,7 @@ xfs_qm_dqalloc(
 
 	return (error);
 }
+
 STATIC int
 xfs_qm_dqrepair(
 	struct xfs_mount	*mp,
@@ -547,7 +436,7 @@ xfs_qm_dqrepair(
 	/* Do the actual repair of dquots in this buffer */
 	for (i = 0; i < mp->m_quotainfo->qi_dqperchunk; i++) {
 		ddq = &d[i].dd_diskdq;
-		error = xfs_qm_dqcheck(mp, ddq, firstid + i,
+		error = xfs_dqcheck(mp, ddq, firstid + i,
 				       dqp->dq_flags & XFS_DQ_ALLTYPES,
 				       XFS_QMOPT_DQREPAIR, "xfs_qm_dqrepair");
 		if (error) {
@@ -1133,7 +1022,7 @@ xfs_qm_dqflush(
 	/*
 	 * A simple sanity check in case we got a corrupted dquot..
 	 */
-	error = xfs_qm_dqcheck(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
+	error = xfs_dqcheck(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
 			   XFS_QMOPT_DOWARN, "dqflush (incore copy)");
 	if (error) {
 		xfs_buf_relse(bp);

fs/xfs/xfs_dquot.h

@@ -172,6 +172,4 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
 	return dqp;
 }
 
-extern const struct xfs_buf_ops xfs_dquot_buf_ops;
-
 #endif /* __XFS_DQUOT_H__ */

fs/xfs/xfs_dquot_buf.c

@@ -0,0 +1,288 @@
+/*
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_trans.h"
+#include "xfs_qm.h"
+#include "xfs_error.h"
+#include "xfs_cksum.h"
+#include "xfs_trace.h"
+
+int
+xfs_calc_dquots_per_chunk(
+	struct xfs_mount	*mp,
+	unsigned int		nbblks)	/* basic block units */
+{
+	unsigned int	ndquots;
+
+	ASSERT(nbblks > 0);
+	ndquots = BBTOB(nbblks);
+	do_div(ndquots, sizeof(xfs_dqblk_t));
+
+	return ndquots;
+}
+
+/*
+ * Do some primitive error checking on ondisk dquot data structures.
+ */
+int
+xfs_dqcheck(
+	struct xfs_mount *mp,
+	xfs_disk_dquot_t *ddq,
+	xfs_dqid_t	 id,
+	uint		 type,	  /* used only when IO_dorepair is true */
+	uint		 flags,
+	char		 *str)
+{
+	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
+	int		errs = 0;
+
+	/*
+	 * We can encounter an uninitialized dquot buffer for 2 reasons:
+	 * 1. If we crash while deleting the quotainode(s), and those blks got
+	 *    used for user data. This is because we take the path of regular
+	 *    file deletion; however, the size field of quotainodes is never
+	 *    updated, so all the tricks that we play in itruncate_finish
+	 *    don't quite matter.
+	 *
+	 * 2. We don't play the quota buffers when there's a quotaoff logitem.
+	 *    But the allocation will be replayed so we'll end up with an
+	 *    uninitialized quota block.
+	 *
+	 * This is all fine; things are still consistent, and we haven't lost
+	 * any quota information. Just don't complain about bad dquot blks.
+	 */
+	if (ddq->d_magic != cpu_to_be16(XFS_DQUOT_MAGIC)) {
+		if (flags & XFS_QMOPT_DOWARN)
+			xfs_alert(mp,
+			"%s : XFS dquot ID 0x%x, magic 0x%x != 0x%x",
+			str, id, be16_to_cpu(ddq->d_magic), XFS_DQUOT_MAGIC);
+		errs++;
+	}
+	if (ddq->d_version != XFS_DQUOT_VERSION) {
+		if (flags & XFS_QMOPT_DOWARN)
+			xfs_alert(mp,
+			"%s : XFS dquot ID 0x%x, version 0x%x != 0x%x",
+			str, id, ddq->d_version, XFS_DQUOT_VERSION);
+		errs++;
+	}
+
+	if (ddq->d_flags != XFS_DQ_USER &&
+	    ddq->d_flags != XFS_DQ_PROJ &&
+	    ddq->d_flags != XFS_DQ_GROUP) {
+		if (flags & XFS_QMOPT_DOWARN)
+			xfs_alert(mp,
+			"%s : XFS dquot ID 0x%x, unknown flags 0x%x",
+			str, id, ddq->d_flags);
+		errs++;
+	}
+
+	if (id != -1 && id != be32_to_cpu(ddq->d_id)) {
+		if (flags & XFS_QMOPT_DOWARN)
+			xfs_alert(mp,
+			"%s : ondisk-dquot 0x%p, ID mismatch: "
+			"0x%x expected, found id 0x%x",
+			str, ddq, id, be32_to_cpu(ddq->d_id));
+		errs++;
+	}
+
+	if (!errs && ddq->d_id) {
+		if (ddq->d_blk_softlimit &&
+		    be64_to_cpu(ddq->d_bcount) >
+				be64_to_cpu(ddq->d_blk_softlimit)) {
+			if (!ddq->d_btimer) {
+				if (flags & XFS_QMOPT_DOWARN)
+					xfs_alert(mp,
+			"%s : Dquot ID 0x%x (0x%p) BLK TIMER NOT STARTED",
+					str, (int)be32_to_cpu(ddq->d_id), ddq);
+				errs++;
+			}
+		}
+		if (ddq->d_ino_softlimit &&
+		    be64_to_cpu(ddq->d_icount) >
+				be64_to_cpu(ddq->d_ino_softlimit)) {
+			if (!ddq->d_itimer) {
+				if (flags & XFS_QMOPT_DOWARN)
+					xfs_alert(mp,
+			"%s : Dquot ID 0x%x (0x%p) INODE TIMER NOT STARTED",
+					str, (int)be32_to_cpu(ddq->d_id), ddq);
+				errs++;
+			}
+		}
+		if (ddq->d_rtb_softlimit &&
+		    be64_to_cpu(ddq->d_rtbcount) >
+				be64_to_cpu(ddq->d_rtb_softlimit)) {
+			if (!ddq->d_rtbtimer) {
+				if (flags & XFS_QMOPT_DOWARN)
+					xfs_alert(mp,
+			"%s : Dquot ID 0x%x (0x%p) RTBLK TIMER NOT STARTED",
+					str, (int)be32_to_cpu(ddq->d_id), ddq);
+				errs++;
+			}
+		}
+	}
+
+	if (!errs || !(flags & XFS_QMOPT_DQREPAIR))
+		return errs;
+
+	if (flags & XFS_QMOPT_DOWARN)
+		xfs_notice(mp, "Re-initializing dquot ID 0x%x", id);
+
+	/*
+	 * Typically, a repair is only requested by quotacheck.
+	 */
+	ASSERT(id != -1);
+	ASSERT(flags & XFS_QMOPT_DQREPAIR);
+	memset(d, 0, sizeof(xfs_dqblk_t));
+
+	d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+	d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
+	d->dd_diskdq.d_flags = type;
+	d->dd_diskdq.d_id = cpu_to_be32(id);
+
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid);
+		xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
+				 XFS_DQUOT_CRC_OFF);
+	}
+
+	return errs;
+}
+
+STATIC bool
+xfs_dquot_buf_verify_crc(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
+	int			ndquots;
+	int			i;
+
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return true;
+
+	/*
+	 * if we are in log recovery, the quota subsystem has not been
+	 * initialised so we have no quotainfo structure. In that case, we need
+	 * to manually calculate the number of dquots in the buffer.
+	 */
+	if (mp->m_quotainfo)
+		ndquots = mp->m_quotainfo->qi_dqperchunk;
+	else
+		ndquots = xfs_calc_dquots_per_chunk(mp,
+					XFS_BB_TO_FSB(mp, bp->b_length));
+
+	for (i = 0; i < ndquots; i++, d++) {
+		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
+				 XFS_DQUOT_CRC_OFF))
+			return false;
+		if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_uuid))
+			return false;
+	}
+	return true;
+}
+
+STATIC bool
+xfs_dquot_buf_verify(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
+	xfs_dqid_t		id = 0;
+	int			ndquots;
+	int			i;
+
+	/*
+	 * if we are in log recovery, the quota subsystem has not been
+	 * initialised so we have no quotainfo structure. In that case, we need
+	 * to manually calculate the number of dquots in the buffer.
+	 */
+	if (mp->m_quotainfo)
+		ndquots = mp->m_quotainfo->qi_dqperchunk;
+	else
+		ndquots = xfs_calc_dquots_per_chunk(mp, bp->b_length);
+
+	/*
+	 * On the first read of the buffer, verify that each dquot is valid.
+	 * We don't know what the id of the dquot is supposed to be, just that
+	 * they should be increasing monotonically within the buffer. If the
+	 * first id is corrupt, then it will fail on the second dquot in the
+	 * buffer so corruptions could point to the wrong dquot in this case.
+	 */
+	for (i = 0; i < ndquots; i++) {
+		struct xfs_disk_dquot	*ddq;
+		int			error;
+
+		ddq = &d[i].dd_diskdq;
+
+		if (i == 0)
+			id = be32_to_cpu(ddq->d_id);
+
+		error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
+				       "xfs_dquot_buf_verify");
+		if (error)
+			return false;
+	}
+	return true;
+}
+
+static void
+xfs_dquot_buf_read_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify_crc(mp, bp) || !xfs_dquot_buf_verify(mp, bp)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+}
+
+/*
+ * we don't calculate the CRC here as that is done when the dquot is flushed to
+ * the buffer after the update is done. This ensures that the dquot in the
+ * buffer always has an up-to-date CRC value.
+ */
+static void
+xfs_dquot_buf_write_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify(mp, bp)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+		return;
+	}
+}
+
+const struct xfs_buf_ops xfs_dquot_buf_ops = {
+	.verify_read = xfs_dquot_buf_read_verify,
+	.verify_write = xfs_dquot_buf_write_verify,
+};
+

fs/xfs/xfs_dquot_item.c

@@ -18,23 +18,19 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_bmap.h"
-#include "xfs_rtalloc.h"
+#include "xfs_quota.h"
 #include "xfs_error.h"
-#include "xfs_itable.h"
-#include "xfs_attr.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
 #include "xfs_qm.h"
+#include "xfs_log.h"
 
 static inline struct xfs_dq_logitem *DQUOT_ITEM(struct xfs_log_item *lip)
 {

fs/xfs/xfs_error.c

@@ -16,16 +16,13 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_format.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
 #include "xfs_error.h"
 
 #ifdef DEBUG
@@ -159,7 +156,7 @@ xfs_error_report(
 {
 	if (level <= xfs_error_level) {
 		xfs_alert_tag(mp, XFS_PTAG_ERROR_REPORT,
-		"Internal error %s at line %d of file %s.  Caller 0x%p\n",
+		"Internal error %s at line %d of file %s.  Caller 0x%p",
 			    tag, linenum, filename, ra);
 
 		xfs_stack_trace();

fs/xfs/xfs_export.c

@@ -16,21 +16,21 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
+#include "xfs_da_format.h"
 #include "xfs_dir2.h"
 #include "xfs_export.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_log.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow

fs/xfs/xfs_extent_busy.c

@@ -19,17 +19,18 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_alloc.h"
-#include "xfs_inode.h"
 #include "xfs_extent_busy.h"
 #include "xfs_trace.h"
+#include "xfs_trans.h"
+#include "xfs_log.h"
 
 void
 xfs_extent_busy_insert(

fs/xfs/xfs_extent_busy.h

@@ -20,6 +20,10 @@
 #ifndef __XFS_EXTENT_BUSY_H__
 #define	__XFS_EXTENT_BUSY_H__
 
+struct xfs_mount;
+struct xfs_trans;
+struct xfs_alloc_arg;
+
 /*
  * Busy block/extent entry.  Indexed by a rbtree in perag to mark blocks that
  * have been freed but whose transactions aren't committed to disk yet.

fs/xfs/xfs_extfree_item.c

@@ -17,14 +17,14 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_buf_item.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_trans.h"
 #include "xfs_trans_priv.h"
+#include "xfs_buf_item.h"
 #include "xfs_extfree_item.h"
 
 

fs/xfs/xfs_file.c

@@ -17,25 +17,27 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_log.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_trans.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_error.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_ioctl.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
+#include "xfs_dinode.h"
 
 #include <linux/aio.h>
 #include <linux/dcache.h>
@@ -805,44 +807,64 @@ out:
 
 STATIC long
 xfs_file_fallocate(
-	struct file	*file,
-	int		mode,
-	loff_t		offset,
-	loff_t		len)
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
 {
-	struct inode	*inode = file_inode(file);
-	long		error;
-	loff_t		new_size = 0;
-	xfs_flock64_t	bf;
-	xfs_inode_t	*ip = XFS_I(inode);
-	int		cmd = XFS_IOC_RESVSP;
-	int		attr_flags = XFS_ATTR_NOLOCK;
+	struct inode		*inode = file_inode(file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_trans	*tp;
+	long			error;
+	loff_t			new_size = 0;
 
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 
-	bf.l_whence = 0;
-	bf.l_start = offset;
-	bf.l_len = len;
-
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		error = xfs_free_file_space(ip, offset, len);
+		if (error)
+			goto out_unlock;
+	} else {
+		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+		    offset + len > i_size_read(inode)) {
+			new_size = offset + len;
+			error = -inode_newsize_ok(inode, new_size);
+			if (error)
+				goto out_unlock;
+		}
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		cmd = XFS_IOC_UNRESVSP;
-
-	/* check the new inode size is valid before allocating */
-	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	    offset + len > i_size_read(inode)) {
-		new_size = offset + len;
-		error = inode_newsize_ok(inode, new_size);
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_PREALLOC);
 		if (error)
 			goto out_unlock;
 	}
 
-	if (file->f_flags & O_DSYNC)
-		attr_flags |= XFS_ATTR_SYNC;
+	tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
+	error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		goto out_unlock;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	ip->i_d.di_mode &= ~S_ISUID;
+	if (ip->i_d.di_mode & S_IXGRP)
+		ip->i_d.di_mode &= ~S_ISGID;
+
+	if (!(mode & FALLOC_FL_PUNCH_HOLE))
+		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
 
-	error = -xfs_change_file_space(ip, cmd, &bf, 0, attr_flags);
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	if (file->f_flags & O_DSYNC)
+		xfs_trans_set_sync(tp);
+	error = xfs_trans_commit(tp, 0);
 	if (error)
 		goto out_unlock;
 
@@ -852,12 +874,12 @@ xfs_file_fallocate(
 
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = new_size;
-		error = -xfs_setattr_size(ip, &iattr, XFS_ATTR_NOLOCK);
+		error = xfs_setattr_size(ip, &iattr);
 	}
 
 out_unlock:
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	return error;
+	return -error;
 }
 
 

fs/xfs/xfs_filestream.c

@@ -16,19 +16,19 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
-#include "xfs_log.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_inum.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_ag.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_mount.h"
+#include "xfs_inum.h"
+#include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_alloc.h"
 #include "xfs_mru_cache.h"
+#include "xfs_dinode.h"
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 

fs/xfs/xfs_format.h

@@ -156,14 +156,259 @@ struct xfs_dsymlink_hdr {
 	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
 			sizeof(struct xfs_dsymlink_hdr) : 0))
 
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-
-extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+
+/*
+ * Allocation Btree format definitions
+ *
+ * There are two on-disk btrees, one sorted by blockno and one sorted
+ * by blockcount and blockno.  All blocks look the same to make the code
+ * simpler; if we have time later, we'll make the optimizations.
+ */
+#define	XFS_ABTB_MAGIC		0x41425442	/* 'ABTB' for bno tree */
+#define	XFS_ABTB_CRC_MAGIC	0x41423342	/* 'AB3B' */
+#define	XFS_ABTC_MAGIC		0x41425443	/* 'ABTC' for cnt tree */
+#define	XFS_ABTC_CRC_MAGIC	0x41423343	/* 'AB3C' */
+
+/*
+ * Data record/key structure
+ */
+typedef struct xfs_alloc_rec {
+	__be32		ar_startblock;	/* starting block number */
+	__be32		ar_blockcount;	/* count of free blocks */
+} xfs_alloc_rec_t, xfs_alloc_key_t;
+
+typedef struct xfs_alloc_rec_incore {
+	xfs_agblock_t	ar_startblock;	/* starting block number */
+	xfs_extlen_t	ar_blockcount;	/* count of free blocks */
+} xfs_alloc_rec_incore_t;
+
+/* btree pointer type */
+typedef __be32 xfs_alloc_ptr_t;
+
+/*
+ * Block numbers in the AG:
+ * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
+ */
+#define	XFS_BNO_BLOCK(mp)	((xfs_agblock_t)(XFS_AGFL_BLOCK(mp) + 1))
+#define	XFS_CNT_BLOCK(mp)	((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))
+
+
+/*
+ * Inode Allocation Btree format definitions
+ *
+ * There is a btree for the inode map per allocation group.
+ */
+#define	XFS_IBT_MAGIC		0x49414254	/* 'IABT' */
+#define	XFS_IBT_CRC_MAGIC	0x49414233	/* 'IAB3' */
+
+typedef	__uint64_t	xfs_inofree_t;
+#define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
+#define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
+#define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
+#define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
+
+static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
+{
+	return ((n >= XFS_INODES_PER_CHUNK ? 0 : XFS_INOBT_MASK(n)) - 1) << i;
+}
+
+/*
+ * Data record structure
+ */
+typedef struct xfs_inobt_rec {
+	__be32		ir_startino;	/* starting inode number */
+	__be32		ir_freecount;	/* count of free inodes (set bits) */
+	__be64		ir_free;	/* free inode mask */
+} xfs_inobt_rec_t;
+
+typedef struct xfs_inobt_rec_incore {
+	xfs_agino_t	ir_startino;	/* starting inode number */
+	__int32_t	ir_freecount;	/* count of free inodes (set bits) */
+	xfs_inofree_t	ir_free;	/* free inode mask */
+} xfs_inobt_rec_incore_t;
+
+
+/*
+ * Key structure
+ */
+typedef struct xfs_inobt_key {
+	__be32		ir_startino;	/* starting inode number */
+} xfs_inobt_key_t;
+
+/* btree pointer type */
+typedef __be32 xfs_inobt_ptr_t;
+
+/*
+ * block numbers in the AG.
+ */
+#define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
+#define	XFS_PREALLOC_BLOCKS(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+
+
+
+/*
+ * BMAP Btree format definitions
+ *
+ * This includes both the root block definition that sits inside an inode fork
+ * and the record/pointer formats for the leaf/node in the blocks.
+ */
+#define XFS_BMAP_MAGIC		0x424d4150	/* 'BMAP' */
+#define XFS_BMAP_CRC_MAGIC	0x424d4133	/* 'BMA3' */
+
+/*
+ * Bmap root header, on-disk form only.
+ */
+typedef struct xfs_bmdr_block {
+	__be16		bb_level;	/* 0 is a leaf */
+	__be16		bb_numrecs;	/* current # of data records */
+} xfs_bmdr_block_t;
+
+/*
+ * Bmap btree record and extent descriptor.
+ *  l0:63 is an extent flag (value 1 indicates non-normal).
+ *  l0:9-62 are startoff.
+ *  l0:0-8 and l1:21-63 are startblock.
+ *  l1:0-20 are blockcount.
+ */
+#define BMBT_EXNTFLAG_BITLEN	1
+#define BMBT_STARTOFF_BITLEN	54
+#define BMBT_STARTBLOCK_BITLEN	52
+#define BMBT_BLOCKCOUNT_BITLEN	21
+
+typedef struct xfs_bmbt_rec {
+	__be64			l0, l1;
+} xfs_bmbt_rec_t;
+
+typedef __uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
+typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
+
+typedef struct xfs_bmbt_rec_host {
+	__uint64_t		l0, l1;
+} xfs_bmbt_rec_host_t;
+
+/*
+ * Values and macros for delayed-allocation startblock fields.
+ */
+#define STARTBLOCKVALBITS	17
+#define STARTBLOCKMASKBITS	(15 + XFS_BIG_BLKNOS * 20)
+#define DSTARTBLOCKMASKBITS	(15 + 20)
+#define STARTBLOCKMASK		\
+	(((((xfs_fsblock_t)1) << STARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
+#define DSTARTBLOCKMASK		\
+	(((((xfs_dfsbno_t)1) << DSTARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
+
+static inline int isnullstartblock(xfs_fsblock_t x)
+{
+	return ((x) & STARTBLOCKMASK) == STARTBLOCKMASK;
+}
+
+static inline int isnulldstartblock(xfs_dfsbno_t x)
+{
+	return ((x) & DSTARTBLOCKMASK) == DSTARTBLOCKMASK;
+}
+
+static inline xfs_fsblock_t nullstartblock(int k)
+{
+	ASSERT(k < (1 << STARTBLOCKVALBITS));
+	return STARTBLOCKMASK | (k);
+}
+
+static inline xfs_filblks_t startblockval(xfs_fsblock_t x)
+{
+	return (xfs_filblks_t)((x) & ~STARTBLOCKMASK);
+}
+
+/*
+ * Possible extent formats.
+ */
+typedef enum {
+	XFS_EXTFMT_NOSTATE = 0,
+	XFS_EXTFMT_HASSTATE
+} xfs_exntfmt_t;
+
+/*
+ * Possible extent states.
+ */
+typedef enum {
+	XFS_EXT_NORM, XFS_EXT_UNWRITTEN,
+	XFS_EXT_DMAPI_OFFLINE, XFS_EXT_INVALID
+} xfs_exntst_t;
+
+/*
+ * Incore version of above.
+ */
+typedef struct xfs_bmbt_irec
+{
+	xfs_fileoff_t	br_startoff;	/* starting file offset */
+	xfs_fsblock_t	br_startblock;	/* starting block number */
+	xfs_filblks_t	br_blockcount;	/* number of blocks */
+	xfs_exntst_t	br_state;	/* extent state */
+} xfs_bmbt_irec_t;
+
+/*
+ * Key structure for non-leaf levels of the tree.
+ */
+typedef struct xfs_bmbt_key {
+	__be64		br_startoff;	/* starting file offset */
+} xfs_bmbt_key_t, xfs_bmdr_key_t;
+
+/* btree pointer type */
+typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
+
+
+/*
+ * Generic Btree block format definitions
+ *
+ * This is a combination of the actual format used on disk for short and long
+ * format btrees.  The first three fields are shared by both format, but the
+ * pointers are different and should be used with care.
+ *
+ * To get the size of the actual short or long form headers please use the size
+ * macros below.  Never use sizeof(xfs_btree_block).
+ *
+ * The blkno, crc, lsn, owner and uuid fields are only available in filesystems
+ * with the crc feature bit, and all accesses to them must be conditional on
+ * that flag.
+ */
+struct xfs_btree_block {
+	__be32		bb_magic;	/* magic number for block type */
+	__be16		bb_level;	/* 0 is a leaf */
+	__be16		bb_numrecs;	/* current # of data records */
+	union {
+		struct {
+			__be32		bb_leftsib;
+			__be32		bb_rightsib;
+
+			__be64		bb_blkno;
+			__be64		bb_lsn;
+			uuid_t		bb_uuid;
+			__be32		bb_owner;
+			__le32		bb_crc;
+		} s;			/* short form pointers */
+		struct	{
+			__be64		bb_leftsib;
+			__be64		bb_rightsib;
+
+			__be64		bb_blkno;
+			__be64		bb_lsn;
+			uuid_t		bb_uuid;
+			__be64		bb_owner;
+			__le32		bb_crc;
+			__be32		bb_pad; /* padding for alignment */
+		} l;			/* long form pointers */
+	} bb_u;				/* rest */
+};
+
+#define XFS_BTREE_SBLOCK_LEN	16	/* size of a short form block */
+#define XFS_BTREE_LBLOCK_LEN	24	/* size of a long form block */
+
+/* sizes of CRC enabled btree blocks */
+#define XFS_BTREE_SBLOCK_CRC_LEN	(XFS_BTREE_SBLOCK_LEN + 40)
+#define XFS_BTREE_LBLOCK_CRC_LEN	(XFS_BTREE_LBLOCK_LEN + 48)
+
+#define XFS_BTREE_SBLOCK_CRC_OFF \
+	offsetof(struct xfs_btree_block, bb_u.s.bb_crc)
+#define XFS_BTREE_LBLOCK_CRC_OFF \
+	offsetof(struct xfs_btree_block, bb_u.l.bb_crc)
 
