Merge tag 'for-linus-v3.6-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs update from Ben Myers:
 "Numerous cleanups and several bug fixes.  Here are some highlights:

   - Discontiguous directory buffer support
   - Inode allocator refactoring
   - Removal of the IO lock in inode reclaim
   - Implementation of .update_time
   - Fix for handling of EOF in xfs_vm_writepage
   - Fix for races in xfsaild, and idle mode is re-enabled
   - Fix for a crash in xfs_buf completion handlers on unmount."

Fix up trivial conflicts in fs/xfs/{xfs_buf.c,xfs_log.c,xfs_log_priv.h}
due to duplicate patches that had already been merged for 3.5.

* tag 'for-linus-v3.6-rc1' of git://oss.sgi.com/xfs/xfs: (44 commits)
  xfs: wait for the write the superblock on unmount
  xfs: re-enable xfsaild idle mode and fix associated races
  xfs: remove iolock lock classes
  xfs: avoid the iolock in xfs_free_eofblocks for evicted inodes
  xfs: do not take the iolock in xfs_inactive
  xfs: remove xfs_inactive_attrs
  xfs: clean up xfs_inactive
  xfs: do not read the AGI buffer in xfs_dialloc until nessecary
  xfs: refactor xfs_ialloc_ag_select
  xfs: add a short cut to xfs_dialloc for the non-NULL agbp case
  xfs: remove the alloc_done argument to xfs_dialloc
  xfs: split xfs_dialloc
  xfs: remove xfs_ialloc_find_free
  Prefix IO_XX flags with XFS_IO_XX to avoid namespace colision.
  xfs: remove xfs_inotobp
  xfs: merge xfs_itobp into xfs_imap_to_bp
  xfs: handle EOF correctly in xfs_vm_writepage
  xfs: implement ->update_time
  xfs: fix comment typo of struct xfs_da_blkinfo.
  xfs: do not call xfs_bdstrat_cb in xfs_buf_iodone_callbacks
  ...

fs/xfs/xfs_alloc_btree.h

@@ -50,20 +50,6 @@ typedef struct xfs_alloc_rec_incore {
 /* btree pointer type */
 typedef __be32 xfs_alloc_ptr_t;
 
-/*
- * Minimum and maximum blocksize and sectorsize.
- * The blocksize upper limit is pretty much arbitrary.
- * The sectorsize upper limit is due to sizeof(sb_sectsize).
- */
-#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
-#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
-#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
-#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
-#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
-#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
-
 /*
  * Block numbers in the AG:
  * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.

fs/xfs/xfs_aops.c

@@ -179,7 +179,7 @@ xfs_finish_ioend(
 	if (atomic_dec_and_test(&ioend->io_remaining)) {
 		struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
 
-		if (ioend->io_type == IO_UNWRITTEN)
+		if (ioend->io_type == XFS_IO_UNWRITTEN)
 			queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
 		else if (ioend->io_append_trans)
 			queue_work(mp->m_data_workqueue, &ioend->io_work);
@@ -210,7 +210,7 @@ xfs_end_io(
 	 * For unwritten extents we need to issue transactions to convert a
 	 * range to normal written extens after the data I/O has finished.
 	 */
-	if (ioend->io_type == IO_UNWRITTEN) {
+	if (ioend->io_type == XFS_IO_UNWRITTEN) {
 		/*
 		 * For buffered I/O we never preallocate a transaction when
 		 * doing the unwritten extent conversion, but for direct I/O
@@ -312,7 +312,7 @@ xfs_map_blocks(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -XFS_ERROR(EIO);
 
-	if (type == IO_UNWRITTEN)
+	if (type == XFS_IO_UNWRITTEN)
 		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
@@ -323,10 +323,10 @@ xfs_map_blocks(
 
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
-	ASSERT(offset <= mp->m_maxioffset);
+	ASSERT(offset <= mp->m_super->s_maxbytes);
 
-	if (offset + count > mp->m_maxioffset)
-		count = mp->m_maxioffset - offset;
+	if (offset + count > mp->m_super->s_maxbytes)
+		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
@@ -336,7 +336,7 @@ xfs_map_blocks(
 	if (error)
 		return -XFS_ERROR(error);
 
-	if (type == IO_DELALLOC &&
+	if (type == XFS_IO_DELALLOC &&
 	    (!nimaps || isnullstartblock(imap->br_startblock))) {
 		error = xfs_iomap_write_allocate(ip, offset, count, imap);
 		if (!error)
@@ -345,7 +345,7 @@ xfs_map_blocks(
 	}
 
 #ifdef DEBUG
-	if (type == IO_UNWRITTEN) {
+	if (type == XFS_IO_UNWRITTEN) {
 		ASSERT(nimaps);
 		ASSERT(imap->br_startblock != HOLESTARTBLOCK);
 		ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
@@ -634,11 +634,11 @@ xfs_check_page_type(
 		bh = head = page_buffers(page);
 		do {
 			if (buffer_unwritten(bh))
-				acceptable += (type == IO_UNWRITTEN);
+				acceptable += (type == XFS_IO_UNWRITTEN);
 			else if (buffer_delay(bh))
-				acceptable += (type == IO_DELALLOC);
+				acceptable += (type == XFS_IO_DELALLOC);
 			else if (buffer_dirty(bh) && buffer_mapped(bh))
-				acceptable += (type == IO_OVERWRITE);
+				acceptable += (type == XFS_IO_OVERWRITE);
 			else
 				break;
 		} while ((bh = bh->b_this_page) != head);
@@ -721,11 +721,11 @@ xfs_convert_page(
 		if (buffer_unwritten(bh) || buffer_delay(bh) ||
 		    buffer_mapped(bh)) {
 			if (buffer_unwritten(bh))
-				type = IO_UNWRITTEN;
+				type = XFS_IO_UNWRITTEN;
 			else if (buffer_delay(bh))
-				type = IO_DELALLOC;
+				type = XFS_IO_DELALLOC;
 			else
-				type = IO_OVERWRITE;
+				type = XFS_IO_OVERWRITE;
 
 			if (!xfs_imap_valid(inode, imap, offset)) {
 				done = 1;
@@ -733,7 +733,7 @@ xfs_convert_page(
 			}
 
 			lock_buffer(bh);
-			if (type != IO_OVERWRITE)
+			if (type != XFS_IO_OVERWRITE)
 				xfs_map_at_offset(inode, bh, imap, offset);
 			xfs_add_to_ioend(inode, bh, offset, type,
 					 ioendp, done);
@@ -831,7 +831,7 @@ xfs_aops_discard_page(
 	struct buffer_head	*bh, *head;
 	loff_t			offset = page_offset(page);
 
-	if (!xfs_check_page_type(page, IO_DELALLOC))
+	if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
 		goto out_invalidate;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -927,11 +927,26 @@ xfs_vm_writepage(
 	end_index = offset >> PAGE_CACHE_SHIFT;
 	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
 	if (page->index >= end_index) {
-		if ((page->index >= end_index + 1) ||
-		    !(i_size_read(inode) & (PAGE_CACHE_SIZE - 1))) {
+		unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
+
+		/*
+		 * Just skip the page if it is fully outside i_size, e.g. due
+		 * to a truncate operation that is in progress.
+		 */
+		if (page->index >= end_index + 1 || offset_into_page == 0) {
 			unlock_page(page);
 			return 0;
 		}
+
+		/*
+		 * The page straddles i_size.  It must be zeroed out on each
+		 * and every writepage invocation because it may be mmapped.
+		 * "A file is mapped in multiples of the page size.  For a file
+		 * that is not a multiple of the  page size, the remaining
+		 * memory is zeroed when mapped, and writes to that region are
+		 * not written out to the file."
+		 */
+		zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
 	}
 
 	end_offset = min_t(unsigned long long,
@@ -941,7 +956,7 @@ xfs_vm_writepage(
 
 	bh = head = page_buffers(page);
 	offset = page_offset(page);
-	type = IO_OVERWRITE;
+	type = XFS_IO_OVERWRITE;
 
 	if (wbc->sync_mode == WB_SYNC_NONE)
 		nonblocking = 1;
@@ -966,18 +981,18 @@ xfs_vm_writepage(
 		}
 
 		if (buffer_unwritten(bh)) {
-			if (type != IO_UNWRITTEN) {
-				type = IO_UNWRITTEN;
+			if (type != XFS_IO_UNWRITTEN) {
+				type = XFS_IO_UNWRITTEN;
 				imap_valid = 0;
 			}
 		} else if (buffer_delay(bh)) {
-			if (type != IO_DELALLOC) {
-				type = IO_DELALLOC;
+			if (type != XFS_IO_DELALLOC) {
+				type = XFS_IO_DELALLOC;
 				imap_valid = 0;
 			}
 		} else if (buffer_uptodate(bh)) {
-			if (type != IO_OVERWRITE) {
-				type = IO_OVERWRITE;
+			if (type != XFS_IO_OVERWRITE) {
+				type = XFS_IO_OVERWRITE;
 				imap_valid = 0;
 			}
 		} else {
@@ -1013,7 +1028,7 @@ xfs_vm_writepage(
 		}
 		if (imap_valid) {
 			lock_buffer(bh);
-			if (type != IO_OVERWRITE)
+			if (type != XFS_IO_OVERWRITE)
 				xfs_map_at_offset(inode, bh, &imap, offset);
 			xfs_add_to_ioend(inode, bh, offset, type, &ioend,
 					 new_ioend);
@@ -1054,7 +1069,7 @@ xfs_vm_writepage(
 		 * Reserve log space if we might write beyond the on-disk
 		 * inode size.
 		 */
-		if (ioend->io_type != IO_UNWRITTEN &&
+		if (ioend->io_type != XFS_IO_UNWRITTEN &&
 		    xfs_ioend_is_append(ioend)) {
 			err = xfs_setfilesize_trans_alloc(ioend);
 			if (err)
@@ -1162,9 +1177,9 @@ __xfs_get_blocks(
 		lockmode = xfs_ilock_map_shared(ip);
 	}
 
-	ASSERT(offset <= mp->m_maxioffset);
-	if (offset + size > mp->m_maxioffset)
-		size = mp->m_maxioffset - offset;
+	ASSERT(offset <= mp->m_super->s_maxbytes);
+	if (offset + size > mp->m_super->s_maxbytes)
+		size = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
@@ -1351,7 +1366,7 @@ xfs_end_io_direct_write(
 	ioend->io_iocb = iocb;
 	ioend->io_result = ret;
 	if (private && size > 0)
-		ioend->io_type = IO_UNWRITTEN;
+		ioend->io_type = XFS_IO_UNWRITTEN;
 
 	if (is_async) {
 		ioend->io_isasync = 1;
@@ -1383,7 +1398,7 @@ xfs_vm_direct_IO(
 		 * and converts at least on unwritten extent we will cancel
 		 * the still clean transaction after the I/O has finished.
 		 */
-		iocb->private = ioend = xfs_alloc_ioend(inode, IO_DIRECT);
+		iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT);
 		if (offset + size > XFS_I(inode)->i_d.di_size) {
 			ret = xfs_setfilesize_trans_alloc(ioend);
 			if (ret)

fs/xfs/xfs_aops.h

@@ -24,17 +24,17 @@ extern mempool_t *xfs_ioend_pool;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
-	IO_DIRECT = 0,	/* special case for direct I/O ioends */
-	IO_DELALLOC,	/* mapping covers delalloc region */
-	IO_UNWRITTEN,	/* mapping covers allocated but uninitialized data */
-	IO_OVERWRITE,	/* mapping covers already allocated extent */
+	XFS_IO_DIRECT = 0,	/* special case for direct I/O ioends */
+	XFS_IO_DELALLOC,	/* covers delalloc region */
+	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
+	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 };
 
 #define XFS_IO_TYPES \
 	{ 0,			"" }, \
-	{ IO_DELALLOC,		"delalloc" }, \
-	{ IO_UNWRITTEN,		"unwritten" }, \
-	{ IO_OVERWRITE,		"overwrite" }
+	{ XFS_IO_DELALLOC,		"delalloc" }, \
+	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
+	{ XFS_IO_OVERWRITE,		"overwrite" }
 
 /*
  * xfs_ioend struct manages large extent writes for XFS.

fs/xfs/xfs_attr.c

@@ -893,7 +893,7 @@ STATIC int
 xfs_attr_leaf_addname(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
@@ -915,11 +915,11 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 */
 	retval = xfs_attr_leaf_lookup_int(bp, args);
 	if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(retval);
 	} else if (retval == EEXIST) {
 		if (args->flags & ATTR_CREATE) {	/* pure create op */
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 			return(retval);
 		}
 
@@ -937,7 +937,6 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 * if required.
 	 */
 	retval = xfs_attr_leaf_add(bp, args);
-	xfs_da_buf_done(bp);
 	if (retval == ENOSPC) {
 		/*
 		 * Promote the attribute list to the Btree format, then
@@ -1065,8 +1064,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			 */
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
-		} else
-			xfs_da_buf_done(bp);
+		}
 
 		/*
 		 * Commit the remove and start the next trans in series.
@@ -1092,7 +1090,7 @@ STATIC int
 xfs_attr_leaf_removename(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error, committed, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
@@ -1111,7 +1109,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	ASSERT(bp != NULL);
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error == ENOATTR) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 
@@ -1141,8 +1139,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 		 */
 		if (committed)
 			xfs_trans_ijoin(args->trans, dp, 0);
-	} else
-		xfs_da_buf_done(bp);
+	}
 	return(0);
 }
 
@@ -1155,7 +1152,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 STATIC int
 xfs_attr_leaf_get(xfs_da_args_t *args)
 {
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	args->blkno = 0;
@@ -1167,11 +1164,11 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
 
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error != EEXIST)  {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 	error = xfs_attr_leaf_getvalue(bp, args);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
 		error = xfs_attr_rmtval_get(args);
 	}
@@ -1186,23 +1183,23 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 {
 	xfs_attr_leafblock_t *leaf;
 	int error;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	context->cursor->blkno = 0;
 	error = xfs_da_read_buf(NULL, context->dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return XFS_ERROR(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	if (unlikely(leaf->hdr.info.magic != cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_attr_leaf_list", XFS_ERRLEVEL_LOW,
 				     context->dp->i_mount, leaf);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
 	error = xfs_attr_leaf_list_int(bp, context);
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return XFS_ERROR(error);
 }
 
@@ -1489,7 +1486,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_da_state_t *state;
 	xfs_da_state_blk_t *blk;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_node_removename(args);
@@ -1601,14 +1598,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 		 */
 		ASSERT(state->path.active == 1);
 		ASSERT(state->path.blk[0].bp);
-		xfs_da_buf_done(state->path.blk[0].bp);
 		state->path.blk[0].bp = NULL;
 
 		error = xfs_da_read_buf(args->trans, args->dp, 0, -1, &bp,
 						     XFS_ATTR_FORK);
 		if (error)
 			goto out;
-		ASSERT((((xfs_attr_leafblock_t *)bp->data)->hdr.info.magic) ==
+		ASSERT((((xfs_attr_leafblock_t *)bp->b_addr)->hdr.info.magic) ==
 		       cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
@@ -1635,7 +1631,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
 		} else
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 	}
 	error = 0;
 