 #endif /* __XFS_FORMAT_H__ */

fs/xfs/xfs_fs.h

@@ -233,11 +233,11 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_LOGV2	0x0100	/* log format version 2	*/
 #define XFS_FSOP_GEOM_FLAGS_SECTOR	0x0200	/* sector sizes >1BB	*/
 #define XFS_FSOP_GEOM_FLAGS_ATTR2	0x0400	/* inline attributes rework */
-#define XFS_FSOP_GEOM_FLAGS_PROJID32	0x0800  /* 32-bit project IDs	*/
+#define XFS_FSOP_GEOM_FLAGS_PROJID32	0x0800	/* 32-bit project IDs	*/
 #define XFS_FSOP_GEOM_FLAGS_DIRV2CI	0x1000	/* ASCII only CI names	*/
 #define XFS_FSOP_GEOM_FLAGS_LAZYSB	0x4000	/* lazy superblock counters */
 #define XFS_FSOP_GEOM_FLAGS_V5SB	0x8000	/* version 5 superblock */
-
+#define XFS_FSOP_GEOM_FLAGS_FTYPE	0x10000	/* inode directory types */
 
 /*
  * Minimum and maximum sizes need for growth checks.

fs/xfs/xfs_fsops.c

@@ -17,28 +17,29 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
-#include "xfs_btree.h"
 #include "xfs_error.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_fsops.h"
 #include "xfs_itable.h"
 #include "xfs_trans_space.h"
 #include "xfs_rtalloc.h"
-#include "xfs_filestream.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
+#include "xfs_dinode.h"
+#include "xfs_filestream.h"
 
 /*
  * File system operations
@@ -101,7 +102,9 @@ xfs_fs_geometry(
 			(xfs_sb_version_hasprojid32bit(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_PROJID32 : 0) |
 			(xfs_sb_version_hascrc(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_V5SB : 0);
+				XFS_FSOP_GEOM_FLAGS_V5SB : 0) |
+			(xfs_sb_version_hasftype(&mp->m_sb) ?
+				XFS_FSOP_GEOM_FLAGS_FTYPE : 0);
 		geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ?
 				mp->m_sb.sb_logsectsize : BBSIZE;
 		geo->rtsectsize = mp->m_sb.sb_blocksize;
@@ -153,7 +156,7 @@ xfs_growfs_data_private(
 	xfs_buf_t		*bp;
 	int			bucket;
 	int			dpct;
-	int			error;
+	int			error, saved_error = 0;
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
 	xfs_rfsblock_t		nb, nb_mod;
@@ -496,29 +499,33 @@ xfs_growfs_data_private(
 				error = ENOMEM;
 		}
 
+		/*
+		 * If we get an error reading or writing alternate superblocks,
+		 * continue.  xfs_repair chooses the "best" superblock based
+		 * on most matches; if we break early, we'll leave more
+		 * superblocks un-updated than updated, and xfs_repair may
+		 * pick them over the properly-updated primary.
+		 */
 		if (error) {
 			xfs_warn(mp,
 		"error %d reading secondary superblock for ag %d",
 				error, agno);
-			break;
+			saved_error = error;
+			continue;
 		}
 		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS);
 
-		/*
-		 * If we get an error writing out the alternate superblocks,
-		 * just issue a warning and continue.  The real work is
-		 * already done and committed.
-		 */
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
 		if (error) {
 			xfs_warn(mp,
 		"write error %d updating secondary superblock for ag %d",
 				error, agno);
-			break; /* no point in continuing */
+			saved_error = error;
+			continue;
 		}
 	}
-	return error;
+	return saved_error ? saved_error : error;
 
  error0:
 	xfs_trans_cancel(tp, XFS_TRANS_ABORT);

fs/xfs/xfs_ialloc.c

@@ -17,29 +17,30 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_bmap.h"
 #include "xfs_cksum.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_icreate_item.h"
 #include "xfs_icache.h"
+#include "xfs_dinode.h"
+#include "xfs_trace.h"
 
 
 /*
@@ -1627,8 +1628,9 @@ xfs_read_agi(
 {
 	int			error;
 
-	ASSERT(agno != NULLAGNUMBER);
+	trace_xfs_read_agi(mp, agno);
 
+	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, bpp, &xfs_agi_buf_ops);
@@ -1651,6 +1653,8 @@ xfs_ialloc_read_agi(
 	struct xfs_perag	*pag;	/* per allocation group data */
 	int			error;
 
+	trace_xfs_ialloc_read_agi(mp, agno);
+
 	error = xfs_read_agi(mp, tp, agno, bpp);
 	if (error)
 		return error;

fs/xfs/xfs_ialloc.h

@@ -23,6 +23,7 @@ struct xfs_dinode;
 struct xfs_imap;
 struct xfs_mount;
 struct xfs_trans;
+struct xfs_btree_cur;
 
 /*
  * Allocation parameters for inode allocation.
@@ -42,7 +43,7 @@ struct xfs_trans;
 static inline struct xfs_dinode *
 xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
 {
-	return (xfs_dinode_t *)
+	return (struct xfs_dinode *)
 		(xfs_buf_offset(b, o << (mp)->m_sb.sb_inodelog));
 }
 
@@ -158,6 +159,4 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
 			  xfs_agnumber_t agno, xfs_agblock_t agbno,
 			  xfs_agblock_t length, unsigned int gen);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 #endif	/* __XFS_IALLOC_H__ */

fs/xfs/xfs_ialloc_btree.c

@@ -17,24 +17,23 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_trans.h"
 
 
 STATIC int

fs/xfs/xfs_ialloc_btree.h

@@ -26,55 +26,6 @@ struct xfs_buf;
 struct xfs_btree_cur;
 struct xfs_mount;
 
-/*
- * There is a btree for the inode map per allocation group.
- */
-#define	XFS_IBT_MAGIC		0x49414254	/* 'IABT' */
-#define	XFS_IBT_CRC_MAGIC	0x49414233	/* 'IAB3' */
-
-typedef	__uint64_t	xfs_inofree_t;
-#define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
-#define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
-#define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
-#define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
-
-static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
-{
-	return ((n >= XFS_INODES_PER_CHUNK ? 0 : XFS_INOBT_MASK(n)) - 1) << i;
-}
-
-/*
- * Data record structure
- */
-typedef struct xfs_inobt_rec {
-	__be32		ir_startino;	/* starting inode number */
-	__be32		ir_freecount;	/* count of free inodes (set bits) */
-	__be64		ir_free;	/* free inode mask */
-} xfs_inobt_rec_t;
-
-typedef struct xfs_inobt_rec_incore {
-	xfs_agino_t	ir_startino;	/* starting inode number */
-	__int32_t	ir_freecount;	/* count of free inodes (set bits) */
-	xfs_inofree_t	ir_free;	/* free inode mask */
-} xfs_inobt_rec_incore_t;
-
-
-/*
- * Key structure
- */
-typedef struct xfs_inobt_key {
-	__be32		ir_startino;	/* starting inode number */
-} xfs_inobt_key_t;
-
-/* btree pointer type */
-typedef __be32 xfs_inobt_ptr_t;
-
-/*
- * block numbers in the AG.
- */
-#define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
-#define	XFS_PREALLOC_BLOCKS(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
-
 /*
  * Btree block header size depends on a superblock flag.
  */
@@ -110,6 +61,4 @@ extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_inobt_buf_ops;
-
 #endif	/* __XFS_IALLOC_BTREE_H__ */

fs/xfs/xfs_icache.c

@@ -18,24 +18,19 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_log_priv.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_dinode.h"
 #include "xfs_error.h"
-#include "xfs_filestream.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
 #include "xfs_inode_item.h"
 #include "xfs_quota.h"
 #include "xfs_trace.h"
-#include "xfs_fsops.h"
 #include "xfs_icache.h"
 #include "xfs_bmap_util.h"
 
@@ -500,11 +495,6 @@ xfs_inode_ag_walk_grab(
 	if (!igrab(inode))
 		return ENOENT;
 
-	if (is_bad_inode(inode)) {
-		IRELE(ip);
-		return ENOENT;
-	}
-
 	/* inode is valid */
 	return 0;
 
@@ -918,8 +908,6 @@ restart:
 		xfs_iflock(ip);
 	}
 
-	if (is_bad_inode(VFS_I(ip)))
-		goto reclaim;
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
 		xfs_iflush_abort(ip, false);

fs/xfs/xfs_icreate_item.c

@@ -17,13 +17,14 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_trans.h"
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
 #include "xfs_icreate_item.h"

fs/xfs/xfs_inode.c

@@ -19,39 +19,38 @@
 
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_trans_space.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
 #include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
 #include "xfs_attr_sf.h"
 #include "xfs_attr.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
+#include "xfs_trans_space.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_inode_item.h"
-#include "xfs_btree.h"
-#include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
+#include "xfs_dinode.h"
 #include "xfs_filestream.h"
 #include "xfs_cksum.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
+#include "xfs_trans_priv.h"
+#include "xfs_log.h"
+#include "xfs_bmap_btree.h"
 
 kmem_zone_t *xfs_inode_zone;
 
@@ -1662,6 +1661,126 @@ xfs_release(
 	return 0;
 }
 
+/*
+ * xfs_inactive_truncate
+ *
+ * Called to perform a truncate when an inode becomes unlinked.
+ */
+STATIC int
+xfs_inactive_truncate(
+	struct xfs_inode *ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+	if (error) {
+		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	/*
+	 * Log the inode size first to prevent stale data exposure in the event
+	 * of a system crash before the truncate completes. See the related
+	 * comment in xfs_setattr_size() for details.
+	 */
+	ip->i_d.di_size = 0;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
+	if (error)
+		goto error_trans_cancel;
+
+	ASSERT(ip->i_d.di_nextents == 0);
+
+	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+	if (error)
+		goto error_unlock;
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return 0;
+
+error_trans_cancel:
+	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+error_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
+/*
+ * xfs_inactive_ifree()
+ *
+ * Perform the inode free when an inode is unlinked.
+ */
+STATIC int
+xfs_inactive_ifree(
+	struct xfs_inode *ip)
+{
+	xfs_bmap_free_t		free_list;
+	xfs_fsblock_t		first_block;
+	int			committed;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
+	if (error) {
+		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	xfs_bmap_init(&free_list, &first_block);
+	error = xfs_ifree(tp, ip, &free_list);
+	if (error) {
+		/*
+		 * If we fail to free the inode, shut down.  The cancel
+		 * might do that, we need to make sure.  Otherwise the
+		 * inode might be lost for a long time or forever.
+		 */
+		if (!XFS_FORCED_SHUTDOWN(mp)) {
+			xfs_notice(mp, "%s: xfs_ifree returned error %d",
+				__func__, error);
+			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+		}
+		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		return error;
+	}
+
+	/*
+	 * Credit the quota account(s). The inode is gone.
+	 */
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);
+
+	/*
+	 * Just ignore errors at this point.  There is nothing we can
+	 * do except to try to keep going. Make sure it's not a silent
+	 * error.
+	 */
+	error = xfs_bmap_finish(&tp,  &free_list, &committed);
+	if (error)
+		xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
+			__func__, error);
+	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+	if (error)
+		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
+			__func__, error);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return 0;
+}
+
 /*
  * xfs_inactive
  *
@@ -1670,16 +1789,11 @@ xfs_release(
  * now be truncated.  Also, we clear all of the read-ahead state
  * kept for the inode here since the file is now closed.
  */
-int
+void
 xfs_inactive(
 	xfs_inode_t	*ip)
 {
-	xfs_bmap_free_t		free_list;
-	xfs_fsblock_t		first_block;
-	int			committed;
-	struct xfs_trans	*tp;
 	struct xfs_mount	*mp;
-	struct xfs_trans_res	*resp;
 	int			error;
 	int			truncate = 0;
 
@@ -1687,19 +1801,17 @@ xfs_inactive(
 	 * If the inode is already free, then there can be nothing
 	 * to clean up here.
 	 */
-	if (ip->i_d.di_mode == 0 || is_bad_inode(VFS_I(ip))) {
+	if (ip->i_d.di_mode == 0) {
 		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
-		return VN_INACTIVE_CACHE;
+		return;
 	}
 
 	mp = ip->i_mount;
 
-	error = 0;
-
 	/* If this is a read-only mount, don't do this (would generate I/O) */
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		goto out;
+		return;
 
 	if (ip->i_d.di_nlink != 0) {
 		/*
@@ -1707,12 +1819,10 @@ xfs_inactive(
 		 * cache. Post-eof blocks must be freed, lest we end up with
 		 * broken free space accounting.
 		 */
-		if (xfs_can_free_eofblocks(ip, true)) {
-			error = xfs_free_eofblocks(mp, ip, false);
-			if (error)
-				return VN_INACTIVE_CACHE;
-		}
-		goto out;
+		if (xfs_can_free_eofblocks(ip, true))
+			xfs_free_eofblocks(mp, ip, false);
+
+		return;
 	}
 
 	if (S_ISREG(ip->i_d.di_mode) &&
@@ -1722,36 +1832,14 @@ xfs_inactive(
 
 	error = xfs_qm_dqattach(ip, 0);
 	if (error)
-		return VN_INACTIVE_CACHE;
+		return;
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	resp = (truncate || S_ISLNK(ip->i_d.di_mode)) ?
-		&M_RES(mp)->tr_itruncate : &M_RES(mp)->tr_ifree;
-
-	error = xfs_trans_reserve(tp, resp, 0, 0);
-	if (error) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
-		xfs_trans_cancel(tp, 0);
-		return VN_INACTIVE_CACHE;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-
-	if (S_ISLNK(ip->i_d.di_mode)) {
-		error = xfs_inactive_symlink(ip, &tp);
-		if (error)
-			goto out_cancel;
-	} else if (truncate) {
-		ip->i_d.di_size = 0;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
-		if (error)
-			goto out_cancel;
-
-		ASSERT(ip->i_d.di_nextents == 0);
-	}
+	if (S_ISLNK(ip->i_d.di_mode))
+		error = xfs_inactive_symlink(ip);
+	else if (truncate)
+		error = xfs_inactive_truncate(ip);
+	if (error)
+		return;
 
 	/*
 	 * If there are attributes associated with the file then blow them away
@@ -1762,25 +1850,9 @@ xfs_inactive(
 	if (ip->i_d.di_anextents > 0) {
 		ASSERT(ip->i_d.di_forkoff != 0);
 
-		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-		if (error)
-			goto out_unlock;
-
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		error = xfs_attr_inactive(ip);
 		if (error)
-			goto out;
-
-		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			goto out;
-		}
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_trans_ijoin(tp, ip, 0);
+			return;
 	}
 
 	if (ip->i_afp)
@@ -1791,52 +1863,14 @@ xfs_inactive(
 	/*
 	 * Free the inode.
 	 */
-	xfs_bmap_init(&free_list, &first_block);
-	error = xfs_ifree(tp, ip, &free_list);
-	if (error) {
-		/*
-		 * If we fail to free the inode, shut down.  The cancel
-		 * might do that, we need to make sure.  Otherwise the
-		 * inode might be lost for a long time or forever.
-		 */
-		if (!XFS_FORCED_SHUTDOWN(mp)) {
-			xfs_notice(mp, "%s: xfs_ifree returned error %d",
-				__func__, error);
-			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
-		}
-		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-	} else {
-		/*
-		 * Credit the quota account(s). The inode is gone.
-		 */
-		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);
-
-		/*
-		 * Just ignore errors at this point.  There is nothing we can
-		 * do except to try to keep going. Make sure it's not a silent
-		 * error.
-		 */
-		error = xfs_bmap_finish(&tp,  &free_list, &committed);
-		if (error)
-			xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
-				__func__, error);
-		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-		if (error)
-			xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
-				__func__, error);
-	}
+	error = xfs_inactive_ifree(ip);
+	if (error)
+		return;
 
 	/*
 	 * Release the dquots held by inode, if any.
 	 */
 	xfs_qm_dqdetach(ip);
-out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-out:
-	return VN_INACTIVE_CACHE;
-out_cancel:
-	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-	goto out_unlock;
 }
 
 /*
@@ -2370,6 +2404,33 @@ xfs_iunpin_wait(
 		__xfs_iunpin_wait(ip);
 }
 
+/*
+ * Removing an inode from the namespace involves removing the directory entry
+ * and dropping the link count on the inode. Removing the directory entry can
+ * result in locking an AGF (directory blocks were freed) and removing a link
+ * count can result in placing the inode on an unlinked list which results in
+ * locking an AGI.
+ *
+ * The big problem here is that we have an ordering constraint on AGF and AGI
+ * locking - inode allocation locks the AGI, then can allocate a new extent for
+ * new inodes, locking the AGF after the AGI. Similarly, freeing the inode
+ * removes the inode from the unlinked list, requiring that we lock the AGI
+ * first, and then freeing the inode can result in an inode chunk being freed
+ * and hence freeing disk space requiring that we lock an AGF.
+ *
+ * Hence the ordering that is imposed by other parts of the code is AGI before
+ * AGF. This means we cannot remove the directory entry before we drop the inode
+ * reference count and put it on the unlinked list as this results in a lock
+ * order of AGF then AGI, and this can deadlock against inode allocation and
+ * freeing. Therefore we must drop the link counts before we remove the
+ * directory entry.
+ *
+ * This is still safe from a transactional point of view - it is not until we
+ * get to xfs_bmap_finish() that we have the possibility of multiple
+ * transactions in this operation. Hence as long as we remove the directory
+ * entry and drop the link count in the first transaction of the remove
+ * operation, there are no transactional constraints on the ordering here.
+ */
 int
 xfs_remove(
 	xfs_inode_t             *dp,
@@ -2439,6 +2500,7 @@ xfs_remove(
 	/*
 	 * If we're removing a directory perform some additional validation.
 	 */
+	cancel_flags |= XFS_TRANS_ABORT;
 	if (is_dir) {
 		ASSERT(ip->i_d.di_nlink >= 2);
 		if (ip->i_d.di_nlink != 2) {
@@ -2449,31 +2511,16 @@ xfs_remove(
 			error = XFS_ERROR(ENOTEMPTY);
 			goto out_trans_cancel;
 		}
-	}
 
-	xfs_bmap_init(&free_list, &first_block);
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
-					&first_block, &free_list, resblks);
-	if (error) {
-		ASSERT(error != ENOENT);
-		goto out_bmap_cancel;
-	}
-	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-
-	if (is_dir) {
-		/*
-		 * Drop the link from ip's "..".
-		 */
+		/* Drop the link from ip's "..".  */
 		error = xfs_droplink(tp, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		/*
-		 * Drop the "." link from ip to self.
-		 */
+		/* Drop the "." link from ip to self.  */
 		error = xfs_droplink(tp, ip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	} else {
 		/*
 		 * When removing a non-directory we need to log the parent
@@ -2482,20 +2529,24 @@ xfs_remove(
 		 */
 		xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 	}
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
-	/*
-	 * Drop the link from dp to ip.
-	 */
+	/* Drop the link from dp to ip. */
 	error = xfs_droplink(tp, ip);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
-	/*
-	 * Determine if this is the last link while
-	 * we are in the transaction.
-	 */
+	/* Determine if this is the last link while the inode is locked */
 	link_zero = (ip->i_d.di_nlink == 0);
 
+	xfs_bmap_init(&free_list, &first_block);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
+					&first_block, &free_list, resblks);
+	if (error) {
+		ASSERT(error != ENOENT);
+		goto out_bmap_cancel;
+	}
+
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * remove transaction goes to disk before returning to
@@ -2525,7 +2576,6 @@ xfs_remove(
 
  out_bmap_cancel:
 	xfs_bmap_cancel(&free_list);
-	cancel_flags |= XFS_TRANS_ABORT;
  out_trans_cancel:
 	xfs_trans_cancel(tp, cancel_flags);
  std_return:

fs/xfs/xfs_inode.h

@@ -24,7 +24,6 @@
 /*
  * Kernel only inode definitions
  */
-
 struct xfs_dinode;
 struct xfs_inode;
 struct xfs_buf;
@@ -50,6 +49,9 @@ typedef struct xfs_inode {
 	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
 	xfs_ifork_t		i_df;		/* data fork */
 
+	/* operations vectors */
+	const struct xfs_dir_ops *d_ops;		/* directory ops vector */
+
 	/* Transaction and locking information. */
 	struct xfs_inode_log_item *i_itemp;	/* logging information */
 	mrlock_t		i_lock;		/* inode lock */
@@ -316,7 +318,7 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
 
 
 int		xfs_release(struct xfs_inode *ip);
-int		xfs_inactive(struct xfs_inode *ip);
+void		xfs_inactive(struct xfs_inode *ip);
 int		xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
 			   struct xfs_inode **ipp, struct xfs_name *ci_name);
 int		xfs_create(struct xfs_inode *dp, struct xfs_name *name,

fs/xfs/xfs_inode_buf.c

@@ -17,20 +17,20 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_error.h"
 #include "xfs_cksum.h"
 #include "xfs_icache.h"
+#include "xfs_trans.h"
 #include "xfs_ialloc.h"
+#include "xfs_dinode.h"
 
 /*
  * Check that none of the inode's in the buffer have a next

fs/xfs/xfs_inode_buf.h

@@ -47,7 +47,4 @@ void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
-extern const struct xfs_buf_ops xfs_inode_buf_ops;
-extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
-
 #endif	/* __XFS_INODE_BUF_H__ */

fs/xfs/xfs_inode_fork.c

@@ -20,31 +20,21 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_buf_item.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
-#include "xfs_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_ialloc.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
-#include "xfs_quota.h"
-#include "xfs_filestream.h"
-#include "xfs_cksum.h"
 #include "xfs_trace.h"
-#include "xfs_icache.h"
+#include "xfs_attr_sf.h"
+#include "xfs_dinode.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -1031,15 +1021,14 @@ xfs_iext_add(
 		 * the next index needed in the indirection array.
 		 */
 		else {
-			int	count = ext_diff;
+			uint	count = ext_diff;
 
 			while (count) {
 				erp = xfs_iext_irec_new(ifp, erp_idx);
-				erp->er_extcount = count;
-				count -= MIN(count, (int)XFS_LINEAR_EXTS);
-				if (count) {
+				erp->er_extcount = min(count, XFS_LINEAR_EXTS);
+				count -= erp->er_extcount;
+				if (count)
 					erp_idx++;
-				}
 			}
 		}
 	}
@@ -1359,7 +1348,7 @@ xfs_iext_remove_indirect(
 void
 xfs_iext_realloc_direct(
 	xfs_ifork_t	*ifp,		/* inode fork pointer */
-	int		new_size)	/* new size of extents */
+	int		new_size)	/* new size of extents after adding */
 {
 	int		rnew_size;	/* real new size of extents */
 
@@ -1397,13 +1386,8 @@ xfs_iext_realloc_direct(
 				rnew_size - ifp->if_real_bytes);
 		}
 	}
-	/*
-	 * Switch from the inline extent buffer to a direct
-	 * extent list. Be sure to include the inline extent
-	 * bytes in new_size.
-	 */
+	/* Switch from the inline extent buffer to a direct extent list */
 	else {
-		new_size += ifp->if_bytes;
 		if (!is_power_of_2(new_size)) {
 			rnew_size = roundup_pow_of_two(new_size);
 		}

fs/xfs/xfs_inode_fork.h

@@ -19,6 +19,7 @@
 #define	__XFS_INODE_FORK_H__
 
 struct xfs_inode_log_item;
+struct xfs_dinode;
 
 /*
  * The following xfs_ext_irec_t struct introduces a second (top) level

fs/xfs/xfs_inode_item.c

@@ -17,19 +17,19 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_trans_priv.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_trans_priv.h"
+#include "xfs_dinode.h"
 
 
 kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */

fs/xfs/xfs_ioctl.c

@@ -17,32 +17,31 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_ioctl.h"
+#include "xfs_alloc.h"
 #include "xfs_rtalloc.h"
 #include "xfs_itable.h"
 #include "xfs_error.h"
 #include "xfs_attr.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_buf_item.h"
 #include "xfs_fsops.h"
 #include "xfs_discard.h"
 #include "xfs_quota.h"
-#include "xfs_inode_item.h"
 #include "xfs_export.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
+#include "xfs_dinode.h"
+#include "xfs_trans.h"
 
 #include <linux/capability.h>
 #include <linux/dcache.h>
@@ -641,7 +640,11 @@ xfs_ioc_space(
 	unsigned int		cmd,
 	xfs_flock64_t		*bf)
 {
-	int			attr_flags = 0;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	struct iattr		iattr;
+	bool			setprealloc = false;
+	bool			clrprealloc = false;
 	int			error;
 