@@ -1665,8 +1661,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1681,8 +1676,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1792,7 +1786,7 @@ xfs_attr_node_get(xfs_da_args_t *args)
 	 * If not in a transaction, we have to release all the buffers.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 
@@ -1808,7 +1802,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	xfs_da_intnode_t *node;
 	xfs_da_node_entry_t *btree;
 	int error, i;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	cursor = context->cursor;
 	cursor->initted = 1;
@@ -1825,30 +1819,30 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		if ((error != 0) && (error != EFSCORRUPTED))
 			return(error);
 		if (bp) {
-			node = bp->data;
+			node = bp->b_addr;
 			switch (be16_to_cpu(node->hdr.info.magic)) {
 			case XFS_DA_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 				break;
 			case XFS_ATTR_LEAF_MAGIC:
-				leaf = bp->data;
+				leaf = bp->b_addr;
 				if (cursor->hashval > be32_to_cpu(leaf->entries[
 				    be16_to_cpu(leaf->hdr.count)-1].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				} else if (cursor->hashval <=
 					     be32_to_cpu(leaf->entries[0].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				}
 				break;
 			default:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 			}
 		}
@@ -1873,7 +1867,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						 context->dp->i_mount);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
-			node = bp->data;
+			node = bp->b_addr;
 			if (node->hdr.info.magic ==
 			    cpu_to_be16(XFS_ATTR_LEAF_MAGIC))
 				break;
@@ -1883,7 +1877,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						     XFS_ERRLEVEL_LOW,
 						     context->dp->i_mount,
 						     node);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
 			btree = node->btree;
@@ -1898,10 +1892,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				}
 			}
 			if (i == be16_to_cpu(node->hdr.count)) {
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(0);
 			}
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 		}
 	}
 	ASSERT(bp != NULL);
@@ -1912,24 +1906,24 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 * adding the information.
 	 */
 	for (;;) {
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		if (unlikely(leaf->hdr.info.magic !=
 			     cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 			XFS_CORRUPTION_ERROR("xfs_attr_node_list(4)",
 					     XFS_ERRLEVEL_LOW,
 					     context->dp->i_mount, leaf);
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 		error = xfs_attr_leaf_list_int(bp, context);
 		if (error) {
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return error;
 		}
 		if (context->seen_enough || leaf->hdr.info.forw == 0)
 			break;
 		cursor->blkno = be32_to_cpu(leaf->hdr.info.forw);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		error = xfs_da_read_buf(NULL, context->dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if (error)
@@ -1941,7 +1935,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 	}
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return(0);
 }
 

fs/xfs/xfs_attr_leaf.c

@@ -54,10 +54,10 @@
  * Routines used for growing the Btree.
  */
 STATIC int xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t which_block,
-				    xfs_dabuf_t **bpp);
-STATIC int xfs_attr_leaf_add_work(xfs_dabuf_t *leaf_buffer, xfs_da_args_t *args,
-					      int freemap_index);
-STATIC void xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *leaf_buffer);
+				struct xfs_buf **bpp);
+STATIC int xfs_attr_leaf_add_work(struct xfs_buf *leaf_buffer,
+				  xfs_da_args_t *args, int freemap_index);
+STATIC void xfs_attr_leaf_compact(xfs_trans_t *tp, struct xfs_buf *leaf_buffer);
 STATIC void xfs_attr_leaf_rebalance(xfs_da_state_t *state,
 						   xfs_da_state_blk_t *blk1,
 						   xfs_da_state_blk_t *blk2);
@@ -71,9 +71,9 @@ STATIC int xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
  * Routines used for shrinking the Btree.
  */
 STATIC int xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp, int level);
+				  struct xfs_buf *bp, int level);
 STATIC int xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp);
+				  struct xfs_buf *bp);
 STATIC int xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
 				   xfs_dablk_t blkno, int blkcnt);
 
@@ -480,7 +480,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	char *tmpbuffer;
 	int error, i, size;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	xfs_ifork_t *ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
@@ -550,8 +550,6 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	error = 0;
 
 out:
-	if(bp)
-		xfs_da_buf_done(bp);
 	kmem_free(tmpbuffer);
 	return(error);
 }
@@ -737,14 +735,16 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
  * a shortform attribute list.
  */
 int
-xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
+xfs_attr_shortform_allfit(
+	struct xfs_buf	*bp,
+	struct xfs_inode *dp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_local_t *name_loc;
 	int bytes, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	entry = &leaf->entries[0];
@@ -774,7 +774,10 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
  * Convert a leaf attribute list to shortform attribute list
  */
 int
-xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
+xfs_attr_leaf_to_shortform(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		forkoff)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -791,10 +794,10 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	ASSERT(tmpbuffer != NULL);
 
 	ASSERT(bp != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(dp->i_mount));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(dp->i_mount));
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
-	memset(bp->data, 0, XFS_LBSIZE(dp->i_mount));
+	memset(bp->b_addr, 0, XFS_LBSIZE(dp->i_mount));
 
 	/*
 	 * Clean out the prior contents of the attribute list.
@@ -855,7 +858,7 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_da_intnode_t *node;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	xfs_dablk_t blkno;
 	int error;
 
@@ -877,10 +880,9 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	if (error)
 		goto out;
 	ASSERT(bp2 != NULL);
-	memcpy(bp2->data, bp1->data, XFS_LBSIZE(dp->i_mount));
-	xfs_da_buf_done(bp1);
+	memcpy(bp2->b_addr, bp1->b_addr, XFS_LBSIZE(dp->i_mount));
 	bp1 = NULL;
-	xfs_da_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	/*
 	 * Set up the new root node.
@@ -888,21 +890,17 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	error = xfs_da_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK);
 	if (error)
 		goto out;
-	node = bp1->data;
-	leaf = bp2->data;
+	node = bp1->b_addr;
+	leaf = bp2->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	/* both on-disk, don't endian-flip twice */
 	node->btree[0].hashval =
 		leaf->entries[be16_to_cpu(leaf->hdr.count)-1 ].hashval;
 	node->btree[0].before = cpu_to_be32(blkno);
 	node->hdr.count = cpu_to_be16(1);
-	xfs_da_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
 	error = 0;
 out:
-	if (bp1)
-		xfs_da_buf_done(bp1);
-	if (bp2)
-		xfs_da_buf_done(bp2);
 	return(error);
 }
 
@@ -916,12 +914,15 @@ out:
  * or a leaf in a node attribute list.
  */
 STATIC int
-xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
+xfs_attr_leaf_create(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	blkno,
+	struct xfs_buf	**bpp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_create(args);
@@ -933,7 +934,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	memset((char *)leaf, 0, XFS_LBSIZE(dp->i_mount));
 	hdr = &leaf->hdr;
 	hdr->info.magic = cpu_to_be16(XFS_ATTR_LEAF_MAGIC);
@@ -947,7 +948,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	hdr->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr->firstused) -
 					   sizeof(xfs_attr_leaf_hdr_t));
 
-	xfs_da_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	*bpp = bp;
 	return(0);
@@ -1014,7 +1015,9 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
  * Add a name to the leaf attribute list structure.
  */
 int
-xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_add(
+	struct xfs_buf		*bp,
+	struct xfs_da_args	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1023,7 +1026,7 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_add(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT((args->index >= 0)
 		&& (args->index <= be16_to_cpu(leaf->hdr.count)));
@@ -1085,7 +1088,10 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * Add a name to a leaf attribute list structure.
  */
 STATIC int
-xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
+xfs_attr_leaf_add_work(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		mapindex)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1096,7 +1102,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 	xfs_mount_t *mp;
 	int tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	ASSERT((mapindex >= 0) && (mapindex < XFS_ATTR_LEAF_MAPSIZE));
@@ -1110,7 +1116,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		tmp  = be16_to_cpu(hdr->count) - args->index;
 		tmp *= sizeof(xfs_attr_leaf_entry_t);
 		memmove((char *)(entry+1), (char *)entry, tmp);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 		    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	}
 	be16_add_cpu(&hdr->count, 1);
@@ -1142,7 +1148,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 			args->index2++;
 		}
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	ASSERT((args->index == 0) ||
 	       (be32_to_cpu(entry->hashval) >= be32_to_cpu((entry-1)->hashval)));
@@ -1174,7 +1180,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		args->rmtblkno = 1;
 		args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen);
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   xfs_attr_leaf_entsize(leaf, args->index)));
 
@@ -1198,7 +1204,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		}
 	}
 	be16_add_cpu(&hdr->usedbytes, xfs_attr_leaf_entsize(leaf, args->index));
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 		XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 	return(0);
 }
@@ -1207,7 +1213,9 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
  * Garbage collect a leaf attribute list block by copying it to a new buffer.
  */
 STATIC void
-xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
+xfs_attr_leaf_compact(
+	struct xfs_trans *trans,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf_s, *leaf_d;
 	xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
@@ -1217,14 +1225,14 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	mp = trans->t_mountp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(mp));
-	memset(bp->data, 0, XFS_LBSIZE(mp));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));
+	memset(bp->b_addr, 0, XFS_LBSIZE(mp));
 
 	/*
 	 * Copy basic information
 	 */
 	leaf_s = (xfs_attr_leafblock_t *)tmpbuffer;
-	leaf_d = bp->data;
+	leaf_d = bp->b_addr;
 	hdr_s = &leaf_s->hdr;
 	hdr_d = &leaf_d->hdr;
 	hdr_d->info = hdr_s->info;	/* struct copy */
@@ -1247,7 +1255,7 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	 */
 	xfs_attr_leaf_moveents(leaf_s, 0, leaf_d, 0,
 				be16_to_cpu(hdr_s->count), mp);
-	xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
 
 	kmem_free(tmpbuffer);
 }
@@ -1279,8 +1287,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	 */
 	ASSERT(blk1->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC);
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	args = state->args;
@@ -1298,8 +1306,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		tmp_blk = blk1;
 		blk1 = blk2;
 		blk2 = tmp_blk;
-		leaf1 = blk1->bp->data;
-		leaf2 = blk2->bp->data;
+		leaf1 = blk1->bp->b_addr;
+		leaf2 = blk2->bp->b_addr;
 		swap = 1;
 	}
 	hdr1 = &leaf1->hdr;
@@ -1346,8 +1354,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf1, be16_to_cpu(hdr1->count) - count,
 				leaf2, 0, count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	} else if (count > be16_to_cpu(hdr1->count)) {
 		/*
 		 * I assert that since all callers pass in an empty
@@ -1378,8 +1386,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf2, 0, leaf1,
 				be16_to_cpu(hdr1->count), count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	}
 
 	/*
@@ -1448,8 +1456,8 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
 	/*
 	 * Set up environment.
 	 */
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	hdr1 = &leaf1->hdr;
 	hdr2 = &leaf2->hdr;
 	foundit = 0;
@@ -1551,7 +1559,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	xfs_da_blkinfo_t *info;
 	int count, bytes, forward, error, retval, i;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -1559,7 +1567,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[ state->path.active-1 ];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	leaf = (xfs_attr_leafblock_t *)info;
 	count = be16_to_cpu(leaf->hdr.count);
@@ -1622,13 +1630,13 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 		count  = be16_to_cpu(leaf->hdr.count);
 		bytes  = state->blocksize - (state->blocksize>>2);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
 		bytes -= count * sizeof(xfs_attr_leaf_entry_t);
 		bytes -= sizeof(xfs_attr_leaf_hdr_t);
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 		if (bytes >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
@@ -1666,7 +1674,9 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
  * If two leaves are 37% full, when combined they will leave 25% free.
  */
 int
-xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_remove(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1676,7 +1686,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	int tablesize, tmp, i;
 	xfs_mount_t *mp;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	mp = args->trans->t_mountp;
@@ -1769,7 +1779,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	 */
 	memset(xfs_attr_leaf_name(leaf, args->index), 0, entsize);
 	be16_add_cpu(&hdr->usedbytes, -entsize);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   entsize));
 
@@ -1777,7 +1787,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 					* sizeof(xfs_attr_leaf_entry_t);
 	memmove((char *)entry, (char *)(entry+1), tmp);
 	be16_add_cpu(&hdr->count, -1);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	entry = &leaf->entries[be16_to_cpu(hdr->count)];
 	memset((char *)entry, 0, sizeof(xfs_attr_leaf_entry_t));
@@ -1807,7 +1817,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	} else {
 		hdr->holes = 1;		/* mark as needing compaction */
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 
 	/*
@@ -1840,8 +1850,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	mp = state->mp;
 	ASSERT(drop_blk->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(save_blk->magic == XFS_ATTR_LEAF_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	drop_hdr = &drop_leaf->hdr;
@@ -1906,7 +1916,7 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 		kmem_free(tmpbuffer);
 	}
 
-	xfs_da_log_buf(state->args->trans, save_blk->bp, 0,
+	xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
 					   state->blocksize - 1);
 
 	/*
@@ -1934,7 +1944,9 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
  * Don't change the args->value unless we find the attribute.
  */
 int
-xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_lookup_int(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -1945,7 +1957,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_lookup(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2041,7 +2053,9 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * list structure.
  */
 int
-xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_getvalue(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	int valuelen;
 	xfs_attr_leafblock_t *leaf;
@@ -2049,7 +2063,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	xfs_attr_leaf_name_local_t *name_loc;
 	xfs_attr_leaf_name_remote_t *name_rmt;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2247,12 +2261,14 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
  * Return 0 unless leaf2 should go before leaf1.
  */
 int
-xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
+xfs_attr_leaf_order(
+	struct xfs_buf	*leaf1_bp,
+	struct xfs_buf	*leaf2_bp)
 {
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT((leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) &&
 	       (leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)));
 	if ((be16_to_cpu(leaf1->hdr.count) > 0) &&
@@ -2272,11 +2288,13 @@ xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
  * Pick up the last hashvalue from a leaf block.
  */
 xfs_dahash_t
-xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_attr_leaf_lasthash(
+	struct xfs_buf	*bp,
+	int		*count)
 {
 	xfs_attr_leafblock_t *leaf;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -2337,7 +2355,9 @@ xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
  * Copy out attribute list entries for attr_list(), for leaf attribute lists.
  */
 int
-xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
+xfs_attr_leaf_list_int(
+	struct xfs_buf		*bp,
+	xfs_attr_list_context_t	*context)
 {
 	attrlist_cursor_kern_t *cursor;
 	xfs_attr_leafblock_t *leaf;
@@ -2345,7 +2365,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
 	int retval, i;
 
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	cursor = context->cursor;
 	cursor->initted = 1;
 
@@ -2463,7 +2483,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2482,7 +2502,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2505,7 +2525,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 #endif /* DEBUG */
 
 	entry->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 
 	if (args->rmtblkno) {
@@ -2513,10 +2533,9 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2533,7 +2552,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_setflag(args);
@@ -2548,7 +2567,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2556,16 +2575,15 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 
 	ASSERT((entry->flags & XFS_ATTR_INCOMPLETE) == 0);
 	entry->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	if ((entry->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2586,7 +2604,7 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 	xfs_attr_leaf_entry_t *entry1, *entry2;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2620,13 +2638,13 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 		bp2 = bp1;
 	}
 
-	leaf1 = bp1->data;
+	leaf1 = bp1->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf1->hdr.count));
 	ASSERT(args->index >= 0);
 	entry1 = &leaf1->entries[ args->index ];
 
-	leaf2 = bp2->data;
+	leaf2 = bp2->b_addr;
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index2 < be16_to_cpu(leaf2->hdr.count));
 	ASSERT(args->index2 >= 0);
@@ -2660,30 +2678,27 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	ASSERT((entry2->flags & XFS_ATTR_INCOMPLETE) == 0);
 
 	entry1->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp1,
+	xfs_trans_log_buf(args->trans, bp1,
 			  XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1)));
 	if (args->rmtblkno) {
 		ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
 		name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp1,
+		xfs_trans_log_buf(args->trans, bp1,
 			 XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
 	}
 
 	entry2->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp2,
+	xfs_trans_log_buf(args->trans, bp2,
 			  XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2)));
 	if ((entry2->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp2,
+		xfs_trans_log_buf(args->trans, bp2,
 			 XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp1);
-	if (bp1 != bp2)
-		xfs_da_buf_done(bp2);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2706,7 +2721,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_daddr_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	/*
@@ -2718,20 +2733,20 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_read_buf(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	blkno = xfs_da_blkno(bp);
+	blkno = XFS_BUF_ADDR(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
 	 * This is a depth-first traversal!
 	 */
-	info = bp->data;
+	info = bp->b_addr;
 	if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 		error = xfs_attr_node_inactive(trans, dp, bp, 1);
 	} else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) {
 		error = xfs_attr_leaf_inactive(trans, dp, bp);
 	} else {
 		error = XFS_ERROR(EIO);
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 	}
 	if (error)
 		return(error);
@@ -2742,7 +2757,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	xfs_da_binval(*trans, bp);	/* remove from cache */
+	xfs_trans_binval(*trans, bp);	/* remove from cache */
 	/*
 	 * Commit the invalidate and start the next transaction.
 	 */
@@ -2756,34 +2771,37 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
  * We're doing a depth-first traversal in order to invalidate everything.
  */
 STATIC int
-xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
-				   int level)
+xfs_attr_node_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp,
+	int		level)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_da_intnode_t *node;
 	xfs_dablk_t child_fsb;
 	xfs_daddr_t parent_blkno, child_blkno;
 	int error, count, i;
-	xfs_dabuf_t *child_bp;
+	struct xfs_buf *child_bp;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
 	 */
 	if (level > XFS_DA_NODE_MAXDEPTH) {
-		xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 		return(XFS_ERROR(EIO));
 	}
 
-	node = bp->data;
+	node = bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
-	parent_blkno = xfs_da_blkno(bp);	/* save for re-read later */
+	parent_blkno = XFS_BUF_ADDR(bp);	/* save for re-read later */
 	count = be16_to_cpu(node->hdr.count);
 	if (!count) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 	child_fsb = be32_to_cpu(node->btree[0].before);
-	xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 
 	/*
 	 * If this is the node level just above the leaves, simply loop
@@ -2803,12 +2821,12 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			return(error);
 		if (child_bp) {
 						/* save for re-read later */
-			child_blkno = xfs_da_blkno(child_bp);
+			child_blkno = XFS_BUF_ADDR(child_bp);
 
 			/*
 			 * Invalidate the subtree, however we have to.
 			 */
-			info = child_bp->data;
+			info = child_bp->b_addr;
 			if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 				error = xfs_attr_node_inactive(trans, dp,
 						child_bp, level+1);
@@ -2817,7 +2835,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 						child_bp);
 			} else {
 				error = XFS_ERROR(EIO);
-				xfs_da_brelse(*trans, child_bp);
+				xfs_trans_brelse(*trans, child_bp);
 			}
 			if (error)
 				return(error);
@@ -2830,7 +2848,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 				&child_bp, XFS_ATTR_FORK);
 			if (error)
 				return(error);
-			xfs_da_binval(*trans, child_bp);
+			xfs_trans_binval(*trans, child_bp);
 		}
 
 		/*
@@ -2843,7 +2861,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			if (error)
 				return(error);
 			child_fsb = be32_to_cpu(node->btree[i+1].before);
-			xfs_da_brelse(*trans, bp);
+			xfs_trans_brelse(*trans, bp);
 		}
 		/*
 		 * Atomically commit the whole invalidate stuff.
@@ -2863,7 +2881,10 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
  * caught holding something that the logging code wants to flush to disk.
  */
 STATIC int
-xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
+xfs_attr_leaf_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -2871,7 +2892,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	xfs_attr_inactive_list_t *list, *lp;
 	int error, count, size, tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	/*
@@ -2892,7 +2913,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	 * If there are no "remote" values, we're done.
 	 */
 	if (count == 0) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 
@@ -2919,7 +2940,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 			}
 		}
 	}
-	xfs_da_brelse(*trans, bp);	/* unlock for trans. in freextent() */
+	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
 
 	/*
 	 * Invalidate each of the "remote" value extents.

fs/xfs/xfs_attr_leaf.h

@@ -31,7 +31,6 @@
 struct attrlist;
 struct attrlist_cursor_kern;
 struct xfs_attr_list_context;
-struct xfs_dabuf;
 struct xfs_da_args;
 struct xfs_da_state;
 struct xfs_da_state_blk;
@@ -215,7 +214,7 @@ int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_list(struct xfs_attr_list_context *context);
-int	xfs_attr_shortform_allfit(struct xfs_dabuf *bp, struct xfs_inode *dp);
+int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
 
 
@@ -223,7 +222,7 @@ int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
  */
 int	xfs_attr_leaf_to_node(struct xfs_da_args *args);
-int	xfs_attr_leaf_to_shortform(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_to_shortform(struct xfs_buf *bp,
 				   struct xfs_da_args *args, int forkoff);
 int	xfs_attr_leaf_clearflag(struct xfs_da_args *args);
 int	xfs_attr_leaf_setflag(struct xfs_da_args *args);
@@ -235,14 +234,14 @@ int	xfs_attr_leaf_flipflags(xfs_da_args_t *args);
 int	xfs_attr_leaf_split(struct xfs_da_state *state,
 				   struct xfs_da_state_blk *oldblk,
 				   struct xfs_da_state_blk *newblk);
-int	xfs_attr_leaf_lookup_int(struct xfs_dabuf *leaf,
+int	xfs_attr_leaf_lookup_int(struct xfs_buf *leaf,
 					struct xfs_da_args *args);
-int	xfs_attr_leaf_getvalue(struct xfs_dabuf *bp, struct xfs_da_args *args);
-int	xfs_attr_leaf_add(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args);
+int	xfs_attr_leaf_add(struct xfs_buf *leaf_buffer,
 				 struct xfs_da_args *args);
-int	xfs_attr_leaf_remove(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_remove(struct xfs_buf *leaf_buffer,
 				    struct xfs_da_args *args);
-int	xfs_attr_leaf_list_int(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_list_int(struct xfs_buf *bp,
 				      struct xfs_attr_list_context *context);
 
 /*
@@ -257,9 +256,9 @@ int	xfs_attr_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
 /*
  * Utility routines.
  */
-xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_dabuf *bp, int *count);
-int	xfs_attr_leaf_order(struct xfs_dabuf *leaf1_bp,
-				   struct xfs_dabuf *leaf2_bp);
+xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
+int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
+				   struct xfs_buf *leaf2_bp);
 int	xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
 					int *local);
 #endif	/* __XFS_ATTR_LEAF_H__ */

fs/xfs/xfs_bmap.c

@@ -5517,7 +5517,7 @@ xfs_getbmap(
 		if (xfs_get_extsz_hint(ip) ||
 		    ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
 			prealloced = 1;
-			fixlen = XFS_MAXIOFFSET(mp);
+			fixlen = mp->m_super->s_maxbytes;
 		} else {
 			prealloced = 0;
 			fixlen = XFS_ISIZE(ip);

fs/xfs/xfs_buf.c

@@ -164,14 +164,49 @@ xfs_buf_stale(
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
 }
 
+static int
+xfs_buf_get_maps(
+	struct xfs_buf		*bp,
+	int			map_count)
+{
+	ASSERT(bp->b_maps == NULL);
+	bp->b_map_count = map_count;
+
+	if (map_count == 1) {
+		bp->b_maps = &bp->b_map;
+		return 0;
+	}
+
+	bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map),
+				KM_NOFS);
+	if (!bp->b_maps)
+		return ENOMEM;
+	return 0;
+}
+
+/*
+ *	Frees b_pages if it was allocated.
+ */
+static void
+xfs_buf_free_maps(
+	struct xfs_buf	*bp)
+{
+	if (bp->b_maps != &bp->b_map) {
+		kmem_free(bp->b_maps);
+		bp->b_maps = NULL;
+	}
+}
+
 struct xfs_buf *
-xfs_buf_alloc(
+_xfs_buf_alloc(
 	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
+	int			error;
+	int			i;
 
 	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
 	if (unlikely(!bp))
@@ -192,16 +227,28 @@ xfs_buf_alloc(
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	XB_SET_OWNER(bp);
 	bp->b_target = target;
+	bp->b_flags = flags;
 
 	/*
 	 * Set length and io_length to the same value initially.
 	 * I/O routines should use io_length, which will be the same in
 	 * most cases but may be reset (e.g. XFS recovery).
 	 */
-	bp->b_length = numblks;
-	bp->b_io_length = numblks;
-	bp->b_flags = flags;
-	bp->b_bn = blkno;
+	error = xfs_buf_get_maps(bp, nmaps);
+	if (error)  {
+		kmem_zone_free(xfs_buf_zone, bp);
+		return NULL;
+	}
+
+	bp->b_bn = map[0].bm_bn;
+	bp->b_length = 0;
+	for (i = 0; i < nmaps; i++) {
+		bp->b_maps[i].bm_bn = map[i].bm_bn;
+		bp->b_maps[i].bm_len = map[i].bm_len;
+		bp->b_length += map[i].bm_len;
+	}
+	bp->b_io_length = bp->b_length;
+
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
 
@@ -280,6 +327,7 @@ xfs_buf_free(
 	} else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
 	_xfs_buf_free_pages(bp);
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
 }
 
@@ -327,8 +375,9 @@ xfs_buf_allocate_memory(
 	}
 
 use_alloc_page:
-	start = BBTOB(bp->b_bn) >> PAGE_SHIFT;
-	end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	start = BBTOB(bp->b_map.bm_bn) >> PAGE_SHIFT;
+	end = (BBTOB(bp->b_map.bm_bn + bp->b_length) + PAGE_SIZE - 1)
+								>> PAGE_SHIFT;
 	page_count = end - start;
 	error = _xfs_buf_get_pages(bp, page_count, flags);
 	if (unlikely(error))
@@ -425,8 +474,8 @@ _xfs_buf_map_pages(
 xfs_buf_t *
 _xfs_buf_find(
 	struct xfs_buftarg	*btp,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags,
 	xfs_buf_t		*new_bp)
 {
@@ -435,7 +484,12 @@ _xfs_buf_find(
 	struct rb_node		**rbp;
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
+	xfs_daddr_t		blkno = map[0].bm_bn;
+	int			numblks = 0;
+	int			i;
 
+	for (i = 0; i < nmaps; i++)
+		numblks += map[i].bm_len;
 	numbytes = BBTOB(numblks);
 
 	/* Check for IOs smaller than the sector size / not sector aligned */
@@ -527,31 +581,31 @@ found:
  * more hits than misses.
  */
 struct xfs_buf *
-xfs_buf_get(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_get_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
 	struct xfs_buf		*new_bp;
 	int			error = 0;
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, NULL);
+	bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
 	if (likely(bp))
 		goto found;
 
-	new_bp = xfs_buf_alloc(target, blkno, numblks, flags);
+	new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
 	error = xfs_buf_allocate_memory(new_bp, flags);
 	if (error) {
-		kmem_zone_free(xfs_buf_zone, new_bp);
+		xfs_buf_free(new_bp);
 		return NULL;
 	}
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp);
+	bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
 	if (!bp) {
 		xfs_buf_free(new_bp);
 		return NULL;
@@ -560,8 +614,6 @@ xfs_buf_get(
 	if (bp != new_bp)
 		xfs_buf_free(new_bp);
 
-	bp->b_io_length = bp->b_length;
-
 found:
 	if (!bp->b_addr) {
 		error = _xfs_buf_map_pages(bp, flags);
@@ -584,7 +636,7 @@ _xfs_buf_read(
 	xfs_buf_flags_t		flags)
 {
 	ASSERT(!(flags & XBF_WRITE));
-	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+	ASSERT(bp->b_map.bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
@@ -596,17 +648,17 @@ _xfs_buf_read(
 }
 
 xfs_buf_t *
-xfs_buf_read(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_read_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
 
 	flags |= XBF_READ;
 
-	bp = xfs_buf_get(target, blkno, numblks, flags);
+	bp = xfs_buf_get_map(target, map, nmaps, flags);
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
@@ -634,15 +686,15 @@ xfs_buf_read(
  *	safe manner.
  */
 void
-xfs_buf_readahead(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks)
+xfs_buf_readahead_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps)
 {
 	if (bdi_read_congested(target->bt_bdi))
 		return;
 
-	xfs_buf_read(target, blkno, numblks,
+	xfs_buf_read_map(target, map, nmaps,
 		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
 }
 
@@ -665,8 +717,10 @@ xfs_buf_read_uncached(
 		return NULL;
 
 	/* set up the buffer for a read IO */
-	XFS_BUF_SET_ADDR(bp, daddr);
-	XFS_BUF_READ(bp);
+	ASSERT(bp->b_map_count == 1);
+	bp->b_bn = daddr;
+	bp->b_maps[0].bm_bn = daddr;
+	bp->b_flags |= XBF_READ;
 
 	xfsbdstrat(target->bt_mount, bp);
 	error = xfs_buf_iowait(bp);
@@ -694,7 +748,11 @@ xfs_buf_set_empty(
 	bp->b_addr = NULL;
 	bp->b_length = numblks;
 	bp->b_io_length = numblks;
+
+	ASSERT(bp->b_map_count == 1);
 	bp->b_bn = XFS_BUF_DADDR_NULL;
+	bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL;
+	bp->b_maps[0].bm_len = bp->b_length;
 }
 
 static inline struct page *
@@ -758,9 +816,10 @@ xfs_buf_get_uncached(
 {
 	unsigned long		page_count;
 	int			error, i;
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
+	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
-	bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0);
+	bp = _xfs_buf_alloc(target, &map, 1, 0);
 	if (unlikely(bp == NULL))
 		goto fail;
 
@@ -791,6 +850,7 @@ xfs_buf_get_uncached(
 		__free_page(bp->b_pages[i]);
 	_xfs_buf_free_pages(bp);
  fail_free_buf:
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
  fail:
 	return NULL;
@@ -1144,36 +1204,39 @@ xfs_buf_bio_end_io(
 	bio_put(bio);
 }
 
-STATIC void
-_xfs_buf_ioapply(
-	xfs_buf_t		*bp)
+static void
+xfs_buf_ioapply_map(
+	struct xfs_buf	*bp,
+	int		map,
+	int		*buf_offset,
+	int		*count,
+	int		rw)
 {
-	int			rw, map_i, total_nr_pages, nr_pages;
-	struct bio		*bio;
-	int			offset = bp->b_offset;
-	int			size = BBTOB(bp->b_io_length);
-	sector_t		sector = bp->b_bn;
+	int		page_index;
+	int		total_nr_pages = bp->b_page_count;
+	int		nr_pages;
+	struct bio	*bio;
+	sector_t	sector =  bp->b_maps[map].bm_bn;
+	int		size;
+	int		offset;
 
 	total_nr_pages = bp->b_page_count;
-	map_i = 0;
 