 	/*
@@ -661,19 +664,128 @@ xfs_ioc_space(
 	if (!S_ISREG(inode->i_mode))
 		return -XFS_ERROR(EINVAL);
 
-	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-		attr_flags |= XFS_ATTR_NONBLOCK;
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
 
-	if (filp->f_flags & O_DSYNC)
-		attr_flags |= XFS_ATTR_SYNC;
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	switch (bf->l_whence) {
+	case 0: /*SEEK_SET*/
+		break;
+	case 1: /*SEEK_CUR*/
+		bf->l_start += filp->f_pos;
+		break;
+	case 2: /*SEEK_END*/
+		bf->l_start += XFS_ISIZE(ip);
+		break;
+	default:
+		error = XFS_ERROR(EINVAL);
+		goto out_unlock;
+	}
 
-	if (ioflags & IO_INVIS)
-		attr_flags |= XFS_ATTR_DMI;
+	/*
+	 * length of <= 0 for resv/unresv/zero is invalid.  length for
+	 * alloc/free is ignored completely and we have no idea what userspace
+	 * might have set it to, so set it to zero to allow range
+	 * checks to pass.
+	 */
+	switch (cmd) {
+	case XFS_IOC_ZERO_RANGE:
+	case XFS_IOC_RESVSP:
+	case XFS_IOC_RESVSP64:
+	case XFS_IOC_UNRESVSP:
+	case XFS_IOC_UNRESVSP64:
+		if (bf->l_len <= 0) {
+			error = XFS_ERROR(EINVAL);
+			goto out_unlock;
+		}
+		break;
+	default:
+		bf->l_len = 0;
+		break;
+	}
+
+	if (bf->l_start < 0 ||
+	    bf->l_start > mp->m_super->s_maxbytes ||
+	    bf->l_start + bf->l_len < 0 ||
+	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes) {
+		error = XFS_ERROR(EINVAL);
+		goto out_unlock;
+	}
+
+	switch (cmd) {
+	case XFS_IOC_ZERO_RANGE:
+		error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
+		if (!error)
+			setprealloc = true;
+		break;
+	case XFS_IOC_RESVSP:
+	case XFS_IOC_RESVSP64:
+		error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
+						XFS_BMAPI_PREALLOC);
+		if (!error)
+			setprealloc = true;
+		break;
+	case XFS_IOC_UNRESVSP:
+	case XFS_IOC_UNRESVSP64:
+		error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
+		break;
+	case XFS_IOC_ALLOCSP:
+	case XFS_IOC_ALLOCSP64:
+	case XFS_IOC_FREESP:
+	case XFS_IOC_FREESP64:
+		if (bf->l_start > XFS_ISIZE(ip)) {
+			error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
+					bf->l_start - XFS_ISIZE(ip), 0);
+			if (error)
+				goto out_unlock;
+		}
+
+		iattr.ia_valid = ATTR_SIZE;
+		iattr.ia_size = bf->l_start;
+
+		error = xfs_setattr_size(ip, &iattr);
+		if (!error)
+			clrprealloc = true;
+		break;
+	default:
+		ASSERT(0);
+		error = XFS_ERROR(EINVAL);
+	}
 
-	error = mnt_want_write_file(filp);
 	if (error)
-		return error;
-	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
+		goto out_unlock;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		goto out_unlock;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	if (!(ioflags & IO_INVIS)) {
+		ip->i_d.di_mode &= ~S_ISUID;
+		if (ip->i_d.di_mode & S_IXGRP)
+			ip->i_d.di_mode &= ~S_ISGID;
+		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	}
+
+	if (setprealloc)
+		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
+	else if (clrprealloc)
+		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	if (filp->f_flags & O_DSYNC)
+		xfs_trans_set_sync(tp);
+	error = xfs_trans_commit(tp, 0);
+
+out_unlock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	mnt_drop_write_file(filp);
 	return -error;
 }

fs/xfs/xfs_ioctl32.c

@@ -22,14 +22,13 @@
 #include <asm/uaccess.h>
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_vnode.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_itable.h"
 #include "xfs_error.h"

fs/xfs/xfs_iomap.c

@@ -17,34 +17,28 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_inode_item.h"
 #include "xfs_btree.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_rtalloc.h"
 #include "xfs_error.h"
-#include "xfs_itable.h"
-#include "xfs_attr.h"
-#include "xfs_buf_item.h"
+#include "xfs_trans.h"
 #include "xfs_trans_space.h"
 #include "xfs_iomap.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_quota.h"
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
+#include "xfs_dinode.h"
 
 
 #define XFS_WRITEIO_ALIGN(mp,off)	(((off) >> mp->m_writeio_log) \
@@ -110,7 +104,7 @@ xfs_alert_fsblock_zero(
 	xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
 			"Access to block zero in inode %llu "
 			"start_block: %llx start_off: %llx "
-			"blkcnt: %llx extent-state: %x\n",
+			"blkcnt: %llx extent-state: %x",
 		(unsigned long long)ip->i_ino,
 		(unsigned long long)imap->br_startblock,
 		(unsigned long long)imap->br_startoff,
@@ -655,7 +649,6 @@ int
 xfs_iomap_write_allocate(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
-	size_t		count,
 	xfs_bmbt_irec_t *imap)
 {
 	xfs_mount_t	*mp = ip->i_mount;

fs/xfs/xfs_iomap.h

@@ -21,12 +21,12 @@
 struct xfs_inode;
 struct xfs_bmbt_irec;
 
-extern int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
+int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *, int);
-extern int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t,
+int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *);
-extern int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t, size_t,
+int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t,
 			struct xfs_bmbt_irec *);
-extern int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t);
 
 #endif /* __XFS_IOMAP_H__*/

fs/xfs/xfs_iops.c

@@ -17,32 +17,28 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_acl.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_rtalloc.h"
+#include "xfs_acl.h"
+#include "xfs_quota.h"
 #include "xfs_error.h"
-#include "xfs_itable.h"
 #include "xfs_attr.h"
-#include "xfs_buf_item.h"
-#include "xfs_inode_item.h"
+#include "xfs_trans.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2_priv.h"
+#include "xfs_dinode.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -709,8 +705,7 @@ out_dqrele:
 int
 xfs_setattr_size(
 	struct xfs_inode	*ip,
-	struct iattr		*iattr,
-	int			flags)
+	struct iattr		*iattr)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
@@ -733,15 +728,11 @@ xfs_setattr_size(
 	if (error)
 		return XFS_ERROR(error);
 
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(S_ISREG(ip->i_d.di_mode));
 	ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
 			ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
-	if (!(flags & XFS_ATTR_NOLOCK)) {
-		lock_flags |= XFS_IOLOCK_EXCL;
-		xfs_ilock(ip, lock_flags);
-	}
-
 	oldsize = inode->i_size;
 	newsize = iattr->ia_size;
 
@@ -750,12 +741,11 @@ xfs_setattr_size(
 	 */
 	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
 		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
-			goto out_unlock;
+			return 0;
 
 		/*
 		 * Use the regular setattr path to update the timestamps.
 		 */
-		xfs_iunlock(ip, lock_flags);
 		iattr->ia_valid &= ~ATTR_SIZE;
 		return xfs_setattr_nonsize(ip, iattr, 0);
 	}
@@ -765,7 +755,7 @@ xfs_setattr_size(
 	 */
 	error = xfs_qm_dqattach(ip, 0);
 	if (error)
-		goto out_unlock;
+		return error;
 
 	/*
 	 * Now we can make the changes.  Before we join the inode to the
@@ -783,7 +773,7 @@ xfs_setattr_size(
 		 */
 		error = xfs_zero_eof(ip, newsize, oldsize);
 		if (error)
-			goto out_unlock;
+			return error;
 	}
 
 	/*
@@ -802,7 +792,7 @@ xfs_setattr_size(
 		error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 						      ip->i_d.di_size, newsize);
 		if (error)
-			goto out_unlock;
+			return error;
 	}
 
 	/*
@@ -812,7 +802,7 @@ xfs_setattr_size(
 
 	error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
 	if (error)
-		goto out_unlock;
+		return error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
@@ -916,12 +906,21 @@ out_trans_cancel:
 
 STATIC int
 xfs_vn_setattr(
-	struct dentry	*dentry,
-	struct iattr	*iattr)
+	struct dentry		*dentry,
+	struct iattr		*iattr)
 {
-	if (iattr->ia_valid & ATTR_SIZE)
-		return -xfs_setattr_size(XFS_I(dentry->d_inode), iattr, 0);
-	return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0);
+	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
+	int			error;
+
+	if (iattr->ia_valid & ATTR_SIZE) {
+		xfs_ilock(ip, XFS_IOLOCK_EXCL);
+		error = xfs_setattr_size(ip, iattr);
+		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	} else {
+		error = xfs_setattr_nonsize(ip, iattr, 0);
+	}
+
+	return -error;
 }
 
 STATIC int
@@ -1169,6 +1168,7 @@ xfs_setup_inode(
 	struct xfs_inode	*ip)
 {
 	struct inode		*inode = &ip->i_vnode;
+	gfp_t			gfp_mask;
 
 	inode->i_ino = ip->i_ino;
 	inode->i_state = I_NEW;
@@ -1204,6 +1204,7 @@ xfs_setup_inode(
 	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
 	xfs_diflags_to_iflags(inode, ip);
 
+	ip->d_ops = ip->i_mount->m_nondir_inode_ops;
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &xfs_inode_operations;
@@ -1216,6 +1217,7 @@ xfs_setup_inode(
 		else
 			inode->i_op = &xfs_dir_inode_operations;
 		inode->i_fop = &xfs_dir_file_operations;
+		ip->d_ops = ip->i_mount->m_dir_inode_ops;
 		break;
 	case S_IFLNK:
 		inode->i_op = &xfs_symlink_inode_operations;
@@ -1228,6 +1230,14 @@ xfs_setup_inode(
 		break;
 	}
 
+	/*
+	 * Ensure all page cache allocations are done from GFP_NOFS context to
+	 * prevent direct reclaim recursion back into the filesystem and blowing
+	 * stacks or deadlocking.
+	 */
+	gfp_mask = mapping_gfp_mask(inode->i_mapping);
+	mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
+
 	/*
 	 * If there is no attribute fork no ACL can exist on this inode,
 	 * and it can't have any file capabilities attached to it either.

fs/xfs/xfs_iops.h

@@ -30,14 +30,10 @@ extern void xfs_setup_inode(struct xfs_inode *);
 /*
  * Internal setattr interfaces.
  */
-#define	XFS_ATTR_DMI		0x01	/* invocation from a DMI function */
-#define	XFS_ATTR_NONBLOCK	0x02	/* return EAGAIN if op would block */
-#define XFS_ATTR_NOLOCK		0x04	/* Don't grab any conflicting locks */
-#define XFS_ATTR_NOACL		0x08	/* Don't call xfs_acl_chmod */
-#define XFS_ATTR_SYNC		0x10	/* synchronous operation required */
+#define XFS_ATTR_NOACL		0x01	/* Don't call xfs_acl_chmod */
 
 extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap,
 			       int flags);
-extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap, int flags);
+extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap);
 
 #endif /* __XFS_IOPS_H__ */

fs/xfs/xfs_itable.c

@@ -17,24 +17,23 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_itable.h"
 #include "xfs_error.h"
-#include "xfs_btree.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_dinode.h"
 
 STATIC int
 xfs_internal_inum(

fs/xfs/xfs_log.c

@@ -17,21 +17,19 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_error.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
+#include "xfs_log.h"
 #include "xfs_log_priv.h"
-#include "xfs_buf_item.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
 #include "xfs_log_recover.h"
-#include "xfs_trans_priv.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_trace.h"
 #include "xfs_fsops.h"
@@ -1000,27 +998,34 @@ xfs_log_space_wake(
 }
 
 /*
- * Determine if we have a transaction that has gone to disk
- * that needs to be covered. To begin the transition to the idle state
- * firstly the log needs to be idle (no AIL and nothing in the iclogs).
- * If we are then in a state where covering is needed, the caller is informed
- * that dummy transactions are required to move the log into the idle state.
+ * Determine if we have a transaction that has gone to disk that needs to be
+ * covered. To begin the transition to the idle state firstly the log needs to
+ * be idle. That means the CIL, the AIL and the iclogs needs to be empty before
+ * we start attempting to cover the log.
  *
- * Because this is called as part of the sync process, we should also indicate
- * that dummy transactions should be issued in anything but the covered or
- * idle states. This ensures that the log tail is accurately reflected in
- * the log at the end of the sync, hence if a crash occurrs avoids replay
- * of transactions where the metadata is already on disk.
+ * Only if we are then in a state where covering is needed, the caller is
+ * informed that dummy transactions are required to move the log into the idle
+ * state.
+ *
+ * If there are any items in the AIl or CIL, then we do not want to attempt to
+ * cover the log as we may be in a situation where there isn't log space
+ * available to run a dummy transaction and this can lead to deadlocks when the
+ * tail of the log is pinned by an item that is modified in the CIL.  Hence
+ * there's no point in running a dummy transaction at this point because we
+ * can't start trying to idle the log until both the CIL and AIL are empty.
  */
 int
 xfs_log_need_covered(xfs_mount_t *mp)
 {
-	int		needed = 0;
 	struct xlog	*log = mp->m_log;
+	int		needed = 0;
 
 	if (!xfs_fs_writable(mp))
 		return 0;
 
+	if (!xlog_cil_empty(log))
+		return 0;
+
 	spin_lock(&log->l_icloglock);
 	switch (log->l_covered_state) {
 	case XLOG_STATE_COVER_DONE:
@@ -1029,14 +1034,17 @@ xfs_log_need_covered(xfs_mount_t *mp)
 		break;
 	case XLOG_STATE_COVER_NEED:
 	case XLOG_STATE_COVER_NEED2:
-		if (!xfs_ail_min_lsn(log->l_ailp) &&
-		    xlog_iclogs_empty(log)) {
-			if (log->l_covered_state == XLOG_STATE_COVER_NEED)
-				log->l_covered_state = XLOG_STATE_COVER_DONE;
-			else
-				log->l_covered_state = XLOG_STATE_COVER_DONE2;
-		}
-		/* FALLTHRU */
+		if (xfs_ail_min_lsn(log->l_ailp))
+			break;
+		if (!xlog_iclogs_empty(log))
+			break;
+
+		needed = 1;
+		if (log->l_covered_state == XLOG_STATE_COVER_NEED)
+			log->l_covered_state = XLOG_STATE_COVER_DONE;
+		else
+			log->l_covered_state = XLOG_STATE_COVER_DONE2;
+		break;
 	default:
 		needed = 1;
 		break;
@@ -1068,6 +1076,7 @@ xlog_assign_tail_lsn_locked(
 		tail_lsn = lip->li_lsn;
 	else
 		tail_lsn = atomic64_read(&log->l_last_sync_lsn);
+	trace_xfs_log_assign_tail_lsn(log, tail_lsn);
 	atomic64_set(&log->l_tail_lsn, tail_lsn);
 	return tail_lsn;
 }
@@ -1979,7 +1988,7 @@ xlog_print_tic_res(
 
 	for (i = 0; i < ticket->t_res_num; i++) {
 		uint r_type = ticket->t_res_arr[i].r_type;
-		xfs_warn(mp, "region[%u]: %s - %u bytes\n", i,
+		xfs_warn(mp, "region[%u]: %s - %u bytes", i,
 			    ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
 			    "bad-rtype" : res_type_str[r_type-1]),
 			    ticket->t_res_arr[i].r_len);
@@ -3702,11 +3711,9 @@ xlog_verify_iclog(
 	/* check validity of iclog pointers */
 	spin_lock(&log->l_icloglock);
 	icptr = log->l_iclog;
-	for (i=0; i < log->l_iclog_bufs; i++) {
-		if (icptr == NULL)
-			xfs_emerg(log->l_mp, "%s: invalid ptr", __func__);
-		icptr = icptr->ic_next;
-	}
+	for (i = 0; i < log->l_iclog_bufs; i++, icptr = icptr->ic_next)
+		ASSERT(icptr);
+
 	if (icptr != log->l_iclog)
 		xfs_emerg(log->l_mp, "%s: corrupt iclog ring", __func__);
 	spin_unlock(&log->l_icloglock);

fs/xfs/xfs_log.h

@@ -18,8 +18,6 @@
 #ifndef	__XFS_LOG_H__
 #define __XFS_LOG_H__
 
-#include "xfs_log_format.h"
-
 struct xfs_log_vec {
 	struct xfs_log_vec	*lv_next;	/* next lv in build list */
 	int			lv_niovecs;	/* number of iovecs in lv */
@@ -82,11 +80,7 @@ struct xlog_ticket;
 struct xfs_log_item;
 struct xfs_item_ops;
 struct xfs_trans;
-
-void	xfs_log_item_init(struct xfs_mount	*mp,
-			struct xfs_log_item	*item,
-			int			type,
-			const struct xfs_item_ops *ops);
+struct xfs_log_callback;
 
 xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
 		       struct xlog_ticket *ticket,
@@ -114,7 +108,7 @@ xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp);
 void	  xfs_log_space_wake(struct xfs_mount *mp);
 int	  xfs_log_notify(struct xfs_mount	*mp,
 			 struct xlog_in_core	*iclog,
-			 xfs_log_callback_t	*callback_entry);
+			 struct xfs_log_callback *callback_entry);
 int	  xfs_log_release_iclog(struct xfs_mount *mp,
 			 struct xlog_in_core	 *iclog);
 int	  xfs_log_reserve(struct xfs_mount *mp,

fs/xfs/xfs_log_cil.c

@@ -17,11 +17,9 @@
 
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
-#include "xfs_log_priv.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
@@ -29,6 +27,10 @@
 #include "xfs_alloc.h"
 #include "xfs_extent_busy.h"
 #include "xfs_discard.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
+#include "xfs_log.h"
+#include "xfs_log_priv.h"
 
 /*
  * Allocate a new ticket. Failing to get a new ticket makes it really hard to
@@ -711,6 +713,20 @@ xlog_cil_push_foreground(
 	xlog_cil_push(log);
 }
 
+bool
+xlog_cil_empty(
+	struct xlog	*log)
+{
+	struct xfs_cil	*cil = log->l_cilp;
+	bool		empty = false;
+
+	spin_lock(&cil->xc_push_lock);
+	if (list_empty(&cil->xc_cil))
+		empty = true;
+	spin_unlock(&cil->xc_push_lock);
+	return empty;
+}
+
 /*
  * Commit a transaction with the given vector to the Committed Item List.
  *

fs/xfs/xfs_log_format.h

@@ -233,178 +233,6 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_QUOTAOFF,	"XFS_LI_QUOTAOFF" }, \
 	{ XFS_LI_ICREATE,	"XFS_LI_ICREATE" }
 
-/*
- * Transaction types.  Used to distinguish types of buffers.
- */
-#define XFS_TRANS_SETATTR_NOT_SIZE	1
-#define XFS_TRANS_SETATTR_SIZE		2
-#define XFS_TRANS_INACTIVE		3
-#define XFS_TRANS_CREATE		4
-#define XFS_TRANS_CREATE_TRUNC		5
-#define XFS_TRANS_TRUNCATE_FILE		6
-#define XFS_TRANS_REMOVE		7
-#define XFS_TRANS_LINK			8
-#define XFS_TRANS_RENAME		9
-#define XFS_TRANS_MKDIR			10
-#define XFS_TRANS_RMDIR			11
-#define XFS_TRANS_SYMLINK		12
-#define XFS_TRANS_SET_DMATTRS		13
-#define XFS_TRANS_GROWFS		14
-#define XFS_TRANS_STRAT_WRITE		15
-#define XFS_TRANS_DIOSTRAT		16
-/* 17 was XFS_TRANS_WRITE_SYNC */
-#define	XFS_TRANS_WRITEID		18
-#define	XFS_TRANS_ADDAFORK		19
-#define	XFS_TRANS_ATTRINVAL		20
-#define	XFS_TRANS_ATRUNCATE		21
-#define	XFS_TRANS_ATTR_SET		22
-#define	XFS_TRANS_ATTR_RM		23
-#define	XFS_TRANS_ATTR_FLAG		24
-#define	XFS_TRANS_CLEAR_AGI_BUCKET	25
-#define XFS_TRANS_QM_SBCHANGE		26
-/*
- * Dummy entries since we use the transaction type to index into the
- * trans_type[] in xlog_recover_print_trans_head()
- */
-#define XFS_TRANS_DUMMY1		27
-#define XFS_TRANS_DUMMY2		28
-#define XFS_TRANS_QM_QUOTAOFF		29
-#define XFS_TRANS_QM_DQALLOC		30
-#define XFS_TRANS_QM_SETQLIM		31
-#define XFS_TRANS_QM_DQCLUSTER		32
-#define XFS_TRANS_QM_QINOCREATE		33
-#define XFS_TRANS_QM_QUOTAOFF_END	34
-#define XFS_TRANS_SB_UNIT		35
-#define XFS_TRANS_FSYNC_TS		36
-#define	XFS_TRANS_GROWFSRT_ALLOC	37
-#define	XFS_TRANS_GROWFSRT_ZERO		38
-#define	XFS_TRANS_GROWFSRT_FREE		39
-#define	XFS_TRANS_SWAPEXT		40
-#define	XFS_TRANS_SB_COUNT		41
-#define	XFS_TRANS_CHECKPOINT		42
-#define	XFS_TRANS_ICREATE		43
-#define	XFS_TRANS_TYPE_MAX		43
-/* new transaction types need to be reflected in xfs_logprint(8) */
-
-#define XFS_TRANS_TYPES \
-	{ XFS_TRANS_SETATTR_NOT_SIZE,	"SETATTR_NOT_SIZE" }, \
-	{ XFS_TRANS_SETATTR_SIZE,	"SETATTR_SIZE" }, \
-	{ XFS_TRANS_INACTIVE,		"INACTIVE" }, \
-	{ XFS_TRANS_CREATE,		"CREATE" }, \
-	{ XFS_TRANS_CREATE_TRUNC,	"CREATE_TRUNC" }, \
-	{ XFS_TRANS_TRUNCATE_FILE,	"TRUNCATE_FILE" }, \
-	{ XFS_TRANS_REMOVE,		"REMOVE" }, \
-	{ XFS_TRANS_LINK,		"LINK" }, \
-	{ XFS_TRANS_RENAME,		"RENAME" }, \
-	{ XFS_TRANS_MKDIR,		"MKDIR" }, \
-	{ XFS_TRANS_RMDIR,		"RMDIR" }, \
-	{ XFS_TRANS_SYMLINK,		"SYMLINK" }, \
-	{ XFS_TRANS_SET_DMATTRS,	"SET_DMATTRS" }, \
-	{ XFS_TRANS_GROWFS,		"GROWFS" }, \
-	{ XFS_TRANS_STRAT_WRITE,	"STRAT_WRITE" }, \
-	{ XFS_TRANS_DIOSTRAT,		"DIOSTRAT" }, \
-	{ XFS_TRANS_WRITEID,		"WRITEID" }, \
-	{ XFS_TRANS_ADDAFORK,		"ADDAFORK" }, \
-	{ XFS_TRANS_ATTRINVAL,		"ATTRINVAL" }, \
-	{ XFS_TRANS_ATRUNCATE,		"ATRUNCATE" }, \
-	{ XFS_TRANS_ATTR_SET,		"ATTR_SET" }, \
-	{ XFS_TRANS_ATTR_RM,		"ATTR_RM" }, \
-	{ XFS_TRANS_ATTR_FLAG,		"ATTR_FLAG" }, \
-	{ XFS_TRANS_CLEAR_AGI_BUCKET,	"CLEAR_AGI_BUCKET" }, \
-	{ XFS_TRANS_QM_SBCHANGE,	"QM_SBCHANGE" }, \
-	{ XFS_TRANS_QM_QUOTAOFF,	"QM_QUOTAOFF" }, \
-	{ XFS_TRANS_QM_DQALLOC,		"QM_DQALLOC" }, \
-	{ XFS_TRANS_QM_SETQLIM,		"QM_SETQLIM" }, \
-	{ XFS_TRANS_QM_DQCLUSTER,	"QM_DQCLUSTER" }, \
-	{ XFS_TRANS_QM_QINOCREATE,	"QM_QINOCREATE" }, \
-	{ XFS_TRANS_QM_QUOTAOFF_END,	"QM_QOFF_END" }, \
-	{ XFS_TRANS_SB_UNIT,		"SB_UNIT" }, \
-	{ XFS_TRANS_FSYNC_TS,		"FSYNC_TS" }, \
-	{ XFS_TRANS_GROWFSRT_ALLOC,	"GROWFSRT_ALLOC" }, \
-	{ XFS_TRANS_GROWFSRT_ZERO,	"GROWFSRT_ZERO" }, \
-	{ XFS_TRANS_GROWFSRT_FREE,	"GROWFSRT_FREE" }, \
-	{ XFS_TRANS_SWAPEXT,		"SWAPEXT" }, \
-	{ XFS_TRANS_SB_COUNT,		"SB_COUNT" }, \
-	{ XFS_TRANS_CHECKPOINT,		"CHECKPOINT" }, \
-	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
-	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
-	{ XLOG_UNMOUNT_REC_TYPE,	"UNMOUNT" }
-
-/*
- * This structure is used to track log items associated with
- * a transaction.  It points to the log item and keeps some
- * flags to track the state of the log item.  It also tracks
- * the amount of space needed to log the item it describes
- * once we get to commit processing (see xfs_trans_commit()).
- */
-struct xfs_log_item_desc {
-	struct xfs_log_item	*lid_item;
-	struct list_head	lid_trans;
-	unsigned char		lid_flags;
-};
-
-#define XFS_LID_DIRTY		0x1
-
-/*
- * Values for t_flags.
- */
-#define	XFS_TRANS_DIRTY		0x01	/* something needs to be logged */
-#define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
-#define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
-#define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
-#define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
-#define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
-#define XFS_TRANS_FREEZE_PROT	0x40	/* Transaction has elevated writer
-					   count in superblock */
-
-/*
- * Values for call flags parameter.
- */
-#define	XFS_TRANS_RELEASE_LOG_RES	0x4
-#define	XFS_TRANS_ABORT			0x8
-
-/*
- * Field values for xfs_trans_mod_sb.
- */
-#define	XFS_TRANS_SB_ICOUNT		0x00000001
-#define	XFS_TRANS_SB_IFREE		0x00000002
-#define	XFS_TRANS_SB_FDBLOCKS		0x00000004
-#define	XFS_TRANS_SB_RES_FDBLOCKS	0x00000008
-#define	XFS_TRANS_SB_FREXTENTS		0x00000010
-#define	XFS_TRANS_SB_RES_FREXTENTS	0x00000020
-#define	XFS_TRANS_SB_DBLOCKS		0x00000040
-#define	XFS_TRANS_SB_AGCOUNT		0x00000080
-#define	XFS_TRANS_SB_IMAXPCT		0x00000100
-#define	XFS_TRANS_SB_REXTSIZE		0x00000200
-#define	XFS_TRANS_SB_RBMBLOCKS		0x00000400
-#define	XFS_TRANS_SB_RBLOCKS		0x00000800
-#define	XFS_TRANS_SB_REXTENTS		0x00001000
-#define	XFS_TRANS_SB_REXTSLOG		0x00002000
-
-/*
- * Here we centralize the specification of XFS meta-data buffer
- * reference count values.  This determine how hard the buffer
- * cache tries to hold onto the buffer.
- */
-#define	XFS_AGF_REF		4
-#define	XFS_AGI_REF		4
-#define	XFS_AGFL_REF		3
-#define	XFS_INO_BTREE_REF	3
-#define	XFS_ALLOC_BTREE_REF	2
-#define	XFS_BMAP_BTREE_REF	2
-#define	XFS_DIR_BTREE_REF	2
-#define	XFS_INO_REF		2
-#define	XFS_ATTR_BTREE_REF	1
-#define	XFS_DQUOT_REF		1
-
-/*
- * Flags for xfs_trans_ichgtime().
- */
-#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
-#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
-#define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
-
-
 /*
  * Inode Log Item Format definitions.
  *
@@ -797,7 +625,6 @@ typedef struct xfs_qoff_logformat {
 	char			qf_pad[12];	/* padding for future */
 } xfs_qoff_logformat_t;
 