-	if (bp->b_flags & XBF_WRITE) {
-		if (bp->b_flags & XBF_SYNCIO)
-			rw = WRITE_SYNC;
-		else
-			rw = WRITE;
-		if (bp->b_flags & XBF_FUA)
-			rw |= REQ_FUA;
-		if (bp->b_flags & XBF_FLUSH)
-			rw |= REQ_FLUSH;
-	} else if (bp->b_flags & XBF_READ_AHEAD) {
-		rw = READA;
-	} else {
-		rw = READ;
+	/* skip the pages in the buffer before the start offset */
+	page_index = 0;
+	offset = *buf_offset;
+	while (offset >= PAGE_SIZE) {
+		page_index++;
+		offset -= PAGE_SIZE;
 	}
 
-	/* we only use the buffer cache for meta-data */
-	rw |= REQ_META;
+	/*
+	 * Limit the IO size to the length of the current vector, and update the
+	 * remaining IO count for the next time around.
+	 */
+	size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count);
+	*count -= size;
+	*buf_offset += size;
 
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
@@ -1188,13 +1251,14 @@ next_chunk:
 	bio->bi_private = bp;
 
 
-	for (; size && nr_pages; nr_pages--, map_i++) {
+	for (; size && nr_pages; nr_pages--, page_index++) {
 		int	rbytes, nbytes = PAGE_SIZE - offset;
 
 		if (nbytes > size)
 			nbytes = size;
 
-		rbytes = bio_add_page(bio, bp->b_pages[map_i], nbytes, offset);
+		rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes,
+				      offset);
 		if (rbytes < nbytes)
 			break;
 
@@ -1216,6 +1280,54 @@ next_chunk:
 		xfs_buf_ioerror(bp, EIO);
 		bio_put(bio);
 	}
+
+}
+
+STATIC void
+_xfs_buf_ioapply(
+	struct xfs_buf	*bp)
+{
+	struct blk_plug	plug;
+	int		rw;
+	int		offset;
+	int		size;
+	int		i;
+
+	if (bp->b_flags & XBF_WRITE) {
+		if (bp->b_flags & XBF_SYNCIO)
+			rw = WRITE_SYNC;
+		else
+			rw = WRITE;
+		if (bp->b_flags & XBF_FUA)
+			rw |= REQ_FUA;
+		if (bp->b_flags & XBF_FLUSH)
+			rw |= REQ_FLUSH;
+	} else if (bp->b_flags & XBF_READ_AHEAD) {
+		rw = READA;
+	} else {
+		rw = READ;
+	}
+
+	/* we only use the buffer cache for meta-data */
+	rw |= REQ_META;
+
+	/*
+	 * Walk all the vectors issuing IO on them. Set up the initial offset
+	 * into the buffer and the desired IO size before we start -
+	 * _xfs_buf_ioapply_vec() will modify them appropriately for each
+	 * subsequent call.
+	 */
+	offset = bp->b_offset;
+	size = BBTOB(bp->b_io_length);
+	blk_start_plug(&plug);
+	for (i = 0; i < bp->b_map_count; i++) {
+		xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+		if (bp->b_error)
+			break;
+		if (size <= 0)
+			break;	/* all done */
+	}
+	blk_finish_plug(&plug);
 }
 
 void
@@ -1557,7 +1669,7 @@ xfs_buf_cmp(
 	struct xfs_buf	*bp = container_of(b, struct xfs_buf, b_list);
 	xfs_daddr_t		diff;
 
-	diff = ap->b_bn - bp->b_bn;
+	diff = ap->b_map.bm_bn - bp->b_map.bm_bn;
 	if (diff < 0)
 		return -1;
 	if (diff > 0)

fs/xfs/xfs_buf.h

@@ -58,6 +58,7 @@ typedef enum {
 #define _XBF_PAGES	(1 << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	(1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	(1 << 22)/* buffer on a delwri queue */
+#define _XBF_COMPOUND	(1 << 23)/* compound buffer */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -75,7 +76,8 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
-	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
+	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
+	{ _XBF_COMPOUND,	"COMPOUND" }
 
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
@@ -98,6 +100,14 @@ typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
+struct xfs_buf_map {
+	xfs_daddr_t		bm_bn;	/* block number for I/O */
+	int			bm_len;	/* size of I/O */
+};
+
+#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \
+	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
+
 typedef struct xfs_buf {
 	/*
 	 * first cacheline holds all the fields needed for an uncontended cache
@@ -107,7 +117,7 @@ typedef struct xfs_buf {
 	 * fast-path on locking.
 	 */
 	struct rb_node		b_rbnode;	/* rbtree node */
-	xfs_daddr_t		b_bn;		/* block number for I/O */
+	xfs_daddr_t		b_bn;		/* block number of buffer */
 	int			b_length;	/* size of buffer in BBs */
 	atomic_t		b_hold;		/* reference count */
 	atomic_t		b_lru_ref;	/* lru reclaim ref count */
@@ -127,12 +137,16 @@ typedef struct xfs_buf {
 	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
+	struct xfs_buf_map	*b_maps;	/* compound buffer map */
+	struct xfs_buf_map	b_map;		/* inline compound buffer map */
+	int			b_map_count;
 	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
 	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
 	unsigned int		b_page_count;	/* size of page array */
 	unsigned int		b_offset;	/* page offset in first page */
 	unsigned short		b_error;	/* error code on I/O */
+
 #ifdef XFS_BUF_LOCK_TRACKING
 	int			b_last_holder;
 #endif
@@ -140,22 +154,78 @@ typedef struct xfs_buf {
 
 
 /* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags,
-				struct xfs_buf *new_bp);
-#define xfs_incore(buftarg,blkno,len,lockit) \
-	_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
-
-struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks);
+struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
+			      struct xfs_buf_map *map, int nmaps,
+			      xfs_buf_flags_t flags, struct xfs_buf *new_bp);
+
+static inline struct xfs_buf *
+xfs_incore(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_find(target, &map, 1, flags, NULL);
+}
+
+struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+
+static inline struct xfs_buf *
+xfs_buf_alloc(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_alloc(target, &map, 1, flags);
+}
+
+struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+void xfs_buf_readahead_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps);
+
+static inline struct xfs_buf *
+xfs_buf_get(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_get_map(target, &map, 1, flags);
+}
+
+static inline struct xfs_buf *
+xfs_buf_read(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_read_map(target, &map, 1, flags);
+}
+
+static inline void
+xfs_buf_readahead(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_readahead_map(target, &map, 1);
+}
 
 struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
-struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
 void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
 int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
@@ -232,8 +302,18 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
 #define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
 
-#define XFS_BUF_ADDR(bp)		((bp)->b_bn)
-#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_bn = (xfs_daddr_t)(bno))
+/*
+ * These macros use the IO block map rather than b_bn. b_bn is now really
+ * just for the buffer cache index for cached buffers. As IO does not use b_bn
+ * anymore, uncached buffers do not use b_bn at all and hence must modify the IO
+ * map directly. Uncached buffers are not allowed to be discontiguous, so this
+ * is safe to do.
+ *
+ * In future, uncached buffers will pass the block number directly to the io
+ * request function and hence these macros will go away at that point.
+ */
+#define XFS_BUF_ADDR(bp)		((bp)->b_map.bm_bn)
+#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_map.bm_bn = (xfs_daddr_t)(bno))
 
 static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {

fs/xfs/xfs_buf_item.c

@@ -153,33 +153,25 @@ STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
  * If the XFS_BLI_STALE flag has been set, then log nothing.
  */
 STATIC uint
-xfs_buf_item_size(
-	struct xfs_log_item	*lip)
+xfs_buf_item_size_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_buf_log_format *blfp)
 {
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			nvecs;
 	int			next_bit;
 	int			last_bit;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	if (bip->bli_flags & XFS_BLI_STALE) {
-		/*
-		 * The buffer is stale, so all we need to log
-		 * is the buf log format structure with the
-		 * cancel flag in it.
-		 */
-		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		return 1;
-	}
+	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (last_bit == -1)
+		return 0;
+
+	/*
+	 * initial count for a dirty buffer is 2 vectors - the format structure
+	 * and the first dirty region.
+	 */
+	nvecs = 2;
 
-	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
-	nvecs = 1;
-	last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
-	ASSERT(last_bit != -1);
-	nvecs++;
 	while (last_bit != -1) {
 		/*
 		 * This takes the bit number to start looking from and
@@ -187,16 +179,15 @@ xfs_buf_item_size(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					last_bit + 1);
 		/*
 		 * If we run out of bits, leave the loop,
 		 * else if we find a new set of bits bump the number of vecs,
 		 * else keep scanning the current set of bits.
 		 */
 		if (next_bit == -1) {
-			last_bit = -1;
+			break;
 		} else if (next_bit != last_bit + 1) {
 			last_bit = next_bit;
 			nvecs++;
@@ -210,22 +201,73 @@ xfs_buf_item_size(
 		}
 	}
 
-	trace_xfs_buf_item_size(bip);
 	return nvecs;
 }
 
 /*
- * This is called to fill in the vector of log iovecs for the
- * given log buf item.  It fills the first entry with a buf log
- * format structure, and the rest point to contiguous chunks
- * within the buffer.
+ * This returns the number of log iovecs needed to log the given buf log item.
+ *
+ * It calculates this as 1 iovec for the buf log format structure and 1 for each
+ * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
+ * in a single iovec.
+ *
+ * Discontiguous buffers need a format structure per region that that is being
+ * logged. This makes the changes in the buffer appear to log recovery as though
+ * they came from separate buffers, just like would occur if multiple buffers
+ * were used instead of a single discontiguous buffer. This enables
+ * discontiguous buffers to be in-memory constructs, completely transparent to
+ * what ends up on disk.
+ *
+ * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
+ * format structures.
  */
-STATIC void
-xfs_buf_item_format(
-	struct xfs_log_item	*lip,
-	struct xfs_log_iovec	*vecp)
+STATIC uint
+xfs_buf_item_size(
+	struct xfs_log_item	*lip)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	uint			nvecs;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	if (bip->bli_flags & XFS_BLI_STALE) {
+		/*
+		 * The buffer is stale, so all we need to log
+		 * is the buf log format structure with the
+		 * cancel flag in it.
+		 */
+		trace_xfs_buf_item_size_stale(bip);
+		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		return bip->bli_format_count;
+	}
+
+	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
+
+	/*
+	 * the vector count is based on the number of buffer vectors we have
+	 * dirty bits in. This will only be greater than one when we have a
+	 * compound buffer with more than one segment dirty. Hence for compound
+	 * buffers we need to track which segment the dirty bits correspond to,
+	 * and when we move from one segment to the next increment the vector
+	 * count for the extra buf log format structure that will need to be
+	 * written.
+	 */
+	nvecs = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		nvecs += xfs_buf_item_size_segment(bip, &bip->bli_formats[i]);
+	}
+
+	trace_xfs_buf_item_size(bip);
+	return nvecs;
+}
+
+static struct xfs_log_iovec *
+xfs_buf_item_format_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_log_iovec	*vecp,
+	uint			offset,
+	struct xfs_buf_log_format *blfp)
+{
 	struct xfs_buf	*bp = bip->bli_buf;
 	uint		base_size;
 	uint		nvecs;
@@ -235,40 +277,22 @@ xfs_buf_item_format(
 	uint		nbits;
 	uint		buffer_offset;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
-	       (bip->bli_flags & XFS_BLI_STALE));
+	/* copy the flags across from the base format item */
+	blfp->blf_flags = bip->bli_format.blf_flags;
 
 	/*
-	 * The size of the base structure is the size of the
-	 * declared structure plus the space for the extra words
-	 * of the bitmap.  We subtract one from the map size, because
-	 * the first element of the bitmap is accounted for in the
-	 * size of the base structure.
+	 * Base size is the actual size of the ondisk structure - it reflects
+	 * the actual size of the dirty bitmap rather than the size of the in
+	 * memory structure.
 	 */
-	base_size =
-		(uint)(sizeof(xfs_buf_log_format_t) +
-		       ((bip->bli_format.blf_map_size - 1) * sizeof(uint)));
-	vecp->i_addr = &bip->bli_format;
+	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
+			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
+	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
 	vecp++;
 	nvecs = 1;
 
-	/*
-	 * If it is an inode buffer, transfer the in-memory state to the
-	 * format flags and clear the in-memory state. We do not transfer
-	 * this state if the inode buffer allocation has not yet been committed
-	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
-	 * correct replay of the inode allocation.
-	 */
-	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
-		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
-		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
-		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
-	}
-
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		/*
 		 * The buffer is stale, so all we need to log
@@ -276,16 +300,15 @@ xfs_buf_item_format(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_format_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		bip->bli_format.blf_size = nvecs;
-		return;
+		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
+		blfp->blf_size = nvecs;
+		return vecp;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	ASSERT(first_bit != -1);
 	last_bit = first_bit;
 	nbits = 1;
@@ -296,9 +319,8 @@ xfs_buf_item_format(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 (uint)last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)last_bit + 1);
 		/*
 		 * If we run out of bits fill in the last iovec and get
 		 * out of the loop.
@@ -309,14 +331,14 @@ xfs_buf_item_format(
 		 * keep counting and scanning.
 		 */
 		if (next_bit == -1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
 			nvecs++;
 			break;
 		} else if (next_bit != last_bit + 1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
@@ -325,14 +347,17 @@ xfs_buf_item_format(
 			first_bit = next_bit;
 			last_bit = next_bit;
 			nbits = 1;
-		} else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
-			   (xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
+		} else if (xfs_buf_offset(bp, offset +
+					      (next_bit << XFS_BLF_SHIFT)) !=
+			   (xfs_buf_offset(bp, offset +
+					       (last_bit << XFS_BLF_SHIFT)) +
 			    XFS_BLF_CHUNK)) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/* You would think we need to bump the nvecs here too, but we do not
+/*
+ * You would think we need to bump the nvecs here too, but we do not
  * this number is used by recovery, and it gets confused by the boundary
  * split here
  *			nvecs++;
@@ -347,6 +372,48 @@ xfs_buf_item_format(
 		}
 	}
 	bip->bli_format.blf_size = nvecs;
+	return vecp;
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the
+ * given log buf item.  It fills the first entry with a buf log
+ * format structure, and the rest point to contiguous chunks
+ * within the buffer.
+ */
+STATIC void
+xfs_buf_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_iovec	*vecp)
+{
+	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	struct xfs_buf		*bp = bip->bli_buf;
+	uint			offset = 0;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+	       (bip->bli_flags & XFS_BLI_STALE));
+
+	/*
+	 * If it is an inode buffer, transfer the in-memory state to the
+	 * format flags and clear the in-memory state. We do not transfer
+	 * this state if the inode buffer allocation has not yet been committed
+	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
+	 * correct replay of the inode allocation.
+	 */
+	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
+		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+		      xfs_log_item_in_current_chkpt(lip)))
+			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+	}
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		vecp = xfs_buf_item_format_segment(bip, vecp, offset,
+						&bip->bli_formats[i]);
+		offset += bp->b_maps[i].bm_len;
+	}
 
 	/*
 	 * Check to make sure everything is consistent.
@@ -622,6 +689,35 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_committing = xfs_buf_item_committing
 };
 
+STATIC int
+xfs_buf_item_get_format(
+	struct xfs_buf_log_item	*bip,
+	int			count)
+{
+	ASSERT(bip->bli_formats == NULL);
+	bip->bli_format_count = count;
+
+	if (count == 1) {
+		bip->bli_formats = &bip->bli_format;
+		return 0;
+	}
+
+	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
+				KM_SLEEP);
+	if (!bip->bli_formats)
+		return ENOMEM;
+	return 0;
+}
+
+STATIC void
+xfs_buf_item_free_format(
+	struct xfs_buf_log_item	*bip)
+{
+	if (bip->bli_formats != &bip->bli_format) {
+		kmem_free(bip->bli_formats);
+		bip->bli_formats = NULL;
+	}
+}
 
 /*
  * Allocate a new buf log item to go with the given buffer.
@@ -639,6 +735,8 @@ xfs_buf_item_init(
 	xfs_buf_log_item_t	*bip;
 	int			chunks;
 	int			map_size;
+	int			error;
+	int			i;
 
 	/*
 	 * Check to see if there is already a buf log item for
@@ -650,25 +748,33 @@ xfs_buf_item_init(
 	if (lip != NULL && lip->li_type == XFS_LI_BUF)
 		return;
 
-	/*
-	 * chunks is the number of XFS_BLF_CHUNK size pieces
-	 * the buffer can be divided into. Make sure not to
-	 * truncate any pieces.  map_size is the size of the
-	 * bitmap needed to describe the chunks of the buffer.
-	 */
-	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
-								XFS_BLF_SHIFT);
-	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
-
-	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
-						    KM_SLEEP);
+	bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
 	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
 	bip->bli_buf = bp;
 	xfs_buf_hold(bp);
-	bip->bli_format.blf_type = XFS_LI_BUF;
-	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)bp->b_length;
-	bip->bli_format.blf_map_size = map_size;
+
+	/*
+	 * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
+	 * can be divided into. Make sure not to truncate any pieces.
+	 * map_size is the size of the bitmap needed to describe the
+	 * chunks of the buffer.
+	 *
+	 * Discontiguous buffer support follows the layout of the underlying
+	 * buffer. This makes the implementation as simple as possible.
+	 */
+	error = xfs_buf_item_get_format(bip, bp->b_map_count);
+	ASSERT(error == 0);
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+				      XFS_BLF_CHUNK);
+		map_size = DIV_ROUND_UP(chunks, NBWORD);
+
+		bip->bli_formats[i].blf_type = XFS_LI_BUF;
+		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
+		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
+		bip->bli_formats[i].blf_map_size = map_size;
+	}
 
 #ifdef XFS_TRANS_DEBUG
 	/*
@@ -699,10 +805,11 @@ xfs_buf_item_init(
  * item's bitmap.
  */
 void
-xfs_buf_item_log(
-	xfs_buf_log_item_t	*bip,
+xfs_buf_item_log_segment(
+	struct xfs_buf_log_item	*bip,
 	uint			first,
-	uint			last)
+	uint			last,
+	uint			*map)
 {
 	uint		first_bit;
 	uint		last_bit;
@@ -714,12 +821,6 @@ xfs_buf_item_log(
 	uint		end_bit;
 	uint		mask;
 
-	/*
-	 * Mark the item as having some dirty data for
-	 * quick reference in xfs_buf_item_dirty.
-	 */
-	bip->bli_flags |= XFS_BLI_DIRTY;
-
 	/*
 	 * Convert byte offsets to bit numbers.
 	 */
@@ -736,7 +837,7 @@ xfs_buf_item_log(
 	 * to set a bit in.
 	 */
 	word_num = first_bit >> BIT_TO_WORD_SHIFT;
-	wordp = &(bip->bli_format.blf_data_map[word_num]);
+	wordp = &map[word_num];
 
 	/*
 	 * Calculate the starting bit in the first word.
@@ -783,6 +884,51 @@ xfs_buf_item_log(
 	xfs_buf_item_log_debug(bip, first, last);
 }
 
+/*
+ * Mark bytes first through last inclusive as dirty in the buf
+ * item's bitmap.
+ */
+void
+xfs_buf_item_log(
+	xfs_buf_log_item_t	*bip,
+	uint			first,
+	uint			last)
+{
+	int			i;
+	uint			start;
+	uint			end;
+	struct xfs_buf		*bp = bip->bli_buf;
+
+	/*
+	 * Mark the item as having some dirty data for
+	 * quick reference in xfs_buf_item_dirty.
+	 */
+	bip->bli_flags |= XFS_BLI_DIRTY;
+
+	/*
+	 * walk each buffer segment and mark them dirty appropriately.
+	 */
+	start = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (start > last)
+			break;
+		end = start + BBTOB(bp->b_maps[i].bm_len);
+		if (first > end) {
+			start += BBTOB(bp->b_maps[i].bm_len);
+			continue;
+		}
+		if (first < start)
+			first = start;
+		if (end > last)
+			end = last;
+
+		xfs_buf_item_log_segment(bip, first, end,
+					 &bip->bli_formats[i].blf_data_map[0]);
+
+		start += bp->b_maps[i].bm_len;
+	}
+}
+
 
 /*
  * Return 1 if the buffer has some data that has been logged (at any
@@ -804,6 +950,7 @@ xfs_buf_item_free(
 	kmem_free(bip->bli_logged);
 #endif /* XFS_TRANS_DEBUG */
 
+	xfs_buf_item_free_format(bip);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 

fs/xfs/xfs_buf_item.h

@@ -20,23 +20,6 @@
 
 extern kmem_zone_t	*xfs_buf_item_zone;
 
-/*
- * This is the structure used to lay out a buf log item in the
- * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.
- * For 6.2 and beyond, this is XFS_LI_BUF.  We use this to log everything.
- */
-typedef struct xfs_buf_log_format {
-	unsigned short	blf_type;	/* buf log item type indicator */
-	unsigned short	blf_size;	/* size of this item */
-	ushort		blf_flags;	/* misc state */
-	ushort		blf_len;	/* number of blocks in this buf */
-	__int64_t	blf_blkno;	/* starting blkno of this buf */
-	unsigned int	blf_map_size;	/* size of data bitmap in words */
-	unsigned int	blf_data_map[1];/* variable size bitmap of */
-					/*   regions of buffer in this item */
-} xfs_buf_log_format_t;
-
 /*
  * This flag indicates that the buffer contains on disk inodes
  * and requires special recovery handling.
@@ -60,6 +43,23 @@ typedef struct xfs_buf_log_format {
 #define	BIT_TO_WORD_SHIFT	5
 #define	NBWORD			(NBBY * sizeof(unsigned int))
 
+/*
+ * This is the structure used to lay out a buf log item in the
+ * log.  The data map describes which 128 byte chunks of the buffer
+ * have been logged.
+ */
+#define XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+
+typedef struct xfs_buf_log_format {
+	unsigned short	blf_type;	/* buf log item type indicator */
+	unsigned short	blf_size;	/* size of this item */
+	ushort		blf_flags;	/* misc state */
+	ushort		blf_len;	/* number of blocks in this buf */
+	__int64_t	blf_blkno;	/* starting blkno of this buf */
+	unsigned int	blf_map_size;	/* used size of data bitmap in words */
+	unsigned int	blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */
+} xfs_buf_log_format_t;
+
 /*
  * buf log item flags
  */
@@ -102,7 +102,9 @@ typedef struct xfs_buf_log_item {
 	char			*bli_orig;	/* original buffer copy */
 	char			*bli_logged;	/* bytes logged (bitmap) */
 #endif
-	xfs_buf_log_format_t	bli_format;	/* in-log header */
+	int			bli_format_count;	/* count of headers */
+	struct xfs_buf_log_format *bli_formats;	/* array of in-log header ptrs */
+	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
 void	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);

fs/xfs/xfs_da_btree.h

@@ -32,7 +32,7 @@ struct zone;
 /*
  * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
  *
- * Is is used to manage a doubly linked list of all blocks at the same
+ * 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 */
@@ -132,24 +132,6 @@ typedef struct xfs_da_args {
 	{ XFS_DA_OP_OKNOENT,	"OKNOENT" }, \
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }
 
-/*
- * Structure to describe buffer(s) for a block.
- * This is needed in the directory version 2 format case, when
- * multiple non-contiguous fsblocks might be needed to cover one
- * logical directory block.
- * If the buffer count is 1 then the data pointer points to the
- * same place as the b_addr field for the buffer, else to kmem_alloced memory.
- */
-typedef struct xfs_dabuf {
-	int		nbuf;		/* number of buffer pointers present */
-	short		dirty;		/* data needs to be copied back */
-	short		bbcount;	/* how large is data in bbs */
-	void		*data;		/* pointer for buffers' data */
-	struct xfs_buf	*bps[1];	/* actually nbuf of these */
-} xfs_dabuf_t;
-#define	XFS_DA_BUF_SIZE(n)	\
-	(sizeof(xfs_dabuf_t) + sizeof(struct xfs_buf *) * ((n) - 1))
-
 /*
  * Storage for holding state during Btree searches and split/join ops.
  *
@@ -158,7 +140,7 @@ typedef struct xfs_dabuf {
  * which is slightly more than enough.
  */
 typedef struct xfs_da_state_blk {
-	xfs_dabuf_t	*bp;		/* buffer containing block */
+	struct xfs_buf	*bp;		/* buffer containing block */
 	xfs_dablk_t	blkno;		/* filesystem blkno of buffer */
 	xfs_daddr_t	disk_blkno;	/* on-disk blkno (in BBs) of buffer */
 	int		index;		/* relevant index into block */
@@ -211,7 +193,7 @@ struct xfs_nameops {
  * Routines used for growing the Btree.
  */
 int	xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
-					 xfs_dabuf_t **bpp, int whichfork);
+					 struct xfs_buf **bpp, int whichfork);
 int	xfs_da_split(xfs_da_state_t *state);
 
 /*
@@ -241,14 +223,14 @@ int	xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
 			      int count);
 int	xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			      xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			      xfs_dabuf_t **bp, int whichfork);
+			      struct xfs_buf **bp, int whichfork);
 int	xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			       xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			       xfs_dabuf_t **bpp, int whichfork);
+			       struct xfs_buf **bpp, int whichfork);
 xfs_daddr_t	xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			xfs_dablk_t bno, int whichfork);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
-					  xfs_dabuf_t *dead_buf);
+					  struct xfs_buf *dead_buf);
 
 uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
@@ -258,15 +240,7 @@ enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 xfs_da_state_t *xfs_da_state_alloc(void);
 void xfs_da_state_free(xfs_da_state_t *state);
 
-void xfs_da_buf_done(xfs_dabuf_t *dabuf);
-void xfs_da_log_buf(struct xfs_trans *tp, xfs_dabuf_t *dabuf, uint first,
-			   uint last);
-void xfs_da_brelse(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-void xfs_da_binval(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
-
 extern struct kmem_zone *xfs_da_state_zone;
-extern struct kmem_zone *xfs_dabuf_zone;
 extern const struct xfs_nameops xfs_default_nameops;
 
 #endif	/* __XFS_DA_BTREE_H__ */

fs/xfs/xfs_dinode.h

@@ -33,7 +33,7 @@ typedef struct xfs_timestamp {
  * variable size the leftover area split into a data and an attribute fork.
  * The format of the data and attribute fork depends on the format of the
  * inode as indicated by di_format and di_aformat.  To access the data and
- * attribute use the XFS_DFORK_PTR, XFS_DFORK_DPTR, and XFS_DFORK_PTR macros
+ * attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
  * below.
  *
  * There is a very similar struct icdinode in xfs_inode which matches the

fs/xfs/xfs_dir2.c

@@ -592,7 +592,7 @@ int
 xfs_dir2_shrink_inode(
 	xfs_da_args_t	*args,
 	xfs_dir2_db_t	db,
-	xfs_dabuf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	xfs_fileoff_t	bno;		/* directory file offset */
 	xfs_dablk_t	da;		/* directory file offset */
@@ -634,7 +634,7 @@ xfs_dir2_shrink_inode(
 	/*
 	 * Invalidate the buffer from the transaction.
 	 */
-	xfs_da_binval(tp, bp);
+	xfs_trans_binval(tp, bp);
 	/*
 	 * If it's not a data block, we're done.
 	 */

fs/xfs/xfs_dir2_block.c

@@ -37,10 +37,10 @@
 /*
  * Local function prototypes.
  */
-static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, xfs_dabuf_t *bp, int first,
-				    int last);
-static void xfs_dir2_block_log_tail(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **bpp,
+static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp,
+				    int first, int last);
+static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp);
+static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp,
 				     int *entno);
 static int xfs_dir2_block_sort(const void *a, const void *b);
 
@@ -66,7 +66,7 @@ xfs_dir2_block_addname(
 	xfs_dir2_data_free_t	*bf;		/* bestfree table in block */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	int			compact;	/* need to compact leaf ents */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
@@ -102,14 +102,14 @@ xfs_dir2_block_addname(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	/*
 	 * Check the magic number, corrupted if wrong.
 	 */
 	if (unlikely(hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_dir2_block_addname",
 				     XFS_ERRLEVEL_LOW, mp, hdr);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 	len = xfs_dir2_data_entsize(args->namelen);
@@ -212,7 +212,7 @@ xfs_dir2_block_addname(
 	 * If this isn't a real add, we're done with the buffer.
 	 */
 	if (args->op_flags & XFS_DA_OP_JUSTCHECK)
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 	/*
 	 * If we don't have space for the new entry & leaf ...
 	 */
@@ -228,7 +228,6 @@ xfs_dir2_block_addname(
 		 * Then add the new entry in that format.
 		 */
 		error = xfs_dir2_block_to_leaf(args, bp);
-		xfs_da_buf_done(bp);
 		if (error)
 			return error;
 		return xfs_dir2_leaf_addname(args);
@@ -422,7 +421,6 @@ xfs_dir2_block_addname(
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_log_entry(tp, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -437,7 +435,7 @@ xfs_dir2_block_getdents(
 	filldir_t		filldir)
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
@@ -469,7 +467,7 @@ xfs_dir2_block_getdents(
 	 * We'll skip entries before this.
 	 */
 	wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	/*
 	 * Set up values for the loop.
@@ -514,7 +512,7 @@ xfs_dir2_block_getdents(
 			    cook & 0x7fffffff, be64_to_cpu(dep->inumber),
 			    DT_UNKNOWN)) {
 			*offset = cook & 0x7fffffff;
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return 0;
 		}
 	}
@@ -525,7 +523,7 @@ xfs_dir2_block_getdents(
 	 */
 	*offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
 			0x7fffffff;
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return 0;
 }
 
@@ -535,17 +533,17 @@ xfs_dir2_block_getdents(
 static void
 xfs_dir2_block_log_leaf(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,		/* block buffer */
 	int			first,		/* index of first logged leaf */
 	int			last)		/* index of last logged leaf */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_leaf_entry_t	*blp;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
-	xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
 		(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
 }
 
@@ -555,13 +553,13 @@ xfs_dir2_block_log_leaf(
 static void
 xfs_dir2_block_log_tail(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_buf		*bp)		/* block buffer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
-	xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
 		(uint)((char *)(btp + 1) - (char *)hdr - 1));
 }
 
@@ -575,7 +573,7 @@ xfs_dir2_block_lookup(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -593,7 +591,7 @@ xfs_dir2_block_lookup(
 		return error;
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -607,7 +605,7 @@ xfs_dir2_block_lookup(
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	return XFS_ERROR(error);
 }
 