-
 /*
  * Disk quotas status in m_qflags, and also sb_qflags. 16 bits.
  */
@@ -849,8 +676,4 @@ struct xfs_icreate_log {
 	__be32		icl_gen;	/* inode generation number to use */
 };
 
-int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
-int	xfs_log_calc_minimum_size(struct xfs_mount *);
-
-
 #endif /* __XFS_LOG_FORMAT_H__ */

fs/xfs/xfs_log_priv.h

@@ -22,6 +22,7 @@ struct xfs_buf;
 struct xlog;
 struct xlog_ticket;
 struct xfs_mount;
+struct xfs_log_callback;
 
 /*
  * Flags for log structure
@@ -227,8 +228,8 @@ typedef struct xlog_in_core {
 
 	/* Callback structures need their own cacheline */
 	spinlock_t		ic_callback_lock ____cacheline_aligned_in_smp;
-	xfs_log_callback_t	*ic_callback;
-	xfs_log_callback_t	**ic_callback_tail;
+	struct xfs_log_callback	*ic_callback;
+	struct xfs_log_callback	**ic_callback_tail;
 
 	/* reference counts need their own cacheline */
 	atomic_t		ic_refcnt ____cacheline_aligned_in_smp;
@@ -254,7 +255,7 @@ struct xfs_cil_ctx {
 	int			space_used;	/* aggregate size of regions */
 	struct list_head	busy_extents;	/* busy extents in chkpt */
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
-	xfs_log_callback_t	log_cb;		/* completion callback hook. */
+	struct xfs_log_callback	log_cb;		/* completion callback hook. */
 	struct list_head	committing;	/* ctx committing list */
 };
 
@@ -514,12 +515,10 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space)
 /*
  * Committed Item List interfaces
  */
-int
-xlog_cil_init(struct xlog *log);
-void
-xlog_cil_init_post_recovery(struct xlog *log);
-void
-xlog_cil_destroy(struct xlog *log);
+int	xlog_cil_init(struct xlog *log);
+void	xlog_cil_init_post_recovery(struct xlog *log);
+void	xlog_cil_destroy(struct xlog *log);
+bool	xlog_cil_empty(struct xlog *log);
 
 /*
  * CIL force routines

fs/xfs/xfs_log_recover.c

@@ -17,42 +17,34 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_error.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
-#include "xfs_inode_item.h"
-#include "xfs_alloc.h"
-#include "xfs_ialloc.h"
+#include "xfs_trans.h"
+#include "xfs_log.h"
 #include "xfs_log_priv.h"
-#include "xfs_buf_item.h"
 #include "xfs_log_recover.h"
+#include "xfs_inode_item.h"
 #include "xfs_extfree_item.h"
 #include "xfs_trans_priv.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
 #include "xfs_quota.h"
 #include "xfs_cksum.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
-#include "xfs_icreate_item.h"
-
-/* Need all the magic numbers and buffer ops structures from these headers */
-#include "xfs_symlink.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dinode.h"
+#include "xfs_error.h"
 #include "xfs_dir2.h"
-#include "xfs_attr_leaf.h"
-#include "xfs_attr_remote.h"
 
 #define BLK_AVG(blk1, blk2)	((blk1+blk2) >> 1)
 
@@ -305,9 +297,9 @@ xlog_header_check_dump(
 	xfs_mount_t		*mp,
 	xlog_rec_header_t	*head)
 {
-	xfs_debug(mp, "%s:  SB : uuid = %pU, fmt = %d\n",
+	xfs_debug(mp, "%s:  SB : uuid = %pU, fmt = %d",
 		__func__, &mp->m_sb.sb_uuid, XLOG_FMT);
-	xfs_debug(mp, "    log : uuid = %pU, fmt = %d\n",
+	xfs_debug(mp, "    log : uuid = %pU, fmt = %d",
 		&head->h_fs_uuid, be32_to_cpu(head->h_fmt));
 }
 #else
@@ -2362,7 +2354,7 @@ xlog_recover_do_reg_buffer(
 					item->ri_buf[i].i_len, __func__);
 				goto next;
 			}
-			error = xfs_qm_dqcheck(mp, item->ri_buf[i].i_addr,
+			error = xfs_dqcheck(mp, item->ri_buf[i].i_addr,
 					       -1, 0, XFS_QMOPT_DOWARN,
 					       "dquot_buf_recover");
 			if (error)
@@ -2393,133 +2385,6 @@ xlog_recover_do_reg_buffer(
 		xlog_recover_validate_buf_type(mp, bp, buf_f);
 }
 
-/*
- * Do some primitive error checking on ondisk dquot data structures.
- */
-int
-xfs_qm_dqcheck(
-	struct xfs_mount *mp,
-	xfs_disk_dquot_t *ddq,
-	xfs_dqid_t	 id,
-	uint		 type,	  /* used only when IO_dorepair is true */
-	uint		 flags,
-	char		 *str)
-{
-	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
-	int		errs = 0;
-
-	/*
-	 * We can encounter an uninitialized dquot buffer for 2 reasons:
-	 * 1. If we crash while deleting the quotainode(s), and those blks got
-	 *    used for user data. This is because we take the path of regular
-	 *    file deletion; however, the size field of quotainodes is never
-	 *    updated, so all the tricks that we play in itruncate_finish
-	 *    don't quite matter.
-	 *
-	 * 2. We don't play the quota buffers when there's a quotaoff logitem.
-	 *    But the allocation will be replayed so we'll end up with an
-	 *    uninitialized quota block.
-	 *
-	 * This is all fine; things are still consistent, and we haven't lost
-	 * any quota information. Just don't complain about bad dquot blks.
-	 */
-	if (ddq->d_magic != cpu_to_be16(XFS_DQUOT_MAGIC)) {
-		if (flags & XFS_QMOPT_DOWARN)
-			xfs_alert(mp,
-			"%s : XFS dquot ID 0x%x, magic 0x%x != 0x%x",
-			str, id, be16_to_cpu(ddq->d_magic), XFS_DQUOT_MAGIC);
-		errs++;
-	}
-	if (ddq->d_version != XFS_DQUOT_VERSION) {
-		if (flags & XFS_QMOPT_DOWARN)
-			xfs_alert(mp,
-			"%s : XFS dquot ID 0x%x, version 0x%x != 0x%x",
-			str, id, ddq->d_version, XFS_DQUOT_VERSION);
-		errs++;
-	}
-
-	if (ddq->d_flags != XFS_DQ_USER &&
-	    ddq->d_flags != XFS_DQ_PROJ &&
-	    ddq->d_flags != XFS_DQ_GROUP) {
-		if (flags & XFS_QMOPT_DOWARN)
-			xfs_alert(mp,
-			"%s : XFS dquot ID 0x%x, unknown flags 0x%x",
-			str, id, ddq->d_flags);
-		errs++;
-	}
-
-	if (id != -1 && id != be32_to_cpu(ddq->d_id)) {
-		if (flags & XFS_QMOPT_DOWARN)
-			xfs_alert(mp,
-			"%s : ondisk-dquot 0x%p, ID mismatch: "
-			"0x%x expected, found id 0x%x",
-			str, ddq, id, be32_to_cpu(ddq->d_id));
-		errs++;
-	}
-
-	if (!errs && ddq->d_id) {
-		if (ddq->d_blk_softlimit &&
-		    be64_to_cpu(ddq->d_bcount) >
-				be64_to_cpu(ddq->d_blk_softlimit)) {
-			if (!ddq->d_btimer) {
-				if (flags & XFS_QMOPT_DOWARN)
-					xfs_alert(mp,
-			"%s : Dquot ID 0x%x (0x%p) BLK TIMER NOT STARTED",
-					str, (int)be32_to_cpu(ddq->d_id), ddq);
-				errs++;
-			}
-		}
-		if (ddq->d_ino_softlimit &&
-		    be64_to_cpu(ddq->d_icount) >
-				be64_to_cpu(ddq->d_ino_softlimit)) {
-			if (!ddq->d_itimer) {
-				if (flags & XFS_QMOPT_DOWARN)
-					xfs_alert(mp,
-			"%s : Dquot ID 0x%x (0x%p) INODE TIMER NOT STARTED",
-					str, (int)be32_to_cpu(ddq->d_id), ddq);
-				errs++;
-			}
-		}
-		if (ddq->d_rtb_softlimit &&
-		    be64_to_cpu(ddq->d_rtbcount) >
-				be64_to_cpu(ddq->d_rtb_softlimit)) {
-			if (!ddq->d_rtbtimer) {
-				if (flags & XFS_QMOPT_DOWARN)
-					xfs_alert(mp,
-			"%s : Dquot ID 0x%x (0x%p) RTBLK TIMER NOT STARTED",
-					str, (int)be32_to_cpu(ddq->d_id), ddq);
-				errs++;
-			}
-		}
-	}
-
-	if (!errs || !(flags & XFS_QMOPT_DQREPAIR))
-		return errs;
-
-	if (flags & XFS_QMOPT_DOWARN)
-		xfs_notice(mp, "Re-initializing dquot ID 0x%x", id);
-
-	/*
-	 * Typically, a repair is only requested by quotacheck.
-	 */
-	ASSERT(id != -1);
-	ASSERT(flags & XFS_QMOPT_DQREPAIR);
-	memset(d, 0, sizeof(xfs_dqblk_t));
-
-	d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
-	d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
-	d->dd_diskdq.d_flags = type;
-	d->dd_diskdq.d_id = cpu_to_be32(id);
-
-	if (xfs_sb_version_hascrc(&mp->m_sb)) {
-		uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid);
-		xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
-				 XFS_DQUOT_CRC_OFF);
-	}
-
-	return errs;
-}
-
 /*
  * Perform a dquot buffer recovery.
  * Simple algorithm: if we have found a QUOTAOFF log item of the same type
@@ -3125,7 +2990,7 @@ xlog_recover_dquot_pass2(
 	 */
 	dq_f = item->ri_buf[0].i_addr;
 	ASSERT(dq_f);
-	error = xfs_qm_dqcheck(mp, recddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
+	error = xfs_dqcheck(mp, recddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
 			   "xlog_recover_dquot_pass2 (log copy)");
 	if (error)
 		return XFS_ERROR(EIO);
@@ -3145,7 +3010,7 @@ xlog_recover_dquot_pass2(
 	 * was among a chunk of dquots created earlier, and we did some
 	 * minimal initialization then.
 	 */
-	error = xfs_qm_dqcheck(mp, ddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
+	error = xfs_dqcheck(mp, ddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
 			   "xlog_recover_dquot_pass2");
 	if (error) {
 		xfs_buf_relse(bp);
@@ -4077,7 +3942,7 @@ xlog_unpack_data_crc(
 	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
-		"log record CRC mismatch: found 0x%x, expected 0x%x.\n",
+		"log record CRC mismatch: found 0x%x, expected 0x%x.",
 					le32_to_cpu(rhead->h_crc),
 					le32_to_cpu(crc));
 			xfs_hex_dump(dp, 32);

fs/xfs/xfs_log_rlimit.c

@@ -17,16 +17,19 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_ag.h"
 #include "xfs_sb.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
 #include "xfs_trans_space.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
 #include "xfs_da_btree.h"
 #include "xfs_attr_leaf.h"
+#include "xfs_bmap_btree.h"
 
 /*
  * Calculate the maximum length in bytes that would be required for a local

fs/xfs/xfs_message.c

@@ -17,9 +17,8 @@
 
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"

fs/xfs/xfs_mount.c

@@ -17,35 +17,30 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
-#include "xfs_dir2.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
-#include "xfs_btree.h"
+#include "xfs_dir2.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
 #include "xfs_rtalloc.h"
 #include "xfs_bmap.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
+#include "xfs_log.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_fsops.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
-#include "xfs_cksum.h"
-#include "xfs_buf_item.h"
 
 
 #ifdef HAVE_PERCPU_SB

fs/xfs/xfs_mount.h

@@ -26,6 +26,7 @@ struct xfs_mru_cache;
 struct xfs_nameops;
 struct xfs_ail;
 struct xfs_quotainfo;
+struct xfs_dir_ops;
 
 #ifdef HAVE_PERCPU_SB
 
@@ -148,6 +149,8 @@ typedef struct xfs_mount {
 	int			m_dir_magicpct;	/* 37% of the dir blocksize */
 	__uint8_t		m_sectbb_log;	/* sectlog - BBSHIFT */
 	const struct xfs_nameops *m_dirnameops;	/* vector of dir name ops */
+	const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
+	const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
 	int			m_dirblksize;	/* directory block sz--bytes */
 	int			m_dirblkfsbs;	/* directory block sz--fsbs */
 	xfs_dablk_t		m_dirdatablk;	/* blockno of dir data v2 */

fs/xfs/xfs_qm.c

@@ -17,31 +17,28 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_ialloc.h"
 #include "xfs_itable.h"
-#include "xfs_rtalloc.h"
+#include "xfs_quota.h"
 #include "xfs_error.h"
 #include "xfs_bmap.h"
-#include "xfs_attr.h"
-#include "xfs_buf_item.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans.h"
 #include "xfs_trans_space.h"
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_cksum.h"
+#include "xfs_dinode.h"
 
 /*
  * The global quota manager. There is only one of these for the entire
@@ -664,20 +661,6 @@ xfs_qm_dqdetach(
 	}
 }
 
-int
-xfs_qm_calc_dquots_per_chunk(
-	struct xfs_mount	*mp,
-	unsigned int		nbblks)	/* basic block units */
-{
-	unsigned int	ndquots;
-
-	ASSERT(nbblks > 0);
-	ndquots = BBTOB(nbblks);
-	do_div(ndquots, sizeof(xfs_dqblk_t));
-
-	return ndquots;
-}
-
 struct xfs_qm_isolate {
 	struct list_head	buffers;
 	struct list_head	dispose;
@@ -858,7 +841,7 @@ xfs_qm_init_quotainfo(
 
 	/* Precalc some constants */
 	qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
-	qinf->qi_dqperchunk = xfs_qm_calc_dquots_per_chunk(mp,
+	qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(mp,
 							qinf->qi_dqchunklen);
 
 	mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
@@ -1092,10 +1075,10 @@ xfs_qm_reset_dqcounts(
 		/*
 		 * Do a sanity check, and if needed, repair the dqblk. Don't
 		 * output any warnings because it's perfectly possible to
-		 * find uninitialised dquot blks. See comment in xfs_qm_dqcheck.
+		 * find uninitialised dquot blks. See comment in xfs_dqcheck.
 		 */
-		(void) xfs_qm_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
-				      "xfs_quotacheck");
+		xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
+			    "xfs_quotacheck");
 		ddq->d_bcount = 0;
 		ddq->d_icount = 0;
 		ddq->d_rtbcount = 0;

fs/xfs/xfs_qm.h

@@ -103,8 +103,6 @@ xfs_dq_to_quota_inode(struct xfs_dquot *dqp)
 	return NULL;
 }
 
-extern int	xfs_qm_calc_dquots_per_chunk(struct xfs_mount *mp,
-					     unsigned int nbblks);
 extern void	xfs_trans_mod_dquot(struct xfs_trans *,
 					struct xfs_dquot *, uint, long);
 extern int	xfs_trans_reserve_quota_bydquots(struct xfs_trans *,

fs/xfs/xfs_qm_bhv.c

@@ -18,21 +18,15 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
 #include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_itable.h"
-#include "xfs_bmap.h"
-#include "xfs_rtalloc.h"
 #include "xfs_error.h"
-#include "xfs_attr.h"
-#include "xfs_buf_item.h"
+#include "xfs_trans.h"
 #include "xfs_qm.h"
 
 

fs/xfs/xfs_qm_syscalls.c

@@ -20,24 +20,18 @@
 
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_inode_item.h"
-#include "xfs_itable.h"
-#include "xfs_bmap.h"
-#include "xfs_rtalloc.h"
+#include "xfs_trans.h"
 #include "xfs_error.h"
-#include "xfs_attr.h"
-#include "xfs_buf_item.h"
+#include "xfs_quota.h"
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
@@ -287,7 +281,7 @@ xfs_qm_scall_trunc_qfiles(
 	int		error = 0, error2 = 0;
 
 	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
-		xfs_debug(mp, "%s: flags=%x m_qflags=%x\n",
+		xfs_debug(mp, "%s: flags=%x m_qflags=%x",
 			__func__, flags, mp->m_qflags);
 		return XFS_ERROR(EINVAL);
 	}
@@ -325,7 +319,7 @@ xfs_qm_scall_quotaon(
 	sbflags = 0;
 
 	if (flags == 0) {
-		xfs_debug(mp, "%s: zero flags, m_qflags=%x\n",
+		xfs_debug(mp, "%s: zero flags, m_qflags=%x",
 			__func__, mp->m_qflags);
 		return XFS_ERROR(EINVAL);
 	}
@@ -348,7 +342,7 @@ xfs_qm_scall_quotaon(
 	     (mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 &&
 	     (flags & XFS_PQUOTA_ENFD))) {
 		xfs_debug(mp,
-			"%s: Can't enforce without acct, flags=%x sbflags=%x\n",
+			"%s: Can't enforce without acct, flags=%x sbflags=%x",
 			__func__, flags, mp->m_sb.sb_qflags);
 		return XFS_ERROR(EINVAL);
 	}
@@ -648,7 +642,7 @@ xfs_qm_scall_setqlim(
 			q->qi_bsoftlimit = soft;
 		}
 	} else {
-		xfs_debug(mp, "blkhard %Ld < blksoft %Ld\n", hard, soft);
+		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
 	}
 	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
 		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
@@ -664,7 +658,7 @@ xfs_qm_scall_setqlim(
 			q->qi_rtbsoftlimit = soft;
 		}
 	} else {
-		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld\n", hard, soft);
+		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
 	}
 
 	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
@@ -681,7 +675,7 @@ xfs_qm_scall_setqlim(
 			q->qi_isoftlimit = soft;
 		}
 	} else {
-		xfs_debug(mp, "ihard %Ld < isoft %Ld\n", hard, soft);
+		xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft);
 	}
 
 	/*

fs/xfs/xfs_quota.h

@@ -150,10 +150,6 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp,
 	xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, pd, nb, ni, \
 				f | XFS_QMOPT_RES_REGBLKS)
 
-extern int xfs_qm_dqcheck(struct xfs_mount *, xfs_disk_dquot_t *,
-				xfs_dqid_t, uint, uint, char *);
 extern int xfs_mount_reset_sbqflags(struct xfs_mount *);
 
-extern const struct xfs_buf_ops xfs_dquot_buf_ops;
-
 #endif	/* __XFS_QUOTA_H__ */

fs/xfs/xfs_quota_defs.h

@@ -154,4 +154,8 @@ typedef __uint16_t	xfs_qwarncnt_t;
 		(XFS_QMOPT_UQUOTA | XFS_QMOPT_PQUOTA | XFS_QMOPT_GQUOTA)
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
+extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
+		       xfs_dqid_t id, uint type, uint flags, char *str);
+extern int xfs_calc_dquots_per_chunk(struct xfs_mount *mp, unsigned int nbblks);
+
 #endif	/* __XFS_QUOTA_H__ */

fs/xfs/xfs_quotaops.c

@@ -17,15 +17,14 @@
  */
 #include "xfs.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
-#include "xfs_log.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_inode.h"
 #include "xfs_quota.h"
 #include "xfs_trans.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_inode.h"
 #include "xfs_qm.h"
 #include <linux/quota.h>
 

fs/xfs/xfs_rtalloc.c

@@ -17,260 +17,348 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_alloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_rtalloc.h"
-#include "xfs_fsops.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc.h"
 #include "xfs_error.h"
-#include "xfs_inode_item.h"
+#include "xfs_trans.h"
 #include "xfs_trans_space.h"
 #include "xfs_trace.h"
 #include "xfs_buf.h"
 #include "xfs_icache.h"
+#include "xfs_dinode.h"
+#include "xfs_rtalloc.h"
 