@@ -617,13 +615,13 @@ xfs_dir2_block_lookup(
 static int					/* error */
 xfs_dir2_block_lookup_int(
 	xfs_da_args_t		*args,		/* dir lookup arguments */
-	xfs_dabuf_t		**bpp,		/* returned block buffer */
+	struct xfs_buf		**bpp,		/* returned block buffer */
 	int			*entno)		/* returned entry number */
 {
 	xfs_dir2_dataptr_t	addr;		/* data entry address */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -647,7 +645,7 @@ xfs_dir2_block_lookup_int(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -666,7 +664,7 @@ xfs_dir2_block_lookup_int(
 			high = mid - 1;
 		if (low > high) {
 			ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
-			xfs_da_brelse(tp, bp);
+			xfs_trans_brelse(tp, bp);
 			return XFS_ERROR(ENOENT);
 		}
 	}
@@ -714,7 +712,7 @@ xfs_dir2_block_lookup_int(
 	/*
 	 * No match, release the buffer and return ENOENT.
 	 */
-	xfs_da_brelse(tp, bp);
+	xfs_trans_brelse(tp, bp);
 	return XFS_ERROR(ENOENT);
 }
 
@@ -728,7 +726,7 @@ xfs_dir2_block_removename(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf pointer */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -753,7 +751,7 @@ xfs_dir2_block_removename(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -790,10 +788,9 @@ xfs_dir2_block_removename(
 	 * See if the size as a shortform is good enough.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		xfs_da_buf_done(bp);
+	if (size > XFS_IFORK_DSIZE(dp))
 		return 0;
-	}
+
 	/*
 	 * If it works, do the conversion.
 	 */
@@ -810,7 +807,7 @@ xfs_dir2_block_replace(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -829,7 +826,7 @@ xfs_dir2_block_replace(
 	}
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -844,7 +841,6 @@ xfs_dir2_block_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	xfs_dir2_data_log_entry(args->trans, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -871,8 +867,8 @@ xfs_dir2_block_sort(
 int						/* error */
 xfs_dir2_leaf_to_block(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp,		/* leaf buffer */
-	xfs_dabuf_t		*dbp)		/* data buffer */
+	struct xfs_buf		*lbp,		/* leaf buffer */
+	struct xfs_buf		*dbp)		/* data buffer */
 {
 	__be16			*bestsp;	/* leaf bests table */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
@@ -898,7 +894,7 @@ xfs_dir2_leaf_to_block(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
@@ -914,11 +910,9 @@ xfs_dir2_leaf_to_block(
 			if ((error =
 			    xfs_dir2_leaf_trim_data(args, lbp,
 				    (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
-				goto out;
-		} else {
-			error = 0;
-			goto out;
-		}
+				return error;
+		} else
+			return 0;
 	}
 	/*
 	 * Read the data block if we don't already have it, give up if it fails.
@@ -926,9 +920,9 @@ xfs_dir2_leaf_to_block(
 	if (dbp == NULL &&
 	    (error = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &dbp,
 		    XFS_DATA_FORK))) {
-		goto out;
+		return error;
 	}
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 	/*
 	 * Size of the "leaf" area in the block.
@@ -944,10 +938,9 @@ xfs_dir2_leaf_to_block(
 	 * If it's not free or is too short we can't do it.
 	 */
 	if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG ||
-	    be16_to_cpu(dup->length) < size) {
-		error = 0;
-		goto out;
-	}
+	    be16_to_cpu(dup->length) < size)
+		return 0;
+
 	/*
 	 * Start converting it to block form.
 	 */
@@ -989,25 +982,17 @@ xfs_dir2_leaf_to_block(
 	 * Pitch the old leaf block.
 	 */
 	error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
-	lbp = NULL;
-	if (error) {
-		goto out;
-	}
+	if (error)
+		return error;
+
 	/*
 	 * Now see if the resulting block can be shrunken to shortform.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		error = 0;
-		goto out;
-	}
+	if (size > XFS_IFORK_DSIZE(dp))
+		return 0;
+
 	return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
-out:
-	if (lbp)
-		xfs_da_buf_done(lbp);
-	if (dbp)
-		xfs_da_buf_done(dbp);
-	return error;
 }
 
 /*
@@ -1020,7 +1005,7 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_db_t		blkno;		/* dir-relative block # (0) */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail pointer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -1088,7 +1073,7 @@ xfs_dir2_sf_to_block(
 		kmem_free(sfp);
 		return error;
 	}
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
 	/*
 	 * Compute size of block "tail" area.
@@ -1217,6 +1202,5 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }

fs/xfs/xfs_dir2_data.c

@@ -42,8 +42,8 @@ xfs_dir2_data_freefind(xfs_dir2_data_hdr_t *hdr, xfs_dir2_data_unused_t *dup);
  */
 void
 xfs_dir2_data_check(
-	xfs_inode_t		*dp,		/* incore inode pointer */
-	xfs_dabuf_t		*bp)		/* data block's buffer */
+	struct xfs_inode	*dp,		/* incore inode pointer */
+	struct xfs_buf		*bp)		/* data block's buffer */
 {
 	xfs_dir2_dataptr_t	addr;		/* addr for leaf lookup */
 	xfs_dir2_data_free_t	*bf;		/* bestfree table */
@@ -65,7 +65,7 @@ xfs_dir2_data_check(
 	struct xfs_name		name;
 
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	bf = hdr->bestfree;
 	p = (char *)(hdr + 1);
 
@@ -389,9 +389,9 @@ int						/* error */
 xfs_dir2_data_init(
 	xfs_da_args_t		*args,		/* directory operation args */
 	xfs_dir2_db_t		blkno,		/* logical dir block number */
-	xfs_dabuf_t		**bpp)		/* output block buffer */
+	struct xfs_buf		**bpp)		/* output block buffer */
 {
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry pointer */
@@ -417,7 +417,7 @@ xfs_dir2_data_init(
 	/*
 	 * Initialize the header.
 	 */
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
 	hdr->bestfree[0].offset = cpu_to_be16(sizeof(*hdr));
 	for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
@@ -449,16 +449,16 @@ xfs_dir2_data_init(
  */
 void
 xfs_dir2_data_log_entry(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
 		(uint)((char *)(xfs_dir2_data_entry_tag_p(dep) + 1) -
 		       (char *)hdr - 1));
 }
@@ -468,15 +468,15 @@ xfs_dir2_data_log_entry(
  */
 void
 xfs_dir2_data_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
+	xfs_trans_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
 }
 
 /*
@@ -484,11 +484,11 @@ xfs_dir2_data_log_header(
  */
 void
 xfs_dir2_data_log_unused(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup)		/* data unused pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
@@ -496,13 +496,13 @@ xfs_dir2_data_log_unused(
 	/*
 	 * Log the first part of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
 		(uint)((char *)&dup->length + sizeof(dup->length) -
 		       1 - (char *)hdr));
 	/*
 	 * Log the end (tag) of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
 		       sizeof(xfs_dir2_data_off_t) - 1));
@@ -514,8 +514,8 @@ xfs_dir2_data_log_unused(
  */
 void
 xfs_dir2_data_make_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
 	xfs_dir2_data_aoff_t	len,		/* length in bytes */
 	int			*needlogp,	/* out: log header */
@@ -531,7 +531,7 @@ xfs_dir2_data_make_free(
 	xfs_dir2_data_unused_t	*prevdup;	/* unused entry before us */
 
 	mp = tp->t_mountp;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 
 	/*
 	 * Figure out where the end of the data area is.
@@ -696,8 +696,8 @@ xfs_dir2_data_make_free(
  */
 void
 xfs_dir2_data_use_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* data block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup,		/* unused entry */
 	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
 	xfs_dir2_data_aoff_t	len,		/* length to use */
@@ -713,7 +713,7 @@ xfs_dir2_data_use_free(
 	xfs_dir2_data_unused_t	*newdup2;	/* another new unused entry */
 	int			oldlen;		/* old unused entry's length */
 
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 	ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);

fs/xfs/xfs_dir2_node.c

@@ -36,20 +36,20 @@
 /*
  * Function declarations.
  */
-static void xfs_dir2_free_log_header(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_leafn_add(xfs_dabuf_t *bp, xfs_da_args_t *args, int index);
+static int xfs_dir2_leafn_add(struct xfs_buf *bp, xfs_da_args_t *args,
+			      int index);
 #ifdef DEBUG
-static void xfs_dir2_leafn_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+static void xfs_dir2_leafn_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_leafn_check(dp, bp)
 #endif
-static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, xfs_dabuf_t *bp_s,
-				    int start_s, xfs_dabuf_t *bp_d, int start_d,
-				    int count);
+static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, struct xfs_buf *bp_s,
+				    int start_s, struct xfs_buf *bp_d,
+				    int start_d, int count);
 static void xfs_dir2_leafn_rebalance(xfs_da_state_t *state,
 				     xfs_da_state_blk_t *blk1,
 				     xfs_da_state_blk_t *blk2);
-static int xfs_dir2_leafn_remove(xfs_da_args_t *args, xfs_dabuf_t *bp,
+static int xfs_dir2_leafn_remove(xfs_da_args_t *args, struct xfs_buf *bp,
 				 int index, xfs_da_state_blk_t *dblk,
 				 int *rval);
 static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
@@ -60,16 +60,16 @@ static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
  */
 STATIC void
 xfs_dir2_free_log_bests(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)&free->bests[first] - (char *)free),
 		(uint)((char *)&free->bests[last] - (char *)free +
 		       sizeof(free->bests[0]) - 1));
@@ -80,14 +80,14 @@ xfs_dir2_free_log_bests(
  */
 static void
 xfs_dir2_free_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
 		(uint)(sizeof(xfs_dir2_free_hdr_t) - 1));
 }
 