 
 /*
- * Prototypes for internal functions.
- */
-
-
-STATIC int xfs_rtallocate_range(xfs_mount_t *, xfs_trans_t *, xfs_rtblock_t,
-		xfs_extlen_t, xfs_buf_t **, xfs_fsblock_t *);
-STATIC int xfs_rtany_summary(xfs_mount_t *, xfs_trans_t *, int, int,
-		xfs_rtblock_t, xfs_buf_t **, xfs_fsblock_t *, int *);
-STATIC int xfs_rtcheck_range(xfs_mount_t *, xfs_trans_t *, xfs_rtblock_t,
-		xfs_extlen_t, int, xfs_rtblock_t *, int *);
-STATIC int xfs_rtfind_back(xfs_mount_t *, xfs_trans_t *, xfs_rtblock_t,
-		xfs_rtblock_t, xfs_rtblock_t *);
-STATIC int xfs_rtfind_forw(xfs_mount_t *, xfs_trans_t *, xfs_rtblock_t,
-		xfs_rtblock_t, xfs_rtblock_t *);
-STATIC int xfs_rtget_summary( xfs_mount_t *, xfs_trans_t *, int,
-		xfs_rtblock_t, xfs_buf_t **, xfs_fsblock_t *, xfs_suminfo_t *);
-STATIC int xfs_rtmodify_range(xfs_mount_t *, xfs_trans_t *, xfs_rtblock_t,
-		xfs_extlen_t, int);
-STATIC int xfs_rtmodify_summary(xfs_mount_t *, xfs_trans_t *, int,
-		xfs_rtblock_t, int, xfs_buf_t **, xfs_fsblock_t *);
-
-/*
- * Internal functions.
- */
-
-/*
- * Allocate space to the bitmap or summary file, and zero it, for growfs.
+ * Read and return the summary information for a given extent size,
+ * bitmap block combination.
+ * Keeps track of a current summary block, so we don't keep reading
+ * it from the buffer cache.
  */
 STATIC int				/* error */
-xfs_growfs_rt_alloc(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_extlen_t	oblocks,	/* old count of blocks */
-	xfs_extlen_t	nblocks,	/* new count of blocks */
-	xfs_inode_t	*ip)		/* inode (bitmap/summary) */
+xfs_rtget_summary(
+	xfs_mount_t	*mp,		/* file system mount structure */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	int		log,		/* log2 of extent size */
+	xfs_rtblock_t	bbno,		/* bitmap block number */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
+	xfs_suminfo_t	*sum)		/* out: summary info for this block */
 {
-	xfs_fileoff_t	bno;		/* block number in file */
-	xfs_buf_t	*bp;		/* temporary buffer for zeroing */
-	int		committed;	/* transaction committed flag */
-	xfs_daddr_t	d;		/* disk block address */
-	int		error;		/* error return value */
-	xfs_fsblock_t	firstblock;	/* first block allocated in xaction */
-	xfs_bmap_free_t	flist;		/* list of freed blocks */
-	xfs_fsblock_t	fsbno;		/* filesystem block for bno */
-	xfs_bmbt_irec_t	map;		/* block map output */
-	int		nmap;		/* number of block maps */
-	int		resblks;	/* space reservation */
+	xfs_buf_t	*bp;		/* buffer for summary block */
+	int		error;		/* error value */
+	xfs_fsblock_t	sb;		/* summary fsblock */
+	int		so;		/* index into the summary file */
+	xfs_suminfo_t	*sp;		/* pointer to returned data */
 
 	/*
-	 * Allocate space to the file, as necessary.
+	 * Compute entry number in the summary file.
 	 */
-	while (oblocks < nblocks) {
-		int		cancelflags = 0;
-		xfs_trans_t	*tp;
-
-		tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ALLOC);
-		resblks = XFS_GROWFSRT_SPACE_RES(mp, nblocks - oblocks);
-		/*
-		 * Reserve space & log for one extent added to the file.
-		 */
-		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growdata,
-					  resblks, 0);
-		if (error)
-			goto error_cancel;
-		cancelflags = XFS_TRANS_RELEASE_LOG_RES;
-		/*
-		 * Lock the inode.
-		 */
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
-		xfs_bmap_init(&flist, &firstblock);
-		/*
-		 * Allocate blocks to the bitmap file.
-		 */
-		nmap = 1;
-		cancelflags |= XFS_TRANS_ABORT;
-		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, &firstblock,
-					resblks, &map, &nmap, &flist);
-		if (!error && nmap < 1)
-			error = XFS_ERROR(ENOSPC);
-		if (error)
-			goto error_cancel;
-		/*
-		 * Free any blocks freed up in the transaction, then commit.
-		 */
-		error = xfs_bmap_finish(&tp, &flist, &committed);
-		if (error)
-			goto error_cancel;
-		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-		if (error)
-			goto error;
+	so = XFS_SUMOFFS(mp, log, bbno);
+	/*
+	 * Compute the block number in the summary file.
+	 */
+	sb = XFS_SUMOFFSTOBLOCK(mp, so);
+	/*
+	 * If we have an old buffer, and the block number matches, use that.
+	 */
+	if (rbpp && *rbpp && *rsb == sb)
+		bp = *rbpp;
+	/*
+	 * Otherwise we have to get the buffer.
+	 */
+	else {
 		/*
-		 * Now we need to clear the allocated blocks.
-		 * Do this one block per transaction, to keep it simple.
+		 * If there was an old one, get rid of it first.
 		 */
-		cancelflags = 0;
-		for (bno = map.br_startoff, fsbno = map.br_startblock;
-		     bno < map.br_startoff + map.br_blockcount;
-		     bno++, fsbno++) {
-			tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ZERO);
-			/*
-			 * Reserve log for one block zeroing.
-			 */
-			error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtzero,
-						  0, 0);
-			if (error)
-				goto error_cancel;
-			/*
-			 * Lock the bitmap inode.
-			 */
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
-			xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-			/*
-			 * Get a buffer for the block.
-			 */
-			d = XFS_FSB_TO_DADDR(mp, fsbno);
-			bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
-				mp->m_bsize, 0);
-			if (bp == NULL) {
-				error = XFS_ERROR(EIO);
-error_cancel:
-				xfs_trans_cancel(tp, cancelflags);
-				goto error;
-			}
-			memset(bp->b_addr, 0, mp->m_sb.sb_blocksize);
-			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
-			/*
-			 * Commit the transaction.
-			 */
-			error = xfs_trans_commit(tp, 0);
-			if (error)
-				goto error;
+		if (rbpp && *rbpp)
+			xfs_trans_brelse(tp, *rbpp);
+		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
+		if (error) {
+			return error;
 		}
 		/*
-		 * Go on to the next extent, if any.
+		 * Remember this buffer and block for the next call.
 		 */
-		oblocks = map.br_startoff + map.br_blockcount;
+		if (rbpp) {
+			*rbpp = bp;
+			*rsb = sb;
+		}
 	}
+	/*
+	 * Point to the summary information & copy it out.
+	 */
+	sp = XFS_SUMPTR(mp, bp, so);
+	*sum = *sp;
+	/*
+	 * Drop the buffer if we're not asked to remember it.
+	 */
+	if (!rbpp)
+		xfs_trans_brelse(tp, bp);
 	return 0;
-
-error:
-	return error;
 }
 
+
 /*
- * Attempt to allocate an extent minlen<=len<=maxlen starting from
- * bitmap block bbno.  If we don't get maxlen then use prod to trim
- * the length, if given.  Returns error; returns starting block in *rtblock.
- * The lengths are all in rtextents.
+ * Return whether there are any free extents in the size range given
+ * by low and high, for the bitmap block bbno.
  */
 STATIC int				/* error */
-xfs_rtallocate_extent_block(
-	xfs_mount_t	*mp,		/* file system mount point */
+xfs_rtany_summary(
+	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
+	int		low,		/* low log2 extent size */
+	int		high,		/* high log2 extent size */
 	xfs_rtblock_t	bbno,		/* bitmap block number */
-	xfs_extlen_t	minlen,		/* minimum length to allocate */
-	xfs_extlen_t	maxlen,		/* maximum length to allocate */
-	xfs_extlen_t	*len,		/* out: actual length allocated */
-	xfs_rtblock_t	*nextp,		/* out: next block to try */
 	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
 	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
-	xfs_extlen_t	prod,		/* extent product factor */
-	xfs_rtblock_t	*rtblock)	/* out: start block allocated */
+	int		*stat)		/* out: any good extents here? */
 {
-	xfs_rtblock_t	besti;		/* best rtblock found so far */
-	xfs_rtblock_t	bestlen;	/* best length found so far */
-	xfs_rtblock_t	end;		/* last rtblock in chunk */
 	int		error;		/* error value */
-	xfs_rtblock_t	i;		/* current rtblock trying */
-	xfs_rtblock_t	next;		/* next rtblock to try */
-	int		stat;		/* status from internal calls */
+	int		log;		/* loop counter, log2 of ext. size */
+	xfs_suminfo_t	sum;		/* summary data */
 
 	/*
-	 * Loop over all the extents starting in this bitmap block,
-	 * looking for one that's long enough.
+	 * Loop over logs of extent sizes.  Order is irrelevant.
 	 */
-	for (i = XFS_BLOCKTOBIT(mp, bbno), besti = -1, bestlen = 0,
-		end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1;
-	     i <= end;
-	     i++) {
+	for (log = low; log <= high; log++) {
 		/*
-		 * See if there's a free extent of maxlen starting at i.
-		 * If it's not so then next will contain the first non-free.
+		 * Get one summary datum.
 		 */
-		error = xfs_rtcheck_range(mp, tp, i, maxlen, 1, &next, &stat);
+		error = xfs_rtget_summary(mp, tp, log, bbno, rbpp, rsb, &sum);
 		if (error) {
 			return error;
 		}
-		if (stat) {
-			/*
-			 * i for maxlen is all free, allocate and return that.
-			 */
-			error = xfs_rtallocate_range(mp, tp, i, maxlen, rbpp,
-				rsb);
-			if (error) {
-				return error;
-			}
-			*len = maxlen;
-			*rtblock = i;
-			return 0;
-		}
 		/*
-		 * In the case where we have a variable-sized allocation
-		 * request, figure out how big this free piece is,
-		 * and if it's big enough for the minimum, and the best
-		 * so far, remember it.
+		 * If there are any, return success.
 		 */
-		if (minlen < maxlen) {
-			xfs_rtblock_t	thislen;	/* this extent size */
-
-			thislen = next - i;
-			if (thislen >= minlen && thislen > bestlen) {
-				besti = i;
-				bestlen = thislen;
-			}
+		if (sum) {
+			*stat = 1;
+			return 0;
 		}
-		/*
-		 * If not done yet, find the start of the next free space.
-		 */
-		if (next < end) {
-			error = xfs_rtfind_forw(mp, tp, next, end, &i);
-			if (error) {
-				return error;
-			}
-		} else
-			break;
 	}
 	/*
-	 * Searched the whole thing & didn't find a maxlen free extent.
+	 * Found nothing, return failure.
+	 */
+	*stat = 0;
+	return 0;
+}
+
+
+/*
+ * Copy and transform the summary file, given the old and new
+ * parameters in the mount structures.
+ */
+STATIC int				/* error */
+xfs_rtcopy_summary(
+	xfs_mount_t	*omp,		/* old file system mount point */
+	xfs_mount_t	*nmp,		/* new file system mount point */
+	xfs_trans_t	*tp)		/* transaction pointer */
+{
+	xfs_rtblock_t	bbno;		/* bitmap block number */
+	xfs_buf_t	*bp;		/* summary buffer */
+	int		error;		/* error return value */
+	int		log;		/* summary level number (log length) */
+	xfs_suminfo_t	sum;		/* summary data */
+	xfs_fsblock_t	sumbno;		/* summary block number */
+
+	bp = NULL;
+	for (log = omp->m_rsumlevels - 1; log >= 0; log--) {
+		for (bbno = omp->m_sb.sb_rbmblocks - 1;
+		     (xfs_srtblock_t)bbno >= 0;
+		     bbno--) {
+			error = xfs_rtget_summary(omp, tp, log, bbno, &bp,
+				&sumbno, &sum);
+			if (error)
+				return error;
+			if (sum == 0)
+				continue;
+			error = xfs_rtmodify_summary(omp, tp, log, bbno, -sum,
+				&bp, &sumbno);
+			if (error)
+				return error;
+			error = xfs_rtmodify_summary(nmp, tp, log, bbno, sum,
+				&bp, &sumbno);
+			if (error)
+				return error;
+			ASSERT(sum > 0);
+		}
+	}
+	return 0;
+}
+/*
+ * Mark an extent specified by start and len allocated.
+ * Updates all the summary information as well as the bitmap.
+ */
+STATIC int				/* error */
+xfs_rtallocate_range(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* start block to allocate */
+	xfs_extlen_t	len,		/* length to allocate */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+{
+	xfs_rtblock_t	end;		/* end of the allocated extent */
+	int		error;		/* error value */
+	xfs_rtblock_t	postblock = 0;	/* first block allocated > end */
+	xfs_rtblock_t	preblock = 0;	/* first block allocated < start */
+
+	end = start + len - 1;
+	/*
+	 * Assume we're allocating out of the middle of a free extent.
+	 * We need to find the beginning and end of the extent so we can
+	 * properly update the summary.
+	 */
+	error = xfs_rtfind_back(mp, tp, start, 0, &preblock);
+	if (error) {
+		return error;
+	}
+	/*
+	 * Find the next allocated block (end of free extent).
+	 */
+	error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
+		&postblock);
+	if (error) {
+		return error;
+	}
+	/*
+	 * Decrement the summary information corresponding to the entire
+	 * (old) free extent.
+	 */
+	error = xfs_rtmodify_summary(mp, tp,
+		XFS_RTBLOCKLOG(postblock + 1 - preblock),
+		XFS_BITTOBLOCK(mp, preblock), -1, rbpp, rsb);
+	if (error) {
+		return error;
+	}
+	/*
+	 * If there are blocks not being allocated at the front of the
+	 * old extent, add summary data for them to be free.
+	 */
+	if (preblock < start) {
+		error = xfs_rtmodify_summary(mp, tp,
+			XFS_RTBLOCKLOG(start - preblock),
+			XFS_BITTOBLOCK(mp, preblock), 1, rbpp, rsb);
+		if (error) {
+			return error;
+		}
+	}
+	/*
+	 * If there are blocks not being allocated at the end of the
+	 * old extent, add summary data for them to be free.
+	 */
+	if (postblock > end) {
+		error = xfs_rtmodify_summary(mp, tp,
+			XFS_RTBLOCKLOG(postblock - end),
+			XFS_BITTOBLOCK(mp, end + 1), 1, rbpp, rsb);
+		if (error) {
+			return error;
+		}
+	}
+	/*
+	 * Modify the bitmap to mark this extent allocated.
+	 */
+	error = xfs_rtmodify_range(mp, tp, start, len, 0);
+	return error;
+}
+
+/*
+ * Attempt to allocate an extent minlen<=len<=maxlen starting from
+ * bitmap block bbno.  If we don't get maxlen then use prod to trim
+ * the length, if given.  Returns error; returns starting block in *rtblock.
+ * The lengths are all in rtextents.
+ */
+STATIC int				/* error */
+xfs_rtallocate_extent_block(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	bbno,		/* bitmap block number */
+	xfs_extlen_t	minlen,		/* minimum length to allocate */
+	xfs_extlen_t	maxlen,		/* maximum length to allocate */
+	xfs_extlen_t	*len,		/* out: actual length allocated */
+	xfs_rtblock_t	*nextp,		/* out: next block to try */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
+	xfs_extlen_t	prod,		/* extent product factor */
+	xfs_rtblock_t	*rtblock)	/* out: start block allocated */
+{
+	xfs_rtblock_t	besti;		/* best rtblock found so far */
+	xfs_rtblock_t	bestlen;	/* best length found so far */
+	xfs_rtblock_t	end;		/* last rtblock in chunk */
+	int		error;		/* error value */
+	xfs_rtblock_t	i;		/* current rtblock trying */
+	xfs_rtblock_t	next;		/* next rtblock to try */
+	int		stat;		/* status from internal calls */
+
+	/*
+	 * Loop over all the extents starting in this bitmap block,
+	 * looking for one that's long enough.
+	 */
+	for (i = XFS_BLOCKTOBIT(mp, bbno), besti = -1, bestlen = 0,
+		end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1;
+	     i <= end;
+	     i++) {
+		/*
+		 * See if there's a free extent of maxlen starting at i.
+		 * If it's not so then next will contain the first non-free.
+		 */
+		error = xfs_rtcheck_range(mp, tp, i, maxlen, 1, &next, &stat);
+		if (error) {
+			return error;
+		}
+		if (stat) {
+			/*
+			 * i for maxlen is all free, allocate and return that.
+			 */
+			error = xfs_rtallocate_range(mp, tp, i, maxlen, rbpp,
+				rsb);
+			if (error) {
+				return error;
+			}
+			*len = maxlen;
+			*rtblock = i;
+			return 0;
+		}
+		/*
+		 * In the case where we have a variable-sized allocation
+		 * request, figure out how big this free piece is,
+		 * and if it's big enough for the minimum, and the best
+		 * so far, remember it.
+		 */
+		if (minlen < maxlen) {
+			xfs_rtblock_t	thislen;	/* this extent size */
+
+			thislen = next - i;
+			if (thislen >= minlen && thislen > bestlen) {
+				besti = i;
+				bestlen = thislen;
+			}
+		}
+		/*
+		 * If not done yet, find the start of the next free space.
+		 */
+		if (next < end) {
+			error = xfs_rtfind_forw(mp, tp, next, end, &i);
+			if (error) {
+				return error;
+			}
+		} else
+			break;
+	}
+	/*
+	 * Searched the whole thing & didn't find a maxlen free extent.
 	 */
 	if (minlen < maxlen && besti != -1) {
 		xfs_extlen_t	p;	/* amount to trim length by */
@@ -639,1191 +727,205 @@ xfs_rtallocate_extent_size(
 			 */
 			if (r != NULLRTBLOCK) {
 				*rtblock = r;
-				return 0;
-			}
-			/*
-			 * If the "next block to try" returned from the
-			 * allocator is beyond the next bitmap block,
-			 * skip to that bitmap block.
-			 */
-			if (XFS_BITTOBLOCK(mp, n) > i + 1)
-				i = XFS_BITTOBLOCK(mp, n) - 1;
-		}
-	}
-	/*
-	 * Didn't find any maxlen blocks.  Try smaller ones, unless
-	 * we're asking for a fixed size extent.
-	 */
-	if (minlen > --maxlen) {
-		*rtblock = NULLRTBLOCK;
-		return 0;
-	}
-	ASSERT(minlen != 0);
-	ASSERT(maxlen != 0);
-
-	/*
-	 * Loop over sizes, from maxlen down to minlen.
-	 * This time, when we do the allocations, allow smaller ones
-	 * to succeed.
-	 */
-	for (l = xfs_highbit32(maxlen); l >= xfs_highbit32(minlen); l--) {
-		/*
-		 * Loop over all the bitmap blocks, try an allocation
-		 * starting in that block.
-		 */
-		for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
-			/*
-			 * Get the summary information for this level/block.
-			 */
-			error =	xfs_rtget_summary(mp, tp, l, i, rbpp, rsb,
-						  &sum);
-			if (error) {
-				return error;
-			}
-			/*
-			 * If nothing there, go on to next.
-			 */
-			if (!sum)
-				continue;
-			/*
-			 * Try the allocation.  Make sure the specified
-			 * minlen/maxlen are in the possible range for
-			 * this summary level.
-			 */
-			error = xfs_rtallocate_extent_block(mp, tp, i,
-					XFS_RTMAX(minlen, 1 << l),
-					XFS_RTMIN(maxlen, (1 << (l + 1)) - 1),
-					len, &n, rbpp, rsb, prod, &r);
-			if (error) {
-				return error;
-			}
-			/*
-			 * If it worked, return that extent.
-			 */
-			if (r != NULLRTBLOCK) {
-				*rtblock = r;
-				return 0;
-			}
-			/*
-			 * If the "next block to try" returned from the
-			 * allocator is beyond the next bitmap block,
-			 * skip to that bitmap block.
-			 */
-			if (XFS_BITTOBLOCK(mp, n) > i + 1)
-				i = XFS_BITTOBLOCK(mp, n) - 1;
-		}
-	}
-	/*
-	 * Got nothing, return failure.
-	 */
-	*rtblock = NULLRTBLOCK;
-	return 0;
-}
-
-/*
- * Mark an extent specified by start and len allocated.
- * Updates all the summary information as well as the bitmap.
- */
-STATIC int				/* error */
-xfs_rtallocate_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* start block to allocate */
-	xfs_extlen_t	len,		/* length to allocate */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
-{
-	xfs_rtblock_t	end;		/* end of the allocated extent */
-	int		error;		/* error value */
-	xfs_rtblock_t	postblock = 0;	/* first block allocated > end */
-	xfs_rtblock_t	preblock = 0;	/* first block allocated < start */
-
-	end = start + len - 1;
-	/*
-	 * Assume we're allocating out of the middle of a free extent.
-	 * We need to find the beginning and end of the extent so we can
-	 * properly update the summary.
-	 */
-	error = xfs_rtfind_back(mp, tp, start, 0, &preblock);
-	if (error) {
-		return error;
-	}
-	/*
-	 * Find the next allocated block (end of free extent).
-	 */
-	error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
-		&postblock);
-	if (error) {
-		return error;
-	}
-	/*
-	 * Decrement the summary information corresponding to the entire
-	 * (old) free extent.
-	 */
-	error = xfs_rtmodify_summary(mp, tp,
-		XFS_RTBLOCKLOG(postblock + 1 - preblock),
-		XFS_BITTOBLOCK(mp, preblock), -1, rbpp, rsb);
-	if (error) {
-		return error;
-	}
-	/*
-	 * If there are blocks not being allocated at the front of the
-	 * old extent, add summary data for them to be free.
-	 */
-	if (preblock < start) {
-		error = xfs_rtmodify_summary(mp, tp,
-			XFS_RTBLOCKLOG(start - preblock),
-			XFS_BITTOBLOCK(mp, preblock), 1, rbpp, rsb);
-		if (error) {
-			return error;
-		}
-	}
-	/*
-	 * If there are blocks not being allocated at the end of the
-	 * old extent, add summary data for them to be free.
-	 */
-	if (postblock > end) {
-		error = xfs_rtmodify_summary(mp, tp,
-			XFS_RTBLOCKLOG(postblock - end),
-			XFS_BITTOBLOCK(mp, end + 1), 1, rbpp, rsb);
-		if (error) {
-			return error;
-		}
-	}
-	/*
-	 * Modify the bitmap to mark this extent allocated.
-	 */
-	error = xfs_rtmodify_range(mp, tp, start, len, 0);
-	return error;
-}
-
-/*
- * Return whether there are any free extents in the size range given
- * by low and high, for the bitmap block bbno.
- */
-STATIC int				/* error */
-xfs_rtany_summary(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	int		low,		/* low log2 extent size */
-	int		high,		/* high log2 extent size */
-	xfs_rtblock_t	bbno,		/* bitmap block number */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
-	int		*stat)		/* out: any good extents here? */
-{
-	int		error;		/* error value */
-	int		log;		/* loop counter, log2 of ext. size */
-	xfs_suminfo_t	sum;		/* summary data */
-
-	/*
-	 * Loop over logs of extent sizes.  Order is irrelevant.
-	 */
-	for (log = low; log <= high; log++) {
-		/*
-		 * Get one summary datum.
-		 */
-		error = xfs_rtget_summary(mp, tp, log, bbno, rbpp, rsb, &sum);
-		if (error) {
-			return error;
-		}
-		/*
-		 * If there are any, return success.
-		 */
-		if (sum) {
-			*stat = 1;
-			return 0;
-		}
-	}
-	/*
-	 * Found nothing, return failure.
-	 */
-	*stat = 0;
-	return 0;
-}
-
-/*
- * Get a buffer for the bitmap or summary file block specified.
- * The buffer is returned read and locked.
- */
-STATIC int				/* error */
-xfs_rtbuf_get(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	block,		/* block number in bitmap or summary */
-	int		issum,		/* is summary not bitmap */
-	xfs_buf_t	**bpp)		/* output: buffer for the block */
-{
-	xfs_buf_t	*bp;		/* block buffer, result */
-	xfs_inode_t	*ip;		/* bitmap or summary inode */
-	xfs_bmbt_irec_t	map;
-	int		nmap = 1;
-	int		error;		/* error value */
-
-	ip = issum ? mp->m_rsumip : mp->m_rbmip;
-
-	error = xfs_bmapi_read(ip, block, 1, &map, &nmap, XFS_DATA_FORK);
-	if (error)
-		return error;
-
-	ASSERT(map.br_startblock != NULLFSBLOCK);
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
-				   mp->m_bsize, 0, &bp, NULL);
-	if (error)
-		return error;
-	ASSERT(!xfs_buf_geterror(bp));
-	*bpp = bp;
-	return 0;
-}
-
-#ifdef DEBUG
-/*
- * Check that the given extent (block range) is allocated already.
- */
-STATIC int				/* error */
-xfs_rtcheck_alloc_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	bno,		/* starting block number of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		*stat)		/* out: 1 for allocated, 0 for not */
-{
-	xfs_rtblock_t	new;		/* dummy for xfs_rtcheck_range */
-
-	return xfs_rtcheck_range(mp, tp, bno, len, 0, &new, stat);
-}
-#endif
-
-/*
- * Check that the given range is either all allocated (val = 0) or
- * all free (val = 1).
- */
-STATIC int				/* error */
-xfs_rtcheck_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block number of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		val,		/* 1 for free, 0 for allocated */
-	xfs_rtblock_t	*new,		/* out: first block not matching */
-	int		*stat)		/* out: 1 for matches, 0 for not */
-{
-	xfs_rtword_t	*b;		/* current word in buffer */
-	int		bit;		/* bit number in the word */
-	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
-	xfs_rtword_t	*bufp;		/* starting word in buffer */
-	int		error;		/* error value */
-	xfs_rtblock_t	i;		/* current bit number rel. to start */
-	xfs_rtblock_t	lastbit;	/* last useful bit in word */
-	xfs_rtword_t	mask;		/* mask of relevant bits for value */
-	xfs_rtword_t	wdiff;		/* difference from wanted value */
-	int		word;		/* word number in the buffer */
-
-	/*
-	 * Compute starting bitmap block number
-	 */
-	block = XFS_BITTOBLOCK(mp, start);
-	/*
-	 * Read the bitmap block.
-	 */
-	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
-	if (error) {
-		return error;
-	}
-	bufp = bp->b_addr;
-	/*
-	 * Compute the starting word's address, and starting bit.
-	 */
-	word = XFS_BITTOWORD(mp, start);
-	b = &bufp[word];
-	bit = (int)(start & (XFS_NBWORD - 1));
-	/*
-	 * 0 (allocated) => all zero's; 1 (free) => all one's.
-	 */
-	val = -val;
-	/*
-	 * If not starting on a word boundary, deal with the first
-	 * (partial) word.
-	 */
-	if (bit) {
-		/*
-		 * Compute first bit not examined.
-		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
-		/*
-		 * Mask of relevant bits.
-		 */
-		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = (*b ^ val) & mask)) {
-			/*
-			 * Different, compute first wrong bit and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i = XFS_RTLOBIT(wdiff) - bit;
-			*new = start + i;
-			*stat = 0;
-			return 0;
-		}
-		i = lastbit - bit;
-		/*
-		 * Go on to next block if that's where the next word is
-		 * and we need the next word.
-		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
-			/*
-			 * If done with this block, get the next one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			b = bufp = bp->b_addr;
-			word = 0;
-		} else {
-			/*
-			 * Go on to the next word in the buffer.
-			 */
-			b++;
-		}
-	} else {
-		/*
-		 * Starting on a word boundary, no partial word.
-		 */
-		i = 0;
-	}
-	/*
-	 * Loop over whole words in buffers.  When we use up one buffer
-	 * we move on to the next one.
-	 */
-	while (len - i >= XFS_NBWORD) {
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = *b ^ val)) {
-			/*
-			 * Different, compute first wrong bit and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_RTLOBIT(wdiff);
-			*new = start + i;
-			*stat = 0;
-			return 0;
-		}
-		i += XFS_NBWORD;
-		/*
-		 * Go on to next block if that's where the next word is
-		 * and we need the next word.
-		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
-			/*
-			 * If done with this block, get the next one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			b = bufp = bp->b_addr;
-			word = 0;
-		} else {
-			/*
-			 * Go on to the next word in the buffer.
-			 */
-			b++;
-		}
-	}
-	/*
-	 * If not ending on a word boundary, deal with the last
-	 * (partial) word.
-	 */
-	if ((lastbit = len - i)) {
-		/*
-		 * Mask of relevant bits.
-		 */
-		mask = ((xfs_rtword_t)1 << lastbit) - 1;
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = (*b ^ val) & mask)) {
-			/*
-			 * Different, compute first wrong bit and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_RTLOBIT(wdiff);
-			*new = start + i;
-			*stat = 0;
-			return 0;
-		} else
-			i = len;
-	}
-	/*
-	 * Successful, return.
-	 */
-	xfs_trans_brelse(tp, bp);
-	*new = start + i;
-	*stat = 1;
-	return 0;
-}
-
-/*
- * Copy and transform the summary file, given the old and new
- * parameters in the mount structures.
- */
-STATIC int				/* error */
-xfs_rtcopy_summary(
-	xfs_mount_t	*omp,		/* old file system mount point */
-	xfs_mount_t	*nmp,		/* new file system mount point */
-	xfs_trans_t	*tp)		/* transaction pointer */
-{
-	xfs_rtblock_t	bbno;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* summary buffer */
-	int		error;		/* error return value */
-	int		log;		/* summary level number (log length) */
-	xfs_suminfo_t	sum;		/* summary data */
-	xfs_fsblock_t	sumbno;		/* summary block number */
-
-	bp = NULL;
-	for (log = omp->m_rsumlevels - 1; log >= 0; log--) {
-		for (bbno = omp->m_sb.sb_rbmblocks - 1;
-		     (xfs_srtblock_t)bbno >= 0;
-		     bbno--) {
-			error = xfs_rtget_summary(omp, tp, log, bbno, &bp,
-				&sumbno, &sum);
-			if (error)
-				return error;
-			if (sum == 0)
-				continue;
-			error = xfs_rtmodify_summary(omp, tp, log, bbno, -sum,
-				&bp, &sumbno);
-			if (error)
-				return error;
-			error = xfs_rtmodify_summary(nmp, tp, log, bbno, sum,
-				&bp, &sumbno);
-			if (error)
-				return error;
-			ASSERT(sum > 0);
-		}
-	}
-	return 0;
-}
-
-/*
- * Searching backward from start to limit, find the first block whose
- * allocated/free state is different from start's.
- */
-STATIC int				/* error */
-xfs_rtfind_back(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block to look at */
-	xfs_rtblock_t	limit,		/* last block to look at */
-	xfs_rtblock_t	*rtblock)	/* out: start block found */
-{
-	xfs_rtword_t	*b;		/* current word in buffer */
-	int		bit;		/* bit number in the word */
-	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
-	xfs_rtword_t	*bufp;		/* starting word in buffer */
-	int		error;		/* error value */
-	xfs_rtblock_t	firstbit;	/* first useful bit in the word */
-	xfs_rtblock_t	i;		/* current bit number rel. to start */
-	xfs_rtblock_t	len;		/* length of inspected area */
-	xfs_rtword_t	mask;		/* mask of relevant bits for value */
-	xfs_rtword_t	want;		/* mask for "good" values */
-	xfs_rtword_t	wdiff;		/* difference from wanted value */
-	int		word;		/* word number in the buffer */
-
-	/*
-	 * Compute and read in starting bitmap block for starting block.
-	 */
-	block = XFS_BITTOBLOCK(mp, start);
-	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
-	if (error) {
-		return error;
-	}
-	bufp = bp->b_addr;
-	/*
-	 * Get the first word's index & point to it.
-	 */
-	word = XFS_BITTOWORD(mp, start);
-	b = &bufp[word];
-	bit = (int)(start & (XFS_NBWORD - 1));
-	len = start - limit + 1;
-	/*
-	 * Compute match value, based on the bit at start: if 1 (free)
-	 * then all-ones, else all-zeroes.
-	 */
-	want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0;
-	/*
-	 * If the starting position is not word-aligned, deal with the
-	 * partial word.
-	 */
-	if (bit < XFS_NBWORD - 1) {
-		/*
-		 * Calculate first (leftmost) bit number to look at,
-		 * and mask for all the relevant bits in this word.
-		 */
-		firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0);
-		mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) <<
-			firstbit;
-		/*
-		 * Calculate the difference between the value there
-		 * and what we're looking for.
-		 */
-		if ((wdiff = (*b ^ want) & mask)) {
-			/*
-			 * Different.  Mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i = bit - XFS_RTHIBIT(wdiff);
-			*rtblock = start - i + 1;
-			return 0;
-		}
-		i = bit - firstbit + 1;
-		/*
-		 * Go on to previous block if that's where the previous word is
-		 * and we need the previous word.
-		 */
-		if (--word == -1 && i < len) {
-			/*
-			 * If done with this block, get the previous one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, --block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			bufp = bp->b_addr;
-			word = XFS_BLOCKWMASK(mp);
-			b = &bufp[word];
-		} else {
-			/*
-			 * Go on to the previous word in the buffer.
-			 */
-			b--;
-		}
-	} else {
-		/*
-		 * Starting on a word boundary, no partial word.
-		 */
-		i = 0;
-	}
-	/*
-	 * Loop over whole words in buffers.  When we use up one buffer
-	 * we move on to the previous one.
-	 */
-	while (len - i >= XFS_NBWORD) {
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = *b ^ want)) {
-			/*
-			 * Different, mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
-			*rtblock = start - i + 1;
-			return 0;
-		}
-		i += XFS_NBWORD;
-		/*
-		 * Go on to previous block if that's where the previous word is
-		 * and we need the previous word.
-		 */
-		if (--word == -1 && i < len) {
-			/*
-			 * If done with this block, get the previous one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, --block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			bufp = bp->b_addr;
-			word = XFS_BLOCKWMASK(mp);
-			b = &bufp[word];
-		} else {
-			/*
-			 * Go on to the previous word in the buffer.
-			 */
-			b--;
-		}
-	}
-	/*
-	 * If not ending on a word boundary, deal with the last
-	 * (partial) word.
-	 */
-	if (len - i) {
-		/*
-		 * Calculate first (leftmost) bit number to look at,
-		 * and mask for all the relevant bits in this word.
-		 */
-		firstbit = XFS_NBWORD - (len - i);
-		mask = (((xfs_rtword_t)1 << (len - i)) - 1) << firstbit;
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = (*b ^ want) & mask)) {
-			/*
-			 * Different, mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
-			*rtblock = start - i + 1;
-			return 0;
-		} else
-			i = len;
-	}
-	/*
-	 * No match, return that we scanned the whole area.
-	 */
-	xfs_trans_brelse(tp, bp);
-	*rtblock = start - i + 1;
-	return 0;
-}
-
-/*
- * Searching forward from start to limit, find the first block whose
- * allocated/free state is different from start's.
- */
-STATIC int				/* error */
-xfs_rtfind_forw(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block to look at */
-	xfs_rtblock_t	limit,		/* last block to look at */
-	xfs_rtblock_t	*rtblock)	/* out: start block found */
-{
-	xfs_rtword_t	*b;		/* current word in buffer */
-	int		bit;		/* bit number in the word */
-	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
-	xfs_rtword_t	*bufp;		/* starting word in buffer */
-	int		error;		/* error value */
-	xfs_rtblock_t	i;		/* current bit number rel. to start */
-	xfs_rtblock_t	lastbit;	/* last useful bit in the word */
-	xfs_rtblock_t	len;		/* length of inspected area */
-	xfs_rtword_t	mask;		/* mask of relevant bits for value */
-	xfs_rtword_t	want;		/* mask for "good" values */
-	xfs_rtword_t	wdiff;		/* difference from wanted value */
-	int		word;		/* word number in the buffer */
-
-	/*
-	 * Compute and read in starting bitmap block for starting block.
-	 */
-	block = XFS_BITTOBLOCK(mp, start);
-	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
-	if (error) {
-		return error;
-	}
-	bufp = bp->b_addr;
-	/*
-	 * Get the first word's index & point to it.
-	 */
-	word = XFS_BITTOWORD(mp, start);
-	b = &bufp[word];
-	bit = (int)(start & (XFS_NBWORD - 1));
-	len = limit - start + 1;
-	/*
-	 * Compute match value, based on the bit at start: if 1 (free)
-	 * then all-ones, else all-zeroes.
-	 */
-	want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0;
-	/*
-	 * If the starting position is not word-aligned, deal with the
-	 * partial word.
-	 */
-	if (bit) {
-		/*
-		 * Calculate last (rightmost) bit number to look at,
-		 * and mask for all the relevant bits in this word.
-		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
-		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
-		/*
-		 * Calculate the difference between the value there
-		 * and what we're looking for.
-		 */
-		if ((wdiff = (*b ^ want) & mask)) {
-			/*
-			 * Different.  Mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i = XFS_RTLOBIT(wdiff) - bit;
-			*rtblock = start + i - 1;
-			return 0;
-		}
-		i = lastbit - bit;
-		/*
-		 * Go on to next block if that's where the next word is
-		 * and we need the next word.
-		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
-			/*
-			 * If done with this block, get the previous one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			b = bufp = bp->b_addr;
-			word = 0;
-		} else {
-			/*
-			 * Go on to the previous word in the buffer.
-			 */
-			b++;
-		}
-	} else {
-		/*
-		 * Starting on a word boundary, no partial word.
-		 */
-		i = 0;
-	}
-	/*
-	 * Loop over whole words in buffers.  When we use up one buffer
-	 * we move on to the next one.
-	 */
-	while (len - i >= XFS_NBWORD) {
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = *b ^ want)) {
-			/*
-			 * Different, mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_RTLOBIT(wdiff);
-			*rtblock = start + i - 1;
-			return 0;
-		}
-		i += XFS_NBWORD;
-		/*
-		 * Go on to next block if that's where the next word is
-		 * and we need the next word.
-		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
-			/*
-			 * If done with this block, get the next one.
-			 */
-			xfs_trans_brelse(tp, bp);
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
-			if (error) {
-				return error;
-			}
-			b = bufp = bp->b_addr;
-			word = 0;
-		} else {
-			/*
-			 * Go on to the next word in the buffer.
-			 */
-			b++;
-		}
-	}
-	/*
-	 * If not ending on a word boundary, deal with the last
-	 * (partial) word.
-	 */
-	if ((lastbit = len - i)) {
-		/*
-		 * Calculate mask for all the relevant bits in this word.
-		 */
-		mask = ((xfs_rtword_t)1 << lastbit) - 1;
-		/*
-		 * Compute difference between actual and desired value.
-		 */
-		if ((wdiff = (*b ^ want) & mask)) {
-			/*
-			 * Different, mark where we are and return.
-			 */
-			xfs_trans_brelse(tp, bp);
-			i += XFS_RTLOBIT(wdiff);
-			*rtblock = start + i - 1;
-			return 0;
-		} else
-			i = len;
-	}
-	/*
-	 * No match, return that we scanned the whole area.
-	 */
-	xfs_trans_brelse(tp, bp);
-	*rtblock = start + i - 1;
-	return 0;
-}
-
-/*
- * Mark an extent specified by start and len freed.
- * Updates all the summary information as well as the bitmap.
- */
-STATIC int				/* error */
-xfs_rtfree_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block to free */
-	xfs_extlen_t	len,		/* length to free */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
-{
-	xfs_rtblock_t	end;		/* end of the freed extent */
-	int		error;		/* error value */
-	xfs_rtblock_t	postblock;	/* first block freed > end */
-	xfs_rtblock_t	preblock;	/* first block freed < start */
-
-	end = start + len - 1;
-	/*
-	 * Modify the bitmap to mark this extent freed.
-	 */
-	error = xfs_rtmodify_range(mp, tp, start, len, 1);
-	if (error) {
-		return error;
-	}
-	/*
-	 * Assume we're freeing out of the middle of an allocated extent.
-	 * We need to find the beginning and end of the extent so we can
-	 * properly update the summary.
-	 */
-	error = xfs_rtfind_back(mp, tp, start, 0, &preblock);
-	if (error) {
-		return error;
-	}
-	/*
-	 * Find the next allocated block (end of allocated extent).
-	 */
-	error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
-		&postblock);
-	if (error)
-		return error;
-	/*
-	 * If there are blocks not being freed at the front of the
-	 * old extent, add summary data for them to be allocated.
-	 */
-	if (preblock < start) {
-		error = xfs_rtmodify_summary(mp, tp,
-			XFS_RTBLOCKLOG(start - preblock),
-			XFS_BITTOBLOCK(mp, preblock), -1, rbpp, rsb);
-		if (error) {
-			return error;
-		}
-	}
-	/*
-	 * If there are blocks not being freed at the end of the
-	 * old extent, add summary data for them to be allocated.
-	 */
-	if (postblock > end) {
-		error = xfs_rtmodify_summary(mp, tp,
-			XFS_RTBLOCKLOG(postblock - end),
-			XFS_BITTOBLOCK(mp, end + 1), -1, rbpp, rsb);
-		if (error) {
-			return error;
-		}
-	}
-	/*
-	 * Increment the summary information corresponding to the entire
-	 * (new) free extent.
-	 */
-	error = xfs_rtmodify_summary(mp, tp,
-		XFS_RTBLOCKLOG(postblock + 1 - preblock),
-		XFS_BITTOBLOCK(mp, preblock), 1, rbpp, rsb);
-	return error;
-}
-
-/*
- * Read and return the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- */
-STATIC int				/* error */
-xfs_rtget_summary(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	int		log,		/* log2 of extent size */
-	xfs_rtblock_t	bbno,		/* bitmap block number */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
-	xfs_suminfo_t	*sum)		/* out: summary info for this block */
-{
-	xfs_buf_t	*bp;		/* buffer for summary block */
-	int		error;		/* error value */
-	xfs_fsblock_t	sb;		/* summary fsblock */
-	int		so;		/* index into the summary file */
-	xfs_suminfo_t	*sp;		/* pointer to returned data */
-
-	/*
-	 * Compute entry number in the summary file.
-	 */
-	so = XFS_SUMOFFS(mp, log, bbno);
-	/*
-	 * Compute the block number in the summary file.
-	 */
-	sb = XFS_SUMOFFSTOBLOCK(mp, so);
-	/*
-	 * If we have an old buffer, and the block number matches, use that.
-	 */
-	if (rbpp && *rbpp && *rsb == sb)
-		bp = *rbpp;
-	/*
-	 * Otherwise we have to get the buffer.
-	 */
-	else {
-		/*
-		 * If there was an old one, get rid of it first.
-		 */
-		if (rbpp && *rbpp)
-			xfs_trans_brelse(tp, *rbpp);
-		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
-		if (error) {
-			return error;
-		}
-		/*
-		 * Remember this buffer and block for the next call.
-		 */
-		if (rbpp) {
-			*rbpp = bp;
-			*rsb = sb;
-		}
-	}
-	/*
-	 * Point to the summary information & copy it out.
-	 */
-	sp = XFS_SUMPTR(mp, bp, so);
-	*sum = *sp;
-	/*
-	 * Drop the buffer if we're not asked to remember it.
-	 */
-	if (!rbpp)
-		xfs_trans_brelse(tp, bp);
-	return 0;
-}
-
-/*
- * Set the given range of bitmap bits to the given value.
- * Do whatever I/O and logging is required.
- */
-STATIC int				/* error */
-xfs_rtmodify_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block to modify */
-	xfs_extlen_t	len,		/* length of extent to modify */
-	int		val)		/* 1 for free, 0 for allocated */
-{
-	xfs_rtword_t	*b;		/* current word in buffer */
-	int		bit;		/* bit number in the word */
-	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
-	xfs_rtword_t	*bufp;		/* starting word in buffer */
-	int		error;		/* error value */
-	xfs_rtword_t	*first;		/* first used word in the buffer */
-	int		i;		/* current bit number rel. to start */
-	int		lastbit;	/* last useful bit in word */
-	xfs_rtword_t	mask;		/* mask o frelevant bits for value */
-	int		word;		/* word number in the buffer */
-
-	/*
-	 * Compute starting bitmap block number.
-	 */
-	block = XFS_BITTOBLOCK(mp, start);
-	/*
-	 * Read the bitmap block, and point to its data.
-	 */
-	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
-	if (error) {
-		return error;
+				return 0;
+			}
+			/*
+			 * If the "next block to try" returned from the
+			 * allocator is beyond the next bitmap block,
+			 * skip to that bitmap block.
+			 */
+			if (XFS_BITTOBLOCK(mp, n) > i + 1)
+				i = XFS_BITTOBLOCK(mp, n) - 1;
+		}
 	}
-	bufp = bp->b_addr;
-	/*
-	 * Compute the starting word's address, and starting bit.
-	 */
-	word = XFS_BITTOWORD(mp, start);
-	first = b = &bufp[word];
-	bit = (int)(start & (XFS_NBWORD - 1));
 	/*
-	 * 0 (allocated) => all zeroes; 1 (free) => all ones.
+	 * Didn't find any maxlen blocks.  Try smaller ones, unless
+	 * we're asking for a fixed size extent.
 	 */
-	val = -val;
+	if (minlen > --maxlen) {
+		*rtblock = NULLRTBLOCK;
+		return 0;
+	}
+	ASSERT(minlen != 0);
+	ASSERT(maxlen != 0);
+
 	/*
-	 * If not starting on a word boundary, deal with the first
-	 * (partial) word.
+	 * Loop over sizes, from maxlen down to minlen.
+	 * This time, when we do the allocations, allow smaller ones
+	 * to succeed.
 	 */
-	if (bit) {
-		/*
-		 * Compute first bit not changed and mask of relevant bits.
-		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
-		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
-		/*
-		 * Set/clear the active bits.
-		 */
-		if (val)
-			*b |= mask;
-		else
-			*b &= ~mask;
-		i = lastbit - bit;
+	for (l = xfs_highbit32(maxlen); l >= xfs_highbit32(minlen); l--) {
 		/*
-		 * Go on to the next block if that's where the next word is
-		 * and we need the next word.
+		 * Loop over all the bitmap blocks, try an allocation
+		 * starting in that block.
 		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+		for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
 			/*
-			 * Log the changed part of this block.
-			 * Get the next one.
+			 * Get the summary information for this level/block.
 			 */
-			xfs_trans_log_buf(tp, bp,
-				(uint)((char *)first - (char *)bufp),
-				(uint)((char *)b - (char *)bufp));
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			error =	xfs_rtget_summary(mp, tp, l, i, rbpp, rsb,
+						  &sum);
 			if (error) {
 				return error;
 			}
-			first = b = bufp = bp->b_addr;
-			word = 0;
-		} else {
 			/*
-			 * Go on to the next word in the buffer
+			 * If nothing there, go on to next.
 			 */
-			b++;
-		}
-	} else {
-		/*
-		 * Starting on a word boundary, no partial word.
-		 */
-		i = 0;
-	}
-	/*
-	 * Loop over whole words in buffers.  When we use up one buffer
-	 * we move on to the next one.
-	 */
-	while (len - i >= XFS_NBWORD) {
-		/*
-		 * Set the word value correctly.
-		 */
-		*b = val;
-		i += XFS_NBWORD;
-		/*
-		 * Go on to the next block if that's where the next word is
-		 * and we need the next word.
-		 */
-		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			if (!sum)
+				continue;
 			/*
-			 * Log the changed part of this block.
-			 * Get the next one.
+			 * Try the allocation.  Make sure the specified
+			 * minlen/maxlen are in the possible range for
+			 * this summary level.
 			 */
-			xfs_trans_log_buf(tp, bp,
-				(uint)((char *)first - (char *)bufp),
-				(uint)((char *)b - (char *)bufp));
-			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			error = xfs_rtallocate_extent_block(mp, tp, i,
+					XFS_RTMAX(minlen, 1 << l),
+					XFS_RTMIN(maxlen, (1 << (l + 1)) - 1),
+					len, &n, rbpp, rsb, prod, &r);
 			if (error) {
 				return error;
 			}
-			first = b = bufp = bp->b_addr;
-			word = 0;
-		} else {
 			/*
-			 * Go on to the next word in the buffer
+			 * If it worked, return that extent.
+			 */
+			if (r != NULLRTBLOCK) {
+				*rtblock = r;
+				return 0;
+			}
+			/*
+			 * If the "next block to try" returned from the
+			 * allocator is beyond the next bitmap block,
+			 * skip to that bitmap block.
 			 */
-			b++;
+			if (XFS_BITTOBLOCK(mp, n) > i + 1)
+				i = XFS_BITTOBLOCK(mp, n) - 1;
 		}
 	}
 	/*
-	 * If not ending on a word boundary, deal with the last
-	 * (partial) word.
-	 */
-	if ((lastbit = len - i)) {
-		/*
-		 * Compute a mask of relevant bits.
-		 */
-		bit = 0;
-		mask = ((xfs_rtword_t)1 << lastbit) - 1;
-		/*
-		 * Set/clear the active bits.
-		 */
-		if (val)
-			*b |= mask;
-		else
-			*b &= ~mask;
-		b++;
-	}
-	/*
-	 * Log any remaining changed bytes.
+	 * Got nothing, return failure.
 	 */
-	if (b > first)
-		xfs_trans_log_buf(tp, bp, (uint)((char *)first - (char *)bufp),
-			(uint)((char *)b - (char *)bufp - 1));
+	*rtblock = NULLRTBLOCK;
 	return 0;
 }
 