@@ -99,11 +99,11 @@ xfs_dir2_free_log_header(
 int						/* error */
 xfs_dir2_leaf_to_node(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp)		/* leaf buffer */
+	struct xfs_buf		*lbp)		/* leaf buffer */
 {
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	xfs_dir2_db_t		fdb;		/* freespace block number */
 	xfs_dir2_free_t		*free;		/* freespace structure */
 	__be16			*from;		/* pointer to freespace entry */
@@ -136,8 +136,8 @@ xfs_dir2_leaf_to_node(
 		return error;
 	}
 	ASSERT(fbp != NULL);
-	free = fbp->data;
-	leaf = lbp->data;
+	free = fbp->b_addr;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
 	 * Initialize the freespace block header.
@@ -164,7 +164,6 @@ xfs_dir2_leaf_to_node(
 	xfs_dir2_leaf_log_header(tp, lbp);
 	xfs_dir2_free_log_header(tp, fbp);
 	xfs_dir2_free_log_bests(tp, fbp, 0, be32_to_cpu(free->hdr.nvalid) - 1);
-	xfs_da_buf_done(fbp);
 	xfs_dir2_leafn_check(dp, lbp);
 	return 0;
 }
@@ -175,7 +174,7 @@ xfs_dir2_leaf_to_node(
  */
 static int					/* error */
 xfs_dir2_leafn_add(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			index)		/* insertion pt for new entry */
 {
@@ -195,7 +194,7 @@ xfs_dir2_leafn_add(
 	dp = args->dp;
 	mp = dp->i_mount;
 	tp = args->trans;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 
 	/*
 	 * Quick check just to make sure we are not going to index
@@ -261,15 +260,15 @@ xfs_dir2_leafn_add(
  */
 void
 xfs_dir2_leafn_check(
-	xfs_inode_t	*dp,			/* incore directory inode */
-	xfs_dabuf_t	*bp)			/* leaf buffer */
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	int		i;			/* leaf index */
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 	xfs_mount_t	*mp;			/* filesystem mount point */
 	int		stale;			/* count of stale leaves */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	mp = dp->i_mount;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
@@ -291,12 +290,12 @@ xfs_dir2_leafn_check(
  */
 xfs_dahash_t					/* hash value */
 xfs_dir2_leafn_lasthash(
-	xfs_dabuf_t	*bp,			/* leaf buffer */
+	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
 {
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -311,12 +310,12 @@ xfs_dir2_leafn_lasthash(
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_addname(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_db_t		curfdb = -1;	/* current free block number */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -335,7 +334,7 @@ xfs_dir2_leafn_lookup_for_addname(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -352,7 +351,7 @@ xfs_dir2_leafn_lookup_for_addname(
 		/* If so, it's a free block buffer, get the block number. */
 		curbp = state->extrablk.bp;
 		curfdb = state->extrablk.blkno;
-		free = curbp->data;
+		free = curbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	}
 	length = xfs_dir2_data_entsize(args->namelen);
@@ -394,7 +393,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				 * If we had one before, drop it.
 				 */
 				if (curbp)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				/*
 				 * Read the free block.
 				 */
@@ -403,7 +402,7 @@ xfs_dir2_leafn_lookup_for_addname(
 						-1, &curbp, XFS_DATA_FORK);
 				if (error)
 					return error;
-				free = curbp->data;
+				free = curbp->b_addr;
 				ASSERT(be32_to_cpu(free->hdr.magic) ==
 					XFS_DIR2_FREE_MAGIC);
 				ASSERT((be32_to_cpu(free->hdr.firstdb) %
@@ -424,7 +423,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
 							XFS_ERRLEVEL_LOW, mp);
 				if (curfdb != newfdb)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				return XFS_ERROR(EFSCORRUPTED);
 			}
 			curfdb = newfdb;
@@ -459,12 +458,12 @@ out:
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_entry(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -480,7 +479,7 @@ xfs_dir2_leafn_lookup_for_entry(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -525,7 +524,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			 */
 			if (curbp && (args->cmpresult == XFS_CMP_DIFFERENT ||
 						curdb != state->extrablk.blkno))
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 			/*
 			 * If needing the block that is saved with a CI match,
 			 * use it otherwise read in the new data block.
@@ -547,7 +546,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		/*
 		 * Point to the data entry.
 		 */
-		dep = (xfs_dir2_data_entry_t *)((char *)curbp->data +
+		dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
 			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
 		/*
 		 * Compare the entry and if it's an exact match, return
@@ -559,7 +558,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			/* If there is a CI match block, drop it */
 			if (args->cmpresult != XFS_CMP_DIFFERENT &&
 						curdb != state->extrablk.blkno)
-				xfs_da_brelse(tp, state->extrablk.bp);
+				xfs_trans_brelse(tp, state->extrablk.bp);
 			args->cmpresult = cmp;
 			args->inumber = be64_to_cpu(dep->inumber);
 			*indexp = index;
@@ -567,7 +566,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			state->extrablk.bp = curbp;
 			state->extrablk.blkno = curdb;
 			state->extrablk.index = (int)((char *)dep -
-							(char *)curbp->data);
+							(char *)curbp->b_addr);
 			state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
 			if (cmp == XFS_CMP_EXACT)
 				return XFS_ERROR(EEXIST);
@@ -586,7 +585,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		} else {
 			/* If the curbp is not the CI match block, drop it */
 			if (state->extrablk.bp != curbp)
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 		}
 	} else {
 		state->extravalid = 0;
@@ -602,7 +601,7 @@ xfs_dir2_leafn_lookup_for_entry(
  */
 int
 xfs_dir2_leafn_lookup_int(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
@@ -620,9 +619,9 @@ xfs_dir2_leafn_lookup_int(
 static void
 xfs_dir2_leafn_moveents(
 	xfs_da_args_t	*args,			/* operation arguments */
-	xfs_dabuf_t	*bp_s,			/* source leaf buffer */
+	struct xfs_buf	*bp_s,			/* source leaf buffer */
 	int		start_s,		/* source leaf index */
-	xfs_dabuf_t	*bp_d,			/* destination leaf buffer */
+	struct xfs_buf	*bp_d,			/* destination leaf buffer */
 	int		start_d,		/* destination leaf index */
 	int		count)			/* count of leaves to copy */
 {
@@ -640,8 +639,8 @@ xfs_dir2_leafn_moveents(
 		return;
 	}
 	tp = args->trans;
-	leaf_s = bp_s->data;
-	leaf_d = bp_d->data;
+	leaf_s = bp_s->b_addr;
+	leaf_d = bp_d->b_addr;
 	/*
 	 * If the destination index is not the end of the current
 	 * destination leaf entries, open up a hole in the destination
@@ -702,14 +701,14 @@ xfs_dir2_leafn_moveents(
  */
 int						/* sort order */
 xfs_dir2_leafn_order(
-	xfs_dabuf_t	*leaf1_bp,		/* leaf1 buffer */
-	xfs_dabuf_t	*leaf2_bp)		/* leaf2 buffer */
+	struct xfs_buf	*leaf1_bp,		/* leaf1 buffer */
+	struct xfs_buf	*leaf2_bp)		/* leaf2 buffer */
 {
 	xfs_dir2_leaf_t	*leaf1;			/* leaf1 structure */
 	xfs_dir2_leaf_t	*leaf2;			/* leaf2 structure */
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (be16_to_cpu(leaf1->hdr.count) > 0 &&
@@ -757,8 +756,8 @@ xfs_dir2_leafn_rebalance(
 		blk1 = blk2;
 		blk2 = tmp;
 	}
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	oldsum = be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count);
 #ifdef DEBUG
 	oldstale = be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale);
@@ -834,14 +833,14 @@ xfs_dir2_leafn_rebalance(
 static int					/* error */
 xfs_dir2_leafn_remove(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			index,		/* leaf entry index */
 	xfs_da_state_blk_t	*dblk,		/* data block */
 	int			*rval)		/* resulting block needs join */
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		db;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -858,7 +857,7 @@ xfs_dir2_leafn_remove(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
 	 * Point to the entry we're removing.
@@ -884,7 +883,7 @@ xfs_dir2_leafn_remove(
 	 * in the data block in case it changes.
 	 */
 	dbp = dblk->bp;
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	dep = (xfs_dir2_data_entry_t *)((char *)hdr + off);
 	longest = be16_to_cpu(hdr->bestfree[0].length);
 	needlog = needscan = 0;
@@ -905,7 +904,7 @@ xfs_dir2_leafn_remove(
 	 */
 	if (longest < be16_to_cpu(hdr->bestfree[0].length)) {
 		int		error;		/* error return value */
-		xfs_dabuf_t	*fbp;		/* freeblock buffer */
+		struct xfs_buf	*fbp;		/* freeblock buffer */
 		xfs_dir2_db_t	fdb;		/* freeblock block number */
 		int		findex;		/* index in freeblock entries */
 		xfs_dir2_free_t	*free;		/* freeblock structure */
@@ -920,7 +919,7 @@ xfs_dir2_leafn_remove(
 				-1, &fbp, XFS_DATA_FORK))) {
 			return error;
 		}
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		ASSERT(be32_to_cpu(free->hdr.firstdb) ==
 		       xfs_dir2_free_max_bests(mp) *
@@ -948,9 +947,7 @@ xfs_dir2_leafn_remove(
 			 * In this case just drop the buffer and some one else
 			 * will eventually get rid of the empty block.
 			 */
-			else if (error == ENOSPC && args->total == 0)
-				xfs_da_buf_done(dbp);
-			else
+			else if (!(error == ENOSPC && args->total == 0))
 				return error;
 		}
 		/*
@@ -1018,11 +1015,6 @@ xfs_dir2_leafn_remove(
 		 */
 		if (logfree)
 			xfs_dir2_free_log_bests(tp, fbp, findex, findex);
-		/*
-		 * Drop the buffer if we still have it.
-		 */
-		if (fbp)
-			xfs_da_buf_done(fbp);
 	}
 	xfs_dir2_leafn_check(dp, bp);
 	/*
@@ -1114,7 +1106,7 @@ xfs_dir2_leafn_toosmall(
 {
 	xfs_da_state_blk_t	*blk;		/* leaf block */
 	xfs_dablk_t		blkno;		/* leaf block number */
-	xfs_dabuf_t		*bp;		/* leaf buffer */
+	struct xfs_buf		*bp;		/* leaf buffer */
 	int			bytes;		/* bytes in use */
 	int			count;		/* leaf live entry count */
 	int			error;		/* error return value */
@@ -1130,7 +1122,7 @@ xfs_dir2_leafn_toosmall(
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[state->path.active - 1];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	leaf = (xfs_dir2_leaf_t *)info;
 	count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
@@ -1189,7 +1181,7 @@ xfs_dir2_leafn_toosmall(
 		leaf = (xfs_dir2_leaf_t *)info;
 		count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes = state->blocksize - (state->blocksize >> 2);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes -= count * (uint)sizeof(leaf->ents[0]);
@@ -1198,7 +1190,7 @@ xfs_dir2_leafn_toosmall(
 		 */
 		if (bytes >= 0)
 			break;
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 	}
 	/*
 	 * Didn't like either block, give up.
@@ -1207,11 +1199,7 @@ xfs_dir2_leafn_toosmall(
 		*action = 0;
 		return 0;
 	}
-	/*
-	 * Done with the sibling leaf block here, drop the dabuf
-	 * so path_shift can get it.
-	 */
-	xfs_da_buf_done(bp);
+
 	/*
 	 * Make altpath point to the block we want to keep (the lower
 	 * numbered block) and path point to the block we want to drop.
@@ -1247,8 +1235,8 @@ xfs_dir2_leafn_unbalance(
 	args = state->args;
 	ASSERT(drop_blk->magic == XFS_DIR2_LEAFN_MAGIC);
 	ASSERT(save_blk->magic == XFS_DIR2_LEAFN_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
@@ -1356,13 +1344,13 @@ xfs_dir2_node_addname_int(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		dbno;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* data unused entry pointer */
 	int			error;		/* error return value */
 	xfs_dir2_db_t		fbno;		/* freespace block number */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	int			findex;		/* freespace entry index */
 	xfs_dir2_free_t		*free=NULL;	/* freespace block structure */
 	xfs_dir2_db_t		ifbno;		/* initial freespace block no */
@@ -1390,7 +1378,7 @@ xfs_dir2_node_addname_int(
 		 * Remember initial freespace block number.
 		 */
 		ifbno = fblk->blkno;
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		findex = fblk->index;
 		/*
@@ -1474,7 +1462,7 @@ xfs_dir2_node_addname_int(
 			if (unlikely(fbp == NULL)) {
 				continue;
 			}
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 			findex = 0;
 		}
@@ -1492,7 +1480,7 @@ xfs_dir2_node_addname_int(
 				/*
 				 * Drop the block.
 				 */
-				xfs_da_brelse(tp, fbp);
+				xfs_trans_brelse(tp, fbp);
 				fbp = NULL;
 				if (fblk && fblk->bp)
 					fblk->bp = NULL;
@@ -1507,36 +1495,23 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Not allowed to allocate, return failure.
 		 */
-		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
-							args->total == 0) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
 			return XFS_ERROR(ENOSPC);
-		}
+
 		/*
 		 * Allocate and initialize the new data block.
 		 */
 		if (unlikely((error = xfs_dir2_grow_inode(args,
 							 XFS_DIR2_DATA_SPACE,
 							 &dbno)) ||
-		    (error = xfs_dir2_data_init(args, dbno, &dbp)))) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		    (error = xfs_dir2_data_init(args, dbno, &dbp))))
 			return error;
-		}
+
 		/*
 		 * If (somehow) we have a freespace block, get rid of it.
 		 */
 		if (fbp)
-			xfs_da_brelse(tp, fbp);
+			xfs_trans_brelse(tp, fbp);
 		if (fblk && fblk->bp)
 			fblk->bp = NULL;
 
@@ -1547,10 +1522,9 @@ xfs_dir2_node_addname_int(
 		fbno = xfs_dir2_db_to_fdb(mp, dbno);
 		if (unlikely(error = xfs_da_read_buf(tp, dp,
 				xfs_dir2_db_to_da(mp, fbno), -2, &fbp,
-				XFS_DATA_FORK))) {
-			xfs_da_buf_done(dbp);
+				XFS_DATA_FORK)))
 			return error;
-  		}
+
 		/*
 		 * If there wasn't a freespace block, the read will
 		 * return a NULL fbp.  Allocate and initialize a new one.
@@ -1598,7 +1572,7 @@ xfs_dir2_node_addname_int(
 			 * Initialize the new block to be empty, and remember
 			 * its first slot as our empty slot.
 			 */
-			free = fbp->data;
+			free = fbp->b_addr;
 			free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
 			free->hdr.firstdb = cpu_to_be32(
 				(fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
@@ -1606,7 +1580,7 @@ xfs_dir2_node_addname_int(
 			free->hdr.nvalid = 0;
 			free->hdr.nused = 0;
 		} else {
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		}
 
@@ -1639,7 +1613,7 @@ xfs_dir2_node_addname_int(
 		 * We haven't allocated the data entry yet so this will
 		 * change again.
 		 */
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		free->bests[findex] = hdr->bestfree[0].length;
 		logfree = 1;
 	}
@@ -1650,22 +1624,17 @@ xfs_dir2_node_addname_int(
 		/*
 		 * If just checking, we succeeded.
 		 */
-		if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if (args->op_flags & XFS_DA_OP_JUSTCHECK)
 			return 0;
-		}
+
 		/*
 		 * Read the data block in.
 		 */
-		if (unlikely(
-		    error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
-				-1, &dbp, XFS_DATA_FORK))) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
+				-1, &dbp, XFS_DATA_FORK);
+		if (error)
 			return error;
-		}
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		logfree = 0;
 	}
 	ASSERT(be16_to_cpu(hdr->bestfree[0].length) >= length);
@@ -1713,17 +1682,11 @@ xfs_dir2_node_addname_int(
 	 */
 	if (logfree)
 		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
-	/*
-	 * If the caller didn't hand us the freespace block, drop it.
-	 */
-	if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-		xfs_da_buf_done(fbp);
 	/*
 	 * Return the data block and offset in args, then drop the data block.
 	 */
 	args->blkno = (xfs_dablk_t)dbno;
 	args->index = be16_to_cpu(*tagp);
-	xfs_da_buf_done(dbp);
 	return 0;
 }
 
@@ -1761,22 +1724,23 @@ xfs_dir2_node_lookup(
 		/* If a CI match, dup the actual name and return EEXIST */
 		xfs_dir2_data_entry_t	*dep;
 
-		dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp->
-						data + state->extrablk.index);
+		dep = (xfs_dir2_data_entry_t *)
+			((char *)state->extrablk.bp->b_addr +
+						 state->extrablk.index);
 		rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
 	}
 	/*
 	 * Release the btree blocks and leaf block.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	/*
 	 * Release the data block if we have it.
 	 */
 	if (state->extravalid && state->extrablk.bp) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1893,13 +1857,13 @@ xfs_dir2_node_replace(
 		 */
 		blk = &state->path.blk[state->path.active - 1];
 		ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
-		leaf = blk->bp->data;
+		leaf = blk->bp->b_addr;
 		lep = &leaf->ents[blk->index];
 		ASSERT(state->extravalid);
 		/*
 		 * Point to the data entry.
 		 */
-		hdr = state->extrablk.bp->data;
+		hdr = state->extrablk.bp->b_addr;
 		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 		dep = (xfs_dir2_data_entry_t *)
 		      ((char *)hdr +
@@ -1916,14 +1880,14 @@ xfs_dir2_node_replace(
 	 * Didn't find it, and we're holding a data block.  Drop it.
 	 */
 	else if (state->extravalid) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	/*
 	 * Release all the buffers in the cursor.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1940,7 +1904,7 @@ xfs_dir2_node_trim_free(
 	xfs_fileoff_t		fo,		/* free block number */
 	int			*rvalp)		/* out: did something */
 {
-	xfs_dabuf_t		*bp;		/* freespace buffer */
+	struct xfs_buf		*bp;		/* freespace buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_free_t		*free;		/* freespace structure */
@@ -1965,13 +1929,13 @@ xfs_dir2_node_trim_free(
 	if (bp == NULL) {
 		return 0;
 	}
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	/*
 	 * If there are used entries, there's nothing to do.
 	 */
 	if (be32_to_cpu(free->hdr.nused) > 0) {
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		*rvalp = 0;
 		return 0;
 	}
@@ -1987,7 +1951,7 @@ xfs_dir2_node_trim_free(
 		 * pieces.  This is the last block of an extent.
 		 */
 		ASSERT(error != ENOSPC);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return error;
 	}
 	/*

fs/xfs/xfs_dir2_priv.h

@@ -25,7 +25,7 @@ extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
 extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
 				xfs_dir2_db_t *dbp);
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
-				struct xfs_dabuf *bp);
+				struct xfs_buf *bp);
 extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
 				const unsigned char *name, int len);
 
@@ -37,11 +37,11 @@ extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_block_removename(struct xfs_da_args *args);
 extern int xfs_dir2_block_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, struct xfs_dabuf *dbp);
+		struct xfs_buf *lbp, struct xfs_buf *dbp);
 
 /* xfs_dir2_data.c */
 #ifdef DEBUG
-extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_dabuf *bp);
+extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_data_check(dp,bp)
 #endif
@@ -51,43 +51,43 @@ xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
 extern void xfs_dir2_data_freescan(struct xfs_mount *mp,
 		struct xfs_dir2_data_hdr *hdr, int *loghead);
 extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
-		struct xfs_dabuf **bpp);
-extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp);
+extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_entry *dep);
 extern void xfs_dir2_data_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup);
-extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
 		int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup, xfs_dir2_data_aoff_t offset,
 		xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
 
 /* xfs_dir2_leaf.c */
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
-		struct xfs_dabuf *dbp);
+		struct xfs_buf *dbp);
 extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);
 extern void xfs_dir2_leaf_compact(struct xfs_da_args *args,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_leaf_compact_x1(struct xfs_dabuf *bp, int *indexp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_leaf_compact_x1(struct xfs_buf *bp, int *indexp,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir2_leaf_getdents(struct xfs_inode *dp, void *dirent,
 		size_t bufsize, xfs_off_t *offset, filldir_t filldir);
 extern int xfs_dir2_leaf_init(struct xfs_da_args *args, xfs_dir2_db_t bno,
-		struct xfs_dabuf **bpp, int magic);
-extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp, int magic);
+extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_buf *bp,
 		int first, int last);
 extern void xfs_dir2_leaf_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
+		struct xfs_buf *bp);
 extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_search_hash(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
+		struct xfs_buf *lbp);
 extern int xfs_dir2_leaf_trim_data(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, xfs_dir2_db_t db);
+		struct xfs_buf *lbp, xfs_dir2_db_t db);
 extern struct xfs_dir2_leaf_entry *
 xfs_dir2_leaf_find_entry(struct xfs_dir2_leaf *leaf, int index, int compact,
 		int lowstale, int highstale,
@@ -96,13 +96,13 @@ extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_dabuf *bp, int *count);
-extern int xfs_dir2_leafn_lookup_int(struct xfs_dabuf *bp,
+		struct xfs_buf *lbp);
+extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_buf *bp, int *count);
+extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp,
 		struct xfs_da_args *args, int *indexp,
 		struct xfs_da_state *state);
-extern int xfs_dir2_leafn_order(struct xfs_dabuf *leaf1_bp,
-		struct xfs_dabuf *leaf2_bp);
+extern int xfs_dir2_leafn_order(struct xfs_buf *leaf1_bp,
+		struct xfs_buf *leaf2_bp);
 extern int xfs_dir2_leafn_split(struct xfs_da_state *state,
 	struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk);
 extern int xfs_dir2_leafn_toosmall(struct xfs_da_state *state, int *action);
@@ -122,7 +122,7 @@ extern xfs_ino_t xfs_dir2_sfe_get_ino(struct xfs_dir2_sf_hdr *sfp,
 		struct xfs_dir2_sf_entry *sfep);
 extern int xfs_dir2_block_sfsize(struct xfs_inode *dp,
 		struct xfs_dir2_data_hdr *block, struct xfs_dir2_sf_hdr *sfhp);
-extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_dabuf *bp,
+extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_buf *bp,
 		int size, xfs_dir2_sf_hdr_t *sfhp);
 extern int xfs_dir2_sf_addname(struct xfs_da_args *args);
 extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);

fs/xfs/xfs_dir2_sf.c

@@ -222,7 +222,7 @@ xfs_dir2_block_sfsize(
 int						/* error */
 xfs_dir2_block_to_sf(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,
 	int			size,		/* shortform directory size */
 	xfs_dir2_sf_hdr_t	*sfhp)		/* shortform directory hdr */
 {
@@ -249,7 +249,7 @@ xfs_dir2_block_to_sf(
 	 * and add local data.
 	 */
 	hdr = kmem_alloc(mp->m_dirblksize, KM_SLEEP);
-	memcpy(hdr, bp->data, mp->m_dirblksize);
+	memcpy(hdr, bp->b_addr, mp->m_dirblksize);
 	logflags = XFS_ILOG_CORE;
 	if ((error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp))) {
 		ASSERT(error != ENOSPC);

fs/xfs/xfs_file.c

@@ -236,7 +236,6 @@ xfs_file_aio_read(
 	ssize_t			ret = 0;
 	int			ioflags = 0;
 	xfs_fsize_t		n;
-	unsigned long		seg;
 