 /*
- * Read and modify the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
+ * Allocate space to the bitmap or summary file, and zero it, for growfs.
  */
 STATIC int				/* error */
-xfs_rtmodify_summary(
+xfs_growfs_rt_alloc(
 	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	int		log,		/* log2 of extent size */
-	xfs_rtblock_t	bbno,		/* bitmap block number */
-	int		delta,		/* change to make to summary info */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+	xfs_extlen_t	oblocks,	/* old count of blocks */
+	xfs_extlen_t	nblocks,	/* new count of blocks */
+	xfs_inode_t	*ip)		/* inode (bitmap/summary) */
 {
-	xfs_buf_t	*bp;		/* buffer for the summary block */
-	int		error;		/* error value */
-	xfs_fsblock_t	sb;		/* summary fsblock */
-	int		so;		/* index into the summary file */
-	xfs_suminfo_t	*sp;		/* pointer to returned data */
+	xfs_fileoff_t	bno;		/* block number in file */
+	xfs_buf_t	*bp;		/* temporary buffer for zeroing */
+	int		committed;	/* transaction committed flag */
+	xfs_daddr_t	d;		/* disk block address */
+	int		error;		/* error return value */
+	xfs_fsblock_t	firstblock;	/* first block allocated in xaction */
+	xfs_bmap_free_t	flist;		/* list of freed blocks */
+	xfs_fsblock_t	fsbno;		/* filesystem block for bno */
+	xfs_bmbt_irec_t	map;		/* block map output */
+	int		nmap;		/* number of block maps */
+	int		resblks;	/* space reservation */
 
 	/*
-	 * Compute entry number in the summary file.
-	 */
-	so = XFS_SUMOFFS(mp, log, bbno);
-	/*
-	 * Compute the block number in the summary file.
-	 */
-	sb = XFS_SUMOFFSTOBLOCK(mp, so);
-	/*
-	 * If we have an old buffer, and the block number matches, use that.
-	 */
-	if (rbpp && *rbpp && *rsb == sb)
-		bp = *rbpp;
-	/*
-	 * Otherwise we have to get the buffer.
+	 * Allocate space to the file, as necessary.
 	 */
-	else {
+	while (oblocks < nblocks) {
+		int		cancelflags = 0;
+		xfs_trans_t	*tp;
+
+		tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ALLOC);
+		resblks = XFS_GROWFSRT_SPACE_RES(mp, nblocks - oblocks);
 		/*
-		 * If there was an old one, get rid of it first.
+		 * Reserve space & log for one extent added to the file.
 		 */
-		if (rbpp && *rbpp)
-			xfs_trans_brelse(tp, *rbpp);
-		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
-		if (error) {
-			return error;
-		}
+		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growdata,
+					  resblks, 0);
+		if (error)
+			goto error_cancel;
+		cancelflags = XFS_TRANS_RELEASE_LOG_RES;
 		/*
-		 * Remember this buffer and block for the next call.
+		 * Lock the inode.
 		 */
-		if (rbpp) {
-			*rbpp = bp;
-			*rsb = sb;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+		xfs_bmap_init(&flist, &firstblock);
+		/*
+		 * Allocate blocks to the bitmap file.
+		 */
+		nmap = 1;
+		cancelflags |= XFS_TRANS_ABORT;
+		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
+					XFS_BMAPI_METADATA, &firstblock,
+					resblks, &map, &nmap, &flist);
+		if (!error && nmap < 1)
+			error = XFS_ERROR(ENOSPC);
+		if (error)
+			goto error_cancel;
+		/*
+		 * Free any blocks freed up in the transaction, then commit.
+		 */
+		error = xfs_bmap_finish(&tp, &flist, &committed);
+		if (error)
+			goto error_cancel;
+		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		if (error)
+			goto error;
+		/*
+		 * Now we need to clear the allocated blocks.
+		 * Do this one block per transaction, to keep it simple.
+		 */
+		cancelflags = 0;
+		for (bno = map.br_startoff, fsbno = map.br_startblock;
+		     bno < map.br_startoff + map.br_blockcount;
+		     bno++, fsbno++) {
+			tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ZERO);
+			/*
+			 * Reserve log for one block zeroing.
+			 */
+			error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtzero,
+						  0, 0);
+			if (error)
+				goto error_cancel;
+			/*
+			 * Lock the bitmap inode.
+			 */
+			xfs_ilock(ip, XFS_ILOCK_EXCL);
+			xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+			/*
+			 * Get a buffer for the block.
+			 */
+			d = XFS_FSB_TO_DADDR(mp, fsbno);
+			bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
+				mp->m_bsize, 0);
+			if (bp == NULL) {
+				error = XFS_ERROR(EIO);
+error_cancel:
+				xfs_trans_cancel(tp, cancelflags);
+				goto error;
+			}
+			memset(bp->b_addr, 0, mp->m_sb.sb_blocksize);
+			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
+			/*
+			 * Commit the transaction.
+			 */
+			error = xfs_trans_commit(tp, 0);
+			if (error)
+				goto error;
 		}
+		/*
+		 * Go on to the next extent, if any.
+		 */
+		oblocks = map.br_startoff + map.br_blockcount;
 	}
-	/*
-	 * Point to the summary information, modify and log it.
-	 */
-	sp = XFS_SUMPTR(mp, bp, so);
-	*sp += delta;
-	xfs_trans_log_buf(tp, bp, (uint)((char *)sp - (char *)bp->b_addr),
-		(uint)((char *)sp - (char *)bp->b_addr + sizeof(*sp) - 1));
 	return 0;
+
+error:
+	return error;
 }
 
 /*
@@ -2128,66 +1230,6 @@ xfs_rtallocate_extent(
 	return 0;
 }
 
-/*
- * Free an extent in the realtime subvolume.  Length is expressed in
- * realtime extents, as is the block number.
- */
-int					/* error */
-xfs_rtfree_extent(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	bno,		/* starting block number to free */
-	xfs_extlen_t	len)		/* length of extent freed */
-{
-	int		error;		/* error value */
-	xfs_mount_t	*mp;		/* file system mount structure */
-	xfs_fsblock_t	sb;		/* summary file block number */
-	xfs_buf_t	*sumbp;		/* summary file block buffer */
-
-	mp = tp->t_mountp;
-
-	ASSERT(mp->m_rbmip->i_itemp != NULL);
-	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
-
-#ifdef DEBUG
-	/*
-	 * Check to see that this whole range is currently allocated.
-	 */
-	{
-		int	stat;		/* result from checking range */
-
-		error = xfs_rtcheck_alloc_range(mp, tp, bno, len, &stat);
-		if (error) {
-			return error;
-		}
-		ASSERT(stat);
-	}
-#endif
-	sumbp = NULL;
-	/*
-	 * Free the range of realtime blocks.
-	 */
-	error = xfs_rtfree_range(mp, tp, bno, len, &sumbp, &sb);
-	if (error) {
-		return error;
-	}
-	/*
-	 * Mark more blocks free in the superblock.
-	 */
-	xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, (long)len);
-	/*
-	 * If we've now freed all the blocks, reset the file sequence
-	 * number to 0.
-	 */
-	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
-	    mp->m_sb.sb_rextents) {
-		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
-			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-		*(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
-		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
-	}
-	return 0;
-}
-
 /*
  * Initialize realtime fields in the mount structure.
  */

fs/xfs/xfs_rtalloc.h

@@ -95,6 +95,30 @@ xfs_growfs_rt(
 	struct xfs_mount	*mp,	/* file system mount structure */
 	xfs_growfs_rt_t		*in);	/* user supplied growfs struct */
 
+/*
+ * From xfs_rtbitmap.c
+ */
+int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp,
+		  xfs_rtblock_t block, int issum, struct xfs_buf **bpp);
+int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp,
+		      xfs_rtblock_t start, xfs_extlen_t len, int val,
+		      xfs_rtblock_t *new, int *stat);
+int xfs_rtfind_back(struct xfs_mount *mp, struct xfs_trans *tp,
+		    xfs_rtblock_t start, xfs_rtblock_t limit,
+		    xfs_rtblock_t *rtblock);
+int xfs_rtfind_forw(struct xfs_mount *mp, struct xfs_trans *tp,
+		    xfs_rtblock_t start, xfs_rtblock_t limit,
+		    xfs_rtblock_t *rtblock);
+int xfs_rtmodify_range(struct xfs_mount *mp, struct xfs_trans *tp,
+		       xfs_rtblock_t start, xfs_extlen_t len, int val);
+int xfs_rtmodify_summary(struct xfs_mount *mp, struct xfs_trans *tp, int log,
+			 xfs_rtblock_t bbno, int delta, xfs_buf_t **rbpp,
+			 xfs_fsblock_t *rsb);
+int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp,
+		     xfs_rtblock_t start, xfs_extlen_t len,
+		     struct xfs_buf **rbpp, xfs_fsblock_t *rsb);
+
+
 #else
 # define xfs_rtallocate_extent(t,b,min,max,l,a,f,p,rb)  (ENOSYS)
 # define xfs_rtfree_extent(t,b,l)                       (ENOSYS)

fs/xfs/xfs_rtbitmap.c

@@ -0,0 +1,974 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_error.h"
+#include "xfs_trans.h"
+#include "xfs_trans_space.h"
+#include "xfs_trace.h"
+#include "xfs_buf.h"
+#include "xfs_icache.h"
+#include "xfs_dinode.h"
+#include "xfs_rtalloc.h"
+
+
+/*
+ * Realtime allocator bitmap functions shared with userspace.
+ */
+
+/*
+ * Get a buffer for the bitmap or summary file block specified.
+ * The buffer is returned read and locked.
+ */
+int
+xfs_rtbuf_get(
+	xfs_mount_t	*mp,		/* file system mount structure */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	block,		/* block number in bitmap or summary */
+	int		issum,		/* is summary not bitmap */
+	xfs_buf_t	**bpp)		/* output: buffer for the block */
+{
+	xfs_buf_t	*bp;		/* block buffer, result */
+	xfs_inode_t	*ip;		/* bitmap or summary inode */
+	xfs_bmbt_irec_t	map;
+	int		nmap = 1;
+	int		error;		/* error value */
+
+	ip = issum ? mp->m_rsumip : mp->m_rbmip;
+
+	error = xfs_bmapi_read(ip, block, 1, &map, &nmap, XFS_DATA_FORK);
+	if (error)
+		return error;
+
+	ASSERT(map.br_startblock != NULLFSBLOCK);
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
+				   mp->m_bsize, 0, &bp, NULL);
+	if (error)
+		return error;
+	ASSERT(!xfs_buf_geterror(bp));
+	*bpp = bp;
+	return 0;
+}
+
+/*
+ * Searching backward from start to limit, find the first block whose
+ * allocated/free state is different from start's.
+ */
+int
+xfs_rtfind_back(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* starting block to look at */
+	xfs_rtblock_t	limit,		/* last block to look at */
+	xfs_rtblock_t	*rtblock)	/* out: start block found */
+{
+	xfs_rtword_t	*b;		/* current word in buffer */
+	int		bit;		/* bit number in the word */
+	xfs_rtblock_t	block;		/* bitmap block number */
+	xfs_buf_t	*bp;		/* buf for the block */
+	xfs_rtword_t	*bufp;		/* starting word in buffer */
+	int		error;		/* error value */
+	xfs_rtblock_t	firstbit;	/* first useful bit in the word */
+	xfs_rtblock_t	i;		/* current bit number rel. to start */
+	xfs_rtblock_t	len;		/* length of inspected area */
+	xfs_rtword_t	mask;		/* mask of relevant bits for value */
+	xfs_rtword_t	want;		/* mask for "good" values */
+	xfs_rtword_t	wdiff;		/* difference from wanted value */
+	int		word;		/* word number in the buffer */
+
+	/*
+	 * Compute and read in starting bitmap block for starting block.
+	 */
+	block = XFS_BITTOBLOCK(mp, start);
+	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
+	if (error) {
+		return error;
+	}
+	bufp = bp->b_addr;
+	/*
+	 * Get the first word's index & point to it.
+	 */
+	word = XFS_BITTOWORD(mp, start);
+	b = &bufp[word];
+	bit = (int)(start & (XFS_NBWORD - 1));
+	len = start - limit + 1;
+	/*
+	 * Compute match value, based on the bit at start: if 1 (free)
+	 * then all-ones, else all-zeroes.
+	 */
+	want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0;
+	/*
+	 * If the starting position is not word-aligned, deal with the
+	 * partial word.
+	 */
+	if (bit < XFS_NBWORD - 1) {
+		/*
+		 * Calculate first (leftmost) bit number to look at,
+		 * and mask for all the relevant bits in this word.
+		 */
+		firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0);
+		mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) <<
+			firstbit;
+		/*
+		 * Calculate the difference between the value there
+		 * and what we're looking for.
+		 */
+		if ((wdiff = (*b ^ want) & mask)) {
+			/*
+			 * Different.  Mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i = bit - XFS_RTHIBIT(wdiff);
+			*rtblock = start - i + 1;
+			return 0;
+		}
+		i = bit - firstbit + 1;
+		/*
+		 * Go on to previous block if that's where the previous word is
+		 * and we need the previous word.
+		 */
+		if (--word == -1 && i < len) {
+			/*
+			 * If done with this block, get the previous one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, --block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			bufp = bp->b_addr;
+			word = XFS_BLOCKWMASK(mp);
+			b = &bufp[word];
+		} else {
+			/*
+			 * Go on to the previous word in the buffer.
+			 */
+			b--;
+		}
+	} else {
+		/*
+		 * Starting on a word boundary, no partial word.
+		 */
+		i = 0;
+	}
+	/*
+	 * Loop over whole words in buffers.  When we use up one buffer
+	 * we move on to the previous one.
+	 */
+	while (len - i >= XFS_NBWORD) {
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = *b ^ want)) {
+			/*
+			 * Different, mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			*rtblock = start - i + 1;
+			return 0;
+		}
+		i += XFS_NBWORD;
+		/*
+		 * Go on to previous block if that's where the previous word is
+		 * and we need the previous word.
+		 */
+		if (--word == -1 && i < len) {
+			/*
+			 * If done with this block, get the previous one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, --block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			bufp = bp->b_addr;
+			word = XFS_BLOCKWMASK(mp);
+			b = &bufp[word];
+		} else {
+			/*
+			 * Go on to the previous word in the buffer.
+			 */
+			b--;
+		}
+	}
+	/*
+	 * If not ending on a word boundary, deal with the last
+	 * (partial) word.
+	 */
+	if (len - i) {
+		/*
+		 * Calculate first (leftmost) bit number to look at,
+		 * and mask for all the relevant bits in this word.
+		 */
+		firstbit = XFS_NBWORD - (len - i);
+		mask = (((xfs_rtword_t)1 << (len - i)) - 1) << firstbit;
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = (*b ^ want) & mask)) {
+			/*
+			 * Different, mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			*rtblock = start - i + 1;
+			return 0;
+		} else
+			i = len;
+	}
+	/*
+	 * No match, return that we scanned the whole area.
+	 */
+	xfs_trans_brelse(tp, bp);
+	*rtblock = start - i + 1;
+	return 0;
+}
+
+/*
+ * Searching forward from start to limit, find the first block whose
+ * allocated/free state is different from start's.
+ */
+int
+xfs_rtfind_forw(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* starting block to look at */
+	xfs_rtblock_t	limit,		/* last block to look at */
+	xfs_rtblock_t	*rtblock)	/* out: start block found */
+{
+	xfs_rtword_t	*b;		/* current word in buffer */
+	int		bit;		/* bit number in the word */
+	xfs_rtblock_t	block;		/* bitmap block number */
+	xfs_buf_t	*bp;		/* buf for the block */
+	xfs_rtword_t	*bufp;		/* starting word in buffer */
+	int		error;		/* error value */
+	xfs_rtblock_t	i;		/* current bit number rel. to start */
+	xfs_rtblock_t	lastbit;	/* last useful bit in the word */
+	xfs_rtblock_t	len;		/* length of inspected area */
+	xfs_rtword_t	mask;		/* mask of relevant bits for value */
+	xfs_rtword_t	want;		/* mask for "good" values */
+	xfs_rtword_t	wdiff;		/* difference from wanted value */
+	int		word;		/* word number in the buffer */
+
+	/*
+	 * Compute and read in starting bitmap block for starting block.
+	 */
+	block = XFS_BITTOBLOCK(mp, start);
+	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
+	if (error) {
+		return error;
+	}
+	bufp = bp->b_addr;
+	/*
+	 * Get the first word's index & point to it.
+	 */
+	word = XFS_BITTOWORD(mp, start);
+	b = &bufp[word];
+	bit = (int)(start & (XFS_NBWORD - 1));
+	len = limit - start + 1;
+	/*
+	 * Compute match value, based on the bit at start: if 1 (free)
+	 * then all-ones, else all-zeroes.
+	 */
+	want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0;
+	/*
+	 * If the starting position is not word-aligned, deal with the
+	 * partial word.
+	 */
+	if (bit) {
+		/*
+		 * Calculate last (rightmost) bit number to look at,
+		 * and mask for all the relevant bits in this word.
+		 */
+		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
+		/*
+		 * Calculate the difference between the value there
+		 * and what we're looking for.
+		 */
+		if ((wdiff = (*b ^ want) & mask)) {
+			/*
+			 * Different.  Mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i = XFS_RTLOBIT(wdiff) - bit;
+			*rtblock = start + i - 1;
+			return 0;
+		}
+		i = lastbit - bit;
+		/*
+		 * Go on to next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * If done with this block, get the previous one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the previous word in the buffer.
+			 */
+			b++;
+		}
+	} else {
+		/*
+		 * Starting on a word boundary, no partial word.
+		 */
+		i = 0;
+	}
+	/*
+	 * Loop over whole words in buffers.  When we use up one buffer
+	 * we move on to the next one.
+	 */
+	while (len - i >= XFS_NBWORD) {
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = *b ^ want)) {
+			/*
+			 * Different, mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_RTLOBIT(wdiff);
+			*rtblock = start + i - 1;
+			return 0;
+		}
+		i += XFS_NBWORD;
+		/*
+		 * Go on to next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * If done with this block, get the next one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the next word in the buffer.
+			 */
+			b++;
+		}
+	}
+	/*
+	 * If not ending on a word boundary, deal with the last
+	 * (partial) word.
+	 */
+	if ((lastbit = len - i)) {
+		/*
+		 * Calculate mask for all the relevant bits in this word.
+		 */
+		mask = ((xfs_rtword_t)1 << lastbit) - 1;
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = (*b ^ want) & mask)) {
+			/*
+			 * Different, mark where we are and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_RTLOBIT(wdiff);
+			*rtblock = start + i - 1;
+			return 0;
+		} else
+			i = len;
+	}
+	/*
+	 * No match, return that we scanned the whole area.
+	 */
+	xfs_trans_brelse(tp, bp);
+	*rtblock = start + i - 1;
+	return 0;
+}
+
+/*
+ * Read and modify the summary information for a given extent size,
+ * bitmap block combination.
+ * Keeps track of a current summary block, so we don't keep reading
+ * it from the buffer cache.
+ */
+int
+xfs_rtmodify_summary(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	int		log,		/* log2 of extent size */
+	xfs_rtblock_t	bbno,		/* bitmap block number */
+	int		delta,		/* change to make to summary info */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+{
+	xfs_buf_t	*bp;		/* buffer for the summary block */
+	int		error;		/* error value */
+	xfs_fsblock_t	sb;		/* summary fsblock */
+	int		so;		/* index into the summary file */
+	xfs_suminfo_t	*sp;		/* pointer to returned data */
+
+	/*
+	 * Compute entry number in the summary file.
+	 */
+	so = XFS_SUMOFFS(mp, log, bbno);
+	/*
+	 * Compute the block number in the summary file.
+	 */
+	sb = XFS_SUMOFFSTOBLOCK(mp, so);
+	/*
+	 * If we have an old buffer, and the block number matches, use that.
+	 */
+	if (rbpp && *rbpp && *rsb == sb)
+		bp = *rbpp;
+	/*
+	 * Otherwise we have to get the buffer.
+	 */
+	else {
+		/*
+		 * If there was an old one, get rid of it first.
+		 */
+		if (rbpp && *rbpp)
+			xfs_trans_brelse(tp, *rbpp);
+		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
+		if (error) {
+			return error;
+		}
+		/*
+		 * Remember this buffer and block for the next call.
+		 */
+		if (rbpp) {
+			*rbpp = bp;
+			*rsb = sb;
+		}
+	}
+	/*
+	 * Point to the summary information, modify and log it.
+	 */
+	sp = XFS_SUMPTR(mp, bp, so);
+	*sp += delta;
+	xfs_trans_log_buf(tp, bp, (uint)((char *)sp - (char *)bp->b_addr),
+		(uint)((char *)sp - (char *)bp->b_addr + sizeof(*sp) - 1));
+	return 0;
+}
+
+/*
+ * Set the given range of bitmap bits to the given value.
+ * Do whatever I/O and logging is required.
+ */
+int
+xfs_rtmodify_range(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* starting block to modify */
+	xfs_extlen_t	len,		/* length of extent to modify */
+	int		val)		/* 1 for free, 0 for allocated */
+{
+	xfs_rtword_t	*b;		/* current word in buffer */
+	int		bit;		/* bit number in the word */
+	xfs_rtblock_t	block;		/* bitmap block number */
+	xfs_buf_t	*bp;		/* buf for the block */
+	xfs_rtword_t	*bufp;		/* starting word in buffer */
+	int		error;		/* error value */
+	xfs_rtword_t	*first;		/* first used word in the buffer */
+	int		i;		/* current bit number rel. to start */
+	int		lastbit;	/* last useful bit in word */
+	xfs_rtword_t	mask;		/* mask o frelevant bits for value */
+	int		word;		/* word number in the buffer */
+
+	/*
+	 * Compute starting bitmap block number.
+	 */
+	block = XFS_BITTOBLOCK(mp, start);
+	/*
+	 * Read the bitmap block, and point to its data.
+	 */
+	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
+	if (error) {
+		return error;
+	}
+	bufp = bp->b_addr;
+	/*
+	 * Compute the starting word's address, and starting bit.
+	 */
+	word = XFS_BITTOWORD(mp, start);
+	first = b = &bufp[word];
+	bit = (int)(start & (XFS_NBWORD - 1));
+	/*
+	 * 0 (allocated) => all zeroes; 1 (free) => all ones.
+	 */
+	val = -val;
+	/*
+	 * If not starting on a word boundary, deal with the first
+	 * (partial) word.
+	 */
+	if (bit) {
+		/*
+		 * Compute first bit not changed and mask of relevant bits.
+		 */
+		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
+		/*
+		 * Set/clear the active bits.
+		 */
+		if (val)
+			*b |= mask;
+		else
+			*b &= ~mask;
+		i = lastbit - bit;
+		/*
+		 * Go on to the next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * Log the changed part of this block.
+			 * Get the next one.
+			 */
+			xfs_trans_log_buf(tp, bp,
+				(uint)((char *)first - (char *)bufp),
+				(uint)((char *)b - (char *)bufp));
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			first = b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the next word in the buffer
+			 */
+			b++;
+		}
+	} else {
+		/*
+		 * Starting on a word boundary, no partial word.
+		 */
+		i = 0;
+	}
+	/*
+	 * Loop over whole words in buffers.  When we use up one buffer
+	 * we move on to the next one.
+	 */
+	while (len - i >= XFS_NBWORD) {
+		/*
+		 * Set the word value correctly.
+		 */
+		*b = val;
+		i += XFS_NBWORD;
+		/*
+		 * Go on to the next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * Log the changed part of this block.
+			 * Get the next one.
+			 */
+			xfs_trans_log_buf(tp, bp,
+				(uint)((char *)first - (char *)bufp),
+				(uint)((char *)b - (char *)bufp));
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			first = b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the next word in the buffer
+			 */
+			b++;
+		}
+	}
+	/*
+	 * If not ending on a word boundary, deal with the last
+	 * (partial) word.
+	 */
+	if ((lastbit = len - i)) {
+		/*
+		 * Compute a mask of relevant bits.
+		 */
+		bit = 0;
+		mask = ((xfs_rtword_t)1 << lastbit) - 1;
+		/*
+		 * Set/clear the active bits.
+		 */
+		if (val)
+			*b |= mask;
+		else
+			*b &= ~mask;
+		b++;
+	}
+	/*
+	 * Log any remaining changed bytes.
+	 */
+	if (b > first)
+		xfs_trans_log_buf(tp, bp, (uint)((char *)first - (char *)bufp),
+			(uint)((char *)b - (char *)bufp - 1));
+	return 0;
+}
+
+/*
+ * Mark an extent specified by start and len freed.
+ * Updates all the summary information as well as the bitmap.
+ */
+int
+xfs_rtfree_range(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* starting block to free */
+	xfs_extlen_t	len,		/* length to free */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+{
+	xfs_rtblock_t	end;		/* end of the freed extent */
+	int		error;		/* error value */
+	xfs_rtblock_t	postblock;	/* first block freed > end */
+	xfs_rtblock_t	preblock;	/* first block freed < start */
+
+	end = start + len - 1;
+	/*
+	 * Modify the bitmap to mark this extent freed.
+	 */
+	error = xfs_rtmodify_range(mp, tp, start, len, 1);
+	if (error) {
+		return error;
+	}
+	/*
+	 * Assume we're freeing out of the middle of an allocated extent.
+	 * We need to find the beginning and end of the extent so we can
+	 * properly update the summary.
+	 */
+	error = xfs_rtfind_back(mp, tp, start, 0, &preblock);
+	if (error) {
+		return error;
+	}
+	/*
+	 * Find the next allocated block (end of allocated extent).
+	 */
+	error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
+		&postblock);
+	if (error)
+		return error;
+	/*
+	 * If there are blocks not being freed at the front of the
+	 * old extent, add summary data for them to be allocated.
+	 */
+	if (preblock < start) {
+		error = xfs_rtmodify_summary(mp, tp,
+			XFS_RTBLOCKLOG(start - preblock),
+			XFS_BITTOBLOCK(mp, preblock), -1, rbpp, rsb);
+		if (error) {
+			return error;
+		}
+	}
+	/*
+	 * If there are blocks not being freed at the end of the
+	 * old extent, add summary data for them to be allocated.
+	 */
+	if (postblock > end) {
+		error = xfs_rtmodify_summary(mp, tp,
+			XFS_RTBLOCKLOG(postblock - end),
+			XFS_BITTOBLOCK(mp, end + 1), -1, rbpp, rsb);
+		if (error) {
+			return error;
+		}
+	}
+	/*
+	 * Increment the summary information corresponding to the entire
+	 * (new) free extent.
+	 */
+	error = xfs_rtmodify_summary(mp, tp,
+		XFS_RTBLOCKLOG(postblock + 1 - preblock),
+		XFS_BITTOBLOCK(mp, preblock), 1, rbpp, rsb);
+	return error;
+}
+
+/*
+ * Check that the given range is either all allocated (val = 0) or
+ * all free (val = 1).
+ */
+int
+xfs_rtcheck_range(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	start,		/* starting block number of extent */
+	xfs_extlen_t	len,		/* length of extent */
+	int		val,		/* 1 for free, 0 for allocated */
+	xfs_rtblock_t	*new,		/* out: first block not matching */
+	int		*stat)		/* out: 1 for matches, 0 for not */
+{
+	xfs_rtword_t	*b;		/* current word in buffer */
+	int		bit;		/* bit number in the word */
+	xfs_rtblock_t	block;		/* bitmap block number */
+	xfs_buf_t	*bp;		/* buf for the block */
+	xfs_rtword_t	*bufp;		/* starting word in buffer */
+	int		error;		/* error value */
+	xfs_rtblock_t	i;		/* current bit number rel. to start */
+	xfs_rtblock_t	lastbit;	/* last useful bit in word */
+	xfs_rtword_t	mask;		/* mask of relevant bits for value */
+	xfs_rtword_t	wdiff;		/* difference from wanted value */
+	int		word;		/* word number in the buffer */
+
+	/*
+	 * Compute starting bitmap block number
+	 */
+	block = XFS_BITTOBLOCK(mp, start);
+	/*
+	 * Read the bitmap block.
+	 */
+	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
+	if (error) {
+		return error;
+	}
+	bufp = bp->b_addr;
+	/*
+	 * Compute the starting word's address, and starting bit.
+	 */
+	word = XFS_BITTOWORD(mp, start);
+	b = &bufp[word];
+	bit = (int)(start & (XFS_NBWORD - 1));
+	/*
+	 * 0 (allocated) => all zero's; 1 (free) => all one's.
+	 */
+	val = -val;
+	/*
+	 * If not starting on a word boundary, deal with the first
+	 * (partial) word.
+	 */
+	if (bit) {
+		/*
+		 * Compute first bit not examined.
+		 */
+		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		/*
+		 * Mask of relevant bits.
+		 */
+		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = (*b ^ val) & mask)) {
+			/*
+			 * Different, compute first wrong bit and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i = XFS_RTLOBIT(wdiff) - bit;
+			*new = start + i;
+			*stat = 0;
+			return 0;
+		}
+		i = lastbit - bit;
+		/*
+		 * Go on to next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * If done with this block, get the next one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the next word in the buffer.
+			 */
+			b++;
+		}
+	} else {
+		/*
+		 * Starting on a word boundary, no partial word.
+		 */
+		i = 0;
+	}
+	/*
+	 * Loop over whole words in buffers.  When we use up one buffer
+	 * we move on to the next one.
+	 */
+	while (len - i >= XFS_NBWORD) {
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = *b ^ val)) {
+			/*
+			 * Different, compute first wrong bit and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_RTLOBIT(wdiff);
+			*new = start + i;
+			*stat = 0;
+			return 0;
+		}
+		i += XFS_NBWORD;
+		/*
+		 * Go on to next block if that's where the next word is
+		 * and we need the next word.
+		 */
+		if (++word == XFS_BLOCKWSIZE(mp) && i < len) {
+			/*
+			 * If done with this block, get the next one.
+			 */
+			xfs_trans_brelse(tp, bp);
+			error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp);
+			if (error) {
+				return error;
+			}
+			b = bufp = bp->b_addr;
+			word = 0;
+		} else {
+			/*
+			 * Go on to the next word in the buffer.
+			 */
+			b++;
+		}
+	}
+	/*
+	 * If not ending on a word boundary, deal with the last
+	 * (partial) word.
+	 */
+	if ((lastbit = len - i)) {
+		/*
+		 * Mask of relevant bits.
+		 */
+		mask = ((xfs_rtword_t)1 << lastbit) - 1;
+		/*
+		 * Compute difference between actual and desired value.
+		 */
+		if ((wdiff = (*b ^ val) & mask)) {
+			/*
+			 * Different, compute first wrong bit and return.
+			 */
+			xfs_trans_brelse(tp, bp);
+			i += XFS_RTLOBIT(wdiff);
+			*new = start + i;
+			*stat = 0;
+			return 0;
+		} else
+			i = len;
+	}
+	/*
+	 * Successful, return.
+	 */
+	xfs_trans_brelse(tp, bp);
+	*new = start + i;
+	*stat = 1;
+	return 0;
+}
+
+#ifdef DEBUG
+/*
+ * Check that the given extent (block range) is allocated already.
+ */
+STATIC int				/* error */
+xfs_rtcheck_alloc_range(
+	xfs_mount_t	*mp,		/* file system mount point */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	bno,		/* starting block number of extent */
+	xfs_extlen_t	len)		/* length of extent */
+{
+	xfs_rtblock_t	new;		/* dummy for xfs_rtcheck_range */
+	int		stat;
+	int		error;
+
+	error = xfs_rtcheck_range(mp, tp, bno, len, 0, &new, &stat);
+	if (error)
+		return error;
+	ASSERT(stat);
+	return 0;
+}
+#else
+#define xfs_rtcheck_alloc_range(m,t,b,l)	(0)
+#endif
+/*
+ * Free an extent in the realtime subvolume.  Length is expressed in
+ * realtime extents, as is the block number.
+ */
+int					/* error */
+xfs_rtfree_extent(
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_rtblock_t	bno,		/* starting block number to free */
+	xfs_extlen_t	len)		/* length of extent freed */
+{
+	int		error;		/* error value */
+	xfs_mount_t	*mp;		/* file system mount structure */
+	xfs_fsblock_t	sb;		/* summary file block number */
+	xfs_buf_t	*sumbp = NULL;	/* summary file block buffer */
+
+	mp = tp->t_mountp;
+
+	ASSERT(mp->m_rbmip->i_itemp != NULL);
+	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
+
+	error = xfs_rtcheck_alloc_range(mp, tp, bno, len);
+	if (error)
+		return error;
+
+	/*
+	 * Free the range of realtime blocks.
+	 */
+	error = xfs_rtfree_range(mp, tp, bno, len, &sumbp, &sb);
+	if (error) {
+		return error;
+	}
+	/*
+	 * Mark more blocks free in the superblock.
+	 */
+	xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, (long)len);
+	/*
+	 * If we've now freed all the blocks, reset the file sequence
+	 * number to 0.
+	 */
+	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
+	    mp->m_sb.sb_rextents) {
+		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
+			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+		*(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
+		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
+	}
+	return 0;
+}
+

fs/xfs/xfs_sb.c

@@ -17,34 +17,26 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
-#include "xfs_dir2.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
 #include "xfs_inode.h"
-#include "xfs_btree.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
-#include "xfs_rtalloc.h"
-#include "xfs_bmap.h"
 #include "xfs_error.h"
-#include "xfs_quota.h"
-#include "xfs_fsops.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_dinode.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -249,13 +241,13 @@ xfs_mount_validate_sb(
 	if (xfs_sb_version_has_pquotino(sbp)) {
 		if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) {
 			xfs_notice(mp,
-			   "Version 5 of Super block has XFS_OQUOTA bits.\n");
+			   "Version 5 of Super block has XFS_OQUOTA bits.");
 			return XFS_ERROR(EFSCORRUPTED);
 		}
 	} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
 				XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
 			xfs_notice(mp,
-"Superblock earlier than Version 5 has XFS_[PQ]UOTA_{ENFD|CHKD} bits.\n");
+"Superblock earlier than Version 5 has XFS_[PQ]UOTA_{ENFD|CHKD} bits.");
 			return XFS_ERROR(EFSCORRUPTED);
 	}
 
@@ -596,6 +588,11 @@ xfs_sb_verify(
  * single bit error could clear the feature bit and unused parts of the
  * superblock are supposed to be zero. Hence a non-null crc field indicates that
  * we've potentially lost a feature bit and we should check it anyway.
+ *
+ * However, past bugs (i.e. in growfs) left non-zeroed regions beyond the
+ * last field in V4 secondary superblocks.  So for secondary superblocks,
+ * we are more forgiving, and ignore CRC failures if the primary doesn't
+ * indicate that the fs version is V5.
  */
 static void
 xfs_sb_read_verify(
@@ -616,16 +613,21 @@ xfs_sb_read_verify(
 
 		if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
 				      offsetof(struct xfs_sb, sb_crc))) {
-			error = EFSCORRUPTED;
-			goto out_error;
+			/* Only fail bad secondaries on a known V5 filesystem */
+			if (bp->b_bn != XFS_SB_DADDR &&
+			    xfs_sb_version_hascrc(&mp->m_sb)) {
+				error = EFSCORRUPTED;
+				goto out_error;
+			}
 		}
 	}
 	error = xfs_sb_verify(bp, true);
 
 out_error:
 	if (error) {
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-				     mp, bp->b_addr);
+		if (error != EWRONGFS)
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
+					     mp, bp->b_addr);
 		xfs_buf_ioerror(bp, error);
 	}
 }

fs/xfs/xfs_sb.h

@@ -699,7 +699,4 @@ extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
 extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
 
-extern const struct xfs_buf_ops xfs_sb_buf_ops;
-extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
-
 #endif	/* __XFS_SB_H__ */

fs/xfs/xfs_shared.h

@@ -0,0 +1,244 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_SHARED_H__
+#define __XFS_SHARED_H__
+
+/*
+ * Definitions shared between kernel and userspace that don't fit into any other
+ * header file that is shared with userspace.
+ */
+struct xfs_ifork;
+struct xfs_buf;
+struct xfs_buf_ops;
+struct xfs_mount;
+struct xfs_trans;
+struct xfs_inode;
+
+/*
+ * Buffer verifier operations are widely used, including userspace tools
+ */
+extern const struct xfs_buf_ops xfs_agf_buf_ops;
+extern const struct xfs_buf_ops xfs_agi_buf_ops;
+extern const struct xfs_buf_ops xfs_agf_buf_ops;
+extern const struct xfs_buf_ops xfs_agfl_buf_ops;
+extern const struct xfs_buf_ops xfs_allocbt_buf_ops;
+extern const struct xfs_buf_ops xfs_attr3_leaf_buf_ops;
+extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops;
+extern const struct xfs_buf_ops xfs_bmbt_buf_ops;
+extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+extern const struct xfs_buf_ops xfs_agi_buf_ops;
+extern const struct xfs_buf_ops xfs_inobt_buf_ops;
+extern const struct xfs_buf_ops xfs_inode_buf_ops;
+extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_sb_buf_ops;
+extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
+extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+
+/*
+ * Transaction types.  Used to distinguish types of buffers. These never reach
+ * the log.
+ */
+#define XFS_TRANS_SETATTR_NOT_SIZE	1
+#define XFS_TRANS_SETATTR_SIZE		2
+#define XFS_TRANS_INACTIVE		3
+#define XFS_TRANS_CREATE		4
+#define XFS_TRANS_CREATE_TRUNC		5
+#define XFS_TRANS_TRUNCATE_FILE		6
+#define XFS_TRANS_REMOVE		7
+#define XFS_TRANS_LINK			8
+#define XFS_TRANS_RENAME		9
+#define XFS_TRANS_MKDIR			10
+#define XFS_TRANS_RMDIR			11
+#define XFS_TRANS_SYMLINK		12
+#define XFS_TRANS_SET_DMATTRS		13
+#define XFS_TRANS_GROWFS		14
+#define XFS_TRANS_STRAT_WRITE		15
+#define XFS_TRANS_DIOSTRAT		16
+/* 17 was XFS_TRANS_WRITE_SYNC */
+#define	XFS_TRANS_WRITEID		18
+#define	XFS_TRANS_ADDAFORK		19
+#define	XFS_TRANS_ATTRINVAL		20
+#define	XFS_TRANS_ATRUNCATE		21
+#define	XFS_TRANS_ATTR_SET		22
+#define	XFS_TRANS_ATTR_RM		23
+#define	XFS_TRANS_ATTR_FLAG		24
+#define	XFS_TRANS_CLEAR_AGI_BUCKET	25
+#define XFS_TRANS_QM_SBCHANGE		26
+/*
+ * Dummy entries since we use the transaction type to index into the
+ * trans_type[] in xlog_recover_print_trans_head()
+ */
+#define XFS_TRANS_DUMMY1		27
+#define XFS_TRANS_DUMMY2		28
+#define XFS_TRANS_QM_QUOTAOFF		29
+#define XFS_TRANS_QM_DQALLOC		30
+#define XFS_TRANS_QM_SETQLIM		31
+#define XFS_TRANS_QM_DQCLUSTER		32
+#define XFS_TRANS_QM_QINOCREATE		33
+#define XFS_TRANS_QM_QUOTAOFF_END	34
+#define XFS_TRANS_SB_UNIT		35
+#define XFS_TRANS_FSYNC_TS		36
+#define	XFS_TRANS_GROWFSRT_ALLOC	37
+#define	XFS_TRANS_GROWFSRT_ZERO		38
+#define	XFS_TRANS_GROWFSRT_FREE		39
+#define	XFS_TRANS_SWAPEXT		40
+#define	XFS_TRANS_SB_COUNT		41
+#define	XFS_TRANS_CHECKPOINT		42
+#define	XFS_TRANS_ICREATE		43
+#define	XFS_TRANS_TYPE_MAX		43
+/* new transaction types need to be reflected in xfs_logprint(8) */
+
+#define XFS_TRANS_TYPES \
+	{ XFS_TRANS_SETATTR_NOT_SIZE,	"SETATTR_NOT_SIZE" }, \
+	{ XFS_TRANS_SETATTR_SIZE,	"SETATTR_SIZE" }, \
+	{ XFS_TRANS_INACTIVE,		"INACTIVE" }, \
+	{ XFS_TRANS_CREATE,		"CREATE" }, \
+	{ XFS_TRANS_CREATE_TRUNC,	"CREATE_TRUNC" }, \
+	{ XFS_TRANS_TRUNCATE_FILE,	"TRUNCATE_FILE" }, \
+	{ XFS_TRANS_REMOVE,		"REMOVE" }, \
+	{ XFS_TRANS_LINK,		"LINK" }, \
+	{ XFS_TRANS_RENAME,		"RENAME" }, \
+	{ XFS_TRANS_MKDIR,		"MKDIR" }, \
+	{ XFS_TRANS_RMDIR,		"RMDIR" }, \
+	{ XFS_TRANS_SYMLINK,		"SYMLINK" }, \
+	{ XFS_TRANS_SET_DMATTRS,	"SET_DMATTRS" }, \
+	{ XFS_TRANS_GROWFS,		"GROWFS" }, \
+	{ XFS_TRANS_STRAT_WRITE,	"STRAT_WRITE" }, \
+	{ XFS_TRANS_DIOSTRAT,		"DIOSTRAT" }, \
+	{ XFS_TRANS_WRITEID,		"WRITEID" }, \
+	{ XFS_TRANS_ADDAFORK,		"ADDAFORK" }, \
+	{ XFS_TRANS_ATTRINVAL,		"ATTRINVAL" }, \
+	{ XFS_TRANS_ATRUNCATE,		"ATRUNCATE" }, \
+	{ XFS_TRANS_ATTR_SET,		"ATTR_SET" }, \
+	{ XFS_TRANS_ATTR_RM,		"ATTR_RM" }, \
+	{ XFS_TRANS_ATTR_FLAG,		"ATTR_FLAG" }, \
+	{ XFS_TRANS_CLEAR_AGI_BUCKET,	"CLEAR_AGI_BUCKET" }, \
+	{ XFS_TRANS_QM_SBCHANGE,	"QM_SBCHANGE" }, \
+	{ XFS_TRANS_QM_QUOTAOFF,	"QM_QUOTAOFF" }, \
+	{ XFS_TRANS_QM_DQALLOC,		"QM_DQALLOC" }, \
+	{ XFS_TRANS_QM_SETQLIM,		"QM_SETQLIM" }, \
+	{ XFS_TRANS_QM_DQCLUSTER,	"QM_DQCLUSTER" }, \
+	{ XFS_TRANS_QM_QINOCREATE,	"QM_QINOCREATE" }, \
+	{ XFS_TRANS_QM_QUOTAOFF_END,	"QM_QOFF_END" }, \
+	{ XFS_TRANS_SB_UNIT,		"SB_UNIT" }, \
+	{ XFS_TRANS_FSYNC_TS,		"FSYNC_TS" }, \
+	{ XFS_TRANS_GROWFSRT_ALLOC,	"GROWFSRT_ALLOC" }, \
+	{ XFS_TRANS_GROWFSRT_ZERO,	"GROWFSRT_ZERO" }, \
+	{ XFS_TRANS_GROWFSRT_FREE,	"GROWFSRT_FREE" }, \
+	{ XFS_TRANS_SWAPEXT,		"SWAPEXT" }, \
+	{ XFS_TRANS_SB_COUNT,		"SB_COUNT" }, \
+	{ XFS_TRANS_CHECKPOINT,		"CHECKPOINT" }, \
+	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
+	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
+	{ XLOG_UNMOUNT_REC_TYPE,	"UNMOUNT" }
+
+/*
+ * This structure is used to track log items associated with
+ * a transaction.  It points to the log item and keeps some
+ * flags to track the state of the log item.  It also tracks
+ * the amount of space needed to log the item it describes
+ * once we get to commit processing (see xfs_trans_commit()).
+ */
+struct xfs_log_item_desc {
+	struct xfs_log_item	*lid_item;
+	struct list_head	lid_trans;
+	unsigned char		lid_flags;
+};
+
+#define XFS_LID_DIRTY		0x1
+
+/* log size calculation functions */
+int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
+int	xfs_log_calc_minimum_size(struct xfs_mount *);
+
+
+/*
+ * Values for t_flags.
+ */
+#define	XFS_TRANS_DIRTY		0x01	/* something needs to be logged */
+#define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
+#define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
+#define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
+#define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
+#define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
+#define XFS_TRANS_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
+/*
+ * Values for call flags parameter.
+ */
+#define	XFS_TRANS_RELEASE_LOG_RES	0x4
+#define	XFS_TRANS_ABORT			0x8
+
+/*
+ * Field values for xfs_trans_mod_sb.
+ */
+#define	XFS_TRANS_SB_ICOUNT		0x00000001
+#define	XFS_TRANS_SB_IFREE		0x00000002
+#define	XFS_TRANS_SB_FDBLOCKS		0x00000004
+#define	XFS_TRANS_SB_RES_FDBLOCKS	0x00000008
+#define	XFS_TRANS_SB_FREXTENTS		0x00000010
+#define	XFS_TRANS_SB_RES_FREXTENTS	0x00000020
+#define	XFS_TRANS_SB_DBLOCKS		0x00000040
+#define	XFS_TRANS_SB_AGCOUNT		0x00000080
+#define	XFS_TRANS_SB_IMAXPCT		0x00000100
+#define	XFS_TRANS_SB_REXTSIZE		0x00000200
+#define	XFS_TRANS_SB_RBMBLOCKS		0x00000400
+#define	XFS_TRANS_SB_RBLOCKS		0x00000800
+#define	XFS_TRANS_SB_REXTENTS		0x00001000
+#define	XFS_TRANS_SB_REXTSLOG		0x00002000
+
+/*
+ * Here we centralize the specification of XFS meta-data buffer reference count
+ * values.  This determines how hard the buffer cache tries to hold onto the
+ * buffer.
+ */
+#define	XFS_AGF_REF		4
+#define	XFS_AGI_REF		4
+#define	XFS_AGFL_REF		3
+#define	XFS_INO_BTREE_REF	3
+#define	XFS_ALLOC_BTREE_REF	2
+#define	XFS_BMAP_BTREE_REF	2
+#define	XFS_DIR_BTREE_REF	2
+#define	XFS_INO_REF		2
+#define	XFS_ATTR_BTREE_REF	1
+#define	XFS_DQUOT_REF		1
+
+/*
+ * Flags for xfs_trans_ichgtime().
+ */
+#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
+#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
+#define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
+
+
+/*
+ * Symlink decoding/encoding functions
+ */
+int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
+int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
+				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+
+#endif /* __XFS_SHARED_H__ */

fs/xfs/xfs_super.c

@@ -17,34 +17,26 @@
  */
 
 #include "xfs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
-#include "xfs_log.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_alloc.h"
-#include "xfs_quota.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
-#include "xfs_ialloc.h"
 #include "xfs_bmap.h"
-#include "xfs_rtalloc.h"
+#include "xfs_alloc.h"
 #include "xfs_error.h"
-#include "xfs_itable.h"
 #include "xfs_fsops.h"
-#include "xfs_attr.h"
+#include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_log.h"
 #include "xfs_log_priv.h"
-#include "xfs_trans_priv.h"
-#include "xfs_filestream.h"
 #include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
 #include "xfs_dir2.h"
 #include "xfs_extfree_item.h"
 #include "xfs_mru_cache.h"
@@ -52,6 +44,9 @@
 #include "xfs_icache.h"
 #include "xfs_trace.h"
 #include "xfs_icreate_item.h"
+#include "xfs_dinode.h"
+#include "xfs_filestream.h"
+#include "xfs_quota.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -946,10 +941,6 @@ xfs_fs_destroy_inode(
 
 	XFS_STATS_INC(vn_reclaim);
 
-	/* bad inode, get out here ASAP */
-	if (is_bad_inode(inode))
-		goto out_reclaim;
-
 	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
 
 	/*
@@ -965,7 +956,6 @@ xfs_fs_destroy_inode(
 	 * this more efficiently than we can here, so simply let background
 	 * reclaim tear down all inodes.
 	 */
-out_reclaim:
 	xfs_inode_set_reclaim_tag(ip);
 }
 
@@ -1165,7 +1155,7 @@ xfs_restore_resvblks(struct xfs_mount *mp)
  * Note: xfs_log_quiesce() stops background log work - the callers must ensure
  * it is started again when appropriate.
  */
-void
+static void
 xfs_quiesce_attr(
 	struct xfs_mount	*mp)
 {
@@ -1246,7 +1236,7 @@ xfs_fs_remount(
 			 */
 #if 0
 			xfs_info(mp,
-		"mount option \"%s\" not supported for remount\n", p);
+		"mount option \"%s\" not supported for remount", p);
 			return -EINVAL;
 #else
 			break;
@@ -1491,10 +1481,6 @@ xfs_fs_fill_super(
 		error = ENOENT;
 		goto out_unmount;
 	}
-	if (is_bad_inode(root)) {
-		error = EINVAL;
-		goto out_unmount;
-	}
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		error = ENOMEM;