 	XFS_STATS_INC(xs_read_calls);
 
@@ -247,19 +246,9 @@ xfs_file_aio_read(
 	if (file->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
 
-	/* START copy & waste from filemap.c */
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *iv = &iovp[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		size += iv->iov_len;
-		if (unlikely((ssize_t)(size|iv->iov_len) < 0))
-			return XFS_ERROR(-EINVAL);
-	}
-	/* END copy & waste from filemap.c */
+	ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
+	if (ret < 0)
+		return ret;
 
 	if (unlikely(ioflags & IO_ISDIRECT)) {
 		xfs_buftarg_t	*target =
@@ -273,7 +262,7 @@ xfs_file_aio_read(
 		}
 	}
 
-	n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
+	n = mp->m_super->s_maxbytes - iocb->ki_pos;
 	if (n <= 0 || size == 0)
 		return 0;
 

fs/xfs/xfs_ialloc.c

@@ -442,14 +442,13 @@ xfs_ialloc_next_ag(
  * Select an allocation group to look for a free inode in, based on the parent
  * inode and then mode.  Return the allocation group buffer.
  */
-STATIC xfs_buf_t *			/* allocation group buffer */
+STATIC xfs_agnumber_t
 xfs_ialloc_ag_select(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_ino_t	parent,		/* parent directory inode number */
 	umode_t		mode,		/* bits set to indicate file type */
 	int		okalloc)	/* ok to allocate more space */
 {
-	xfs_buf_t	*agbp;		/* allocation group header buffer */
 	xfs_agnumber_t	agcount;	/* number of ag's in the filesystem */
 	xfs_agnumber_t	agno;		/* current ag number */
 	int		flags;		/* alloc buffer locking flags */
@@ -459,6 +458,7 @@ xfs_ialloc_ag_select(
 	int		needspace;	/* file mode implies space allocated */
 	xfs_perag_t	*pag;		/* per allocation group data */
 	xfs_agnumber_t	pagno;		/* parent (starting) ag number */
+	int		error;
 
 	/*
 	 * Files of these types need at least one block if length > 0
@@ -474,7 +474,9 @@ xfs_ialloc_ag_select(
 		if (pagno >= agcount)
 			pagno = 0;
 	}
+
 	ASSERT(pagno < agcount);
+
 	/*
 	 * Loop through allocation groups, looking for one with a little
 	 * free space in it.  Note we don't look for free inodes, exactly.
@@ -486,51 +488,45 @@ xfs_ialloc_ag_select(
 	flags = XFS_ALLOC_FLAG_TRYLOCK;
 	for (;;) {
 		pag = xfs_perag_get(mp, agno);
+		if (!pag->pagi_inodeok) {
+			xfs_ialloc_next_ag(mp);
+			goto nextag;
+		}
+
 		if (!pag->pagi_init) {
-			if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-				agbp = NULL;
+			error = xfs_ialloc_pagi_init(mp, tp, agno);
+			if (error)
 				goto nextag;
-			}
-		} else
-			agbp = NULL;
+		}
 
-		if (!pag->pagi_inodeok) {
-			xfs_ialloc_next_ag(mp);
-			goto unlock_nextag;
+		if (pag->pagi_freecount) {
+			xfs_perag_put(pag);
+			return agno;
 		}
 
-		/*
-		 * Is there enough free space for the file plus a block
-		 * of inodes (if we need to allocate some)?
-		 */
-		ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
-		if (ineed && !pag->pagf_init) {
-			if (agbp == NULL &&
-			    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-				agbp = NULL;
+		if (!okalloc)
+			goto nextag;
+
+		if (!pag->pagf_init) {
+			error = xfs_alloc_pagf_init(mp, tp, agno, flags);
+			if (error)
 				goto nextag;
-			}
-			(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
 		}
-		if (!ineed || pag->pagf_init) {
-			if (ineed && !(longest = pag->pagf_longest))
-				longest = pag->pagf_flcount > 0;
-			if (!ineed ||
-			    (pag->pagf_freeblks >= needspace + ineed &&
-			     longest >= ineed &&
-			     okalloc)) {
-				if (agbp == NULL &&
-				    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-					agbp = NULL;
-					goto nextag;
-				}
-				xfs_perag_put(pag);
-				return agbp;
-			}
+
+		/*
+		 * Is there enough free space for the file plus a block of
+		 * inodes? (if we need to allocate some)?
+		 */
+		ineed = XFS_IALLOC_BLOCKS(mp);
+		longest = pag->pagf_longest;
+		if (!longest)
+			longest = pag->pagf_flcount > 0;
+
+		if (pag->pagf_freeblks >= needspace + ineed &&
+		    longest >= ineed) {
+			xfs_perag_put(pag);
+			return agno;
 		}
-unlock_nextag:
-		if (agbp)
-			xfs_trans_brelse(tp, agbp);
 nextag:
 		xfs_perag_put(pag);
 		/*
@@ -538,13 +534,13 @@ nextag:
 		 * down.
 		 */
 		if (XFS_FORCED_SHUTDOWN(mp))
-			return NULL;
+			return NULLAGNUMBER;
 		agno++;
 		if (agno >= agcount)
 			agno = 0;
 		if (agno == pagno) {
 			if (flags == 0)
-				return NULL;
+				return NULLAGNUMBER;
 			flags = 0;
 		}
 	}
@@ -607,195 +603,39 @@ xfs_ialloc_get_rec(
 }
 
 /*
- * Visible inode allocation functions.
- */
-/*
- * Find a free (set) bit in the inode bitmask.
- */
-static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
-{
-	return xfs_lowbit64(*fp);
-}
-
-/*
- * Allocate an inode on disk.
- * Mode is used to tell whether the new inode will need space, and whether
- * it is a directory.
- *
- * The arguments IO_agbp and alloc_done are defined to work within
- * the constraint of one allocation per transaction.
- * xfs_dialloc() is designed to be called twice if it has to do an
- * allocation to make more free inodes.  On the first call,
- * IO_agbp should be set to NULL. If an inode is available,
- * i.e., xfs_dialloc() did not need to do an allocation, an inode
- * number is returned.  In this case, IO_agbp would be set to the
- * current ag_buf and alloc_done set to false.
- * If an allocation needed to be done, xfs_dialloc would return
- * the current ag_buf in IO_agbp and set alloc_done to true.
- * The caller should then commit the current transaction, allocate a new
- * transaction, and call xfs_dialloc() again, passing in the previous
- * value of IO_agbp.  IO_agbp should be held across the transactions.
- * Since the agbp is locked across the two calls, the second call is
- * guaranteed to have a free inode available.
+ * Allocate an inode.
  *
- * Once we successfully pick an inode its number is returned and the
- * on-disk data structures are updated.  The inode itself is not read
- * in, since doing so would break ordering constraints with xfs_reclaim.
+ * The caller selected an AG for us, and made sure that free inodes are
+ * available.
  */
-int
-xfs_dialloc(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_ino_t	parent,		/* parent inode (directory) */
-	umode_t		mode,		/* mode bits for new inode */
-	int		okalloc,	/* ok to allocate more space */
-	xfs_buf_t	**IO_agbp,	/* in/out ag header's buffer */
-	boolean_t	*alloc_done,	/* true if we needed to replenish
-					   inode freelist */
-	xfs_ino_t	*inop)		/* inode number allocated */
+STATIC int
+xfs_dialloc_ag(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_ino_t		parent,
+	xfs_ino_t		*inop)
 {
-	xfs_agnumber_t	agcount;	/* number of allocation groups */
-	xfs_buf_t	*agbp;		/* allocation group header's buffer */
-	xfs_agnumber_t	agno;		/* allocation group number */
-	xfs_agi_t	*agi;		/* allocation group header structure */
-	xfs_btree_cur_t	*cur;		/* inode allocation btree cursor */
-	int		error;		/* error return value */
-	int		i;		/* result code */
-	int		ialloced;	/* inode allocation status */
-	int		noroom = 0;	/* no space for inode blk allocation */
-	xfs_ino_t	ino;		/* fs-relative inode to be returned */
-	/* REFERENCED */
-	int		j;		/* result code */
-	xfs_mount_t	*mp;		/* file system mount structure */
-	int		offset;		/* index of inode in chunk */
-	xfs_agino_t	pagino;		/* parent's AG relative inode # */
-	xfs_agnumber_t	pagno;		/* parent's AG number */
-	xfs_inobt_rec_incore_t rec;	/* inode allocation record */
-	xfs_agnumber_t	tagno;		/* testing allocation group number */
-	xfs_btree_cur_t	*tcur;		/* temp cursor */
-	xfs_inobt_rec_incore_t trec;	/* temp inode allocation record */
-	struct xfs_perag *pag;
-
-
-	if (*IO_agbp == NULL) {
-		/*
-		 * We do not have an agbp, so select an initial allocation
-		 * group for inode allocation.
-		 */
-		agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
-		/*
-		 * Couldn't find an allocation group satisfying the
-		 * criteria, give up.
-		 */
-		if (!agbp) {
-			*inop = NULLFSINO;
-			return 0;
-		}
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	} else {
-		/*
-		 * Continue where we left off before.  In this case, we
-		 * know that the allocation group has free inodes.
-		 */
-		agbp = *IO_agbp;
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-		ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
-	}
-	mp = tp->t_mountp;
-	agcount = mp->m_sb.sb_agcount;
-	agno = be32_to_cpu(agi->agi_seqno);
-	tagno = agno;
-	pagno = XFS_INO_TO_AGNO(mp, parent);
-	pagino = XFS_INO_TO_AGINO(mp, parent);
-
-	/*
-	 * If we have already hit the ceiling of inode blocks then clear
-	 * okalloc so we scan all available agi structures for a free
-	 * inode.
-	 */
-
-	if (mp->m_maxicount &&
-	    mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
-		noroom = 1;
-		okalloc = 0;
-	}
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t		agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agnumber_t		pagno = XFS_INO_TO_AGNO(mp, parent);
+	xfs_agino_t		pagino = XFS_INO_TO_AGINO(mp, parent);
+	struct xfs_perag	*pag;
+	struct xfs_btree_cur	*cur, *tcur;
+	struct xfs_inobt_rec_incore rec, trec;
+	xfs_ino_t		ino;
+	int			error;
+	int			offset;
+	int			i, j;
 
-	/*
-	 * Loop until we find an allocation group that either has free inodes
-	 * or in which we can allocate some inodes.  Iterate through the
-	 * allocation groups upward, wrapping at the end.
-	 */
-	*alloc_done = B_FALSE;
-	while (!agi->agi_freecount) {
-		/*
-		 * Don't do anything if we're not supposed to allocate
-		 * any blocks, just go on to the next ag.
-		 */
-		if (okalloc) {
-			/*
-			 * Try to allocate some new inodes in the allocation
-			 * group.
-			 */
-			if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
-				xfs_trans_brelse(tp, agbp);
-				if (error == ENOSPC) {
-					*inop = NULLFSINO;
-					return 0;
-				} else
-					return error;
-			}
-			if (ialloced) {
-				/*
-				 * We successfully allocated some inodes, return
-				 * the current context to the caller so that it
-				 * can commit the current transaction and call
-				 * us again where we left off.
-				 */
-				ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
-				*alloc_done = B_TRUE;
-				*IO_agbp = agbp;
-				*inop = NULLFSINO;
-				return 0;
-			}
-		}
-		/*
-		 * If it failed, give up on this ag.
-		 */
-		xfs_trans_brelse(tp, agbp);
-		/*
-		 * Go on to the next ag: get its ag header.
-		 */
-nextag:
-		if (++tagno == agcount)
-			tagno = 0;
-		if (tagno == agno) {
-			*inop = NULLFSINO;
-			return noroom ? ENOSPC : 0;
-		}
-		pag = xfs_perag_get(mp, tagno);
-		if (pag->pagi_inodeok == 0) {
-			xfs_perag_put(pag);
-			goto nextag;
-		}
-		error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
-		xfs_perag_put(pag);
-		if (error)
-			goto nextag;
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	}
-	/*
-	 * Here with an allocation group that has a free inode.
-	 * Reset agno since we may have chosen a new ag in the
-	 * loop above.
-	 */
-	agno = tagno;
-	*IO_agbp = NULL;
 	pag = xfs_perag_get(mp, agno);
 
+	ASSERT(pag->pagi_init);
+	ASSERT(pag->pagi_inodeok);
+	ASSERT(pag->pagi_freecount > 0);
+
  restart_pagno:
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -995,7 +835,7 @@ newino:
 	}
 
 alloc_inode:
-	offset = xfs_ialloc_find_free(&rec.ir_free);
+	offset = xfs_lowbit64(rec.ir_free);
 	ASSERT(offset >= 0);
 	ASSERT(offset < XFS_INODES_PER_CHUNK);
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
@@ -1027,6 +867,164 @@ error0:
 	return error;
 }
 
+/*
+ * Allocate an inode on disk.
+ *
+ * Mode is used to tell whether the new inode will need space, and whether it
+ * is a directory.
+ *
+ * This function is designed to be called twice if it has to do an allocation
+ * to make more free inodes.  On the first call, *IO_agbp should be set to NULL.
+ * If an inode is available without having to performn an allocation, an inode
+ * number is returned.  In this case, *IO_agbp would be NULL.  If an allocation
+ * needes to be done, xfs_dialloc would return the current AGI buffer in
+ * *IO_agbp.  The caller should then commit the current transaction, allocate a
+ * new transaction, and call xfs_dialloc() again, passing in the previous value
+ * of *IO_agbp.  IO_agbp should be held across the transactions. Since the AGI
+ * buffer is locked across the two calls, the second call is guaranteed to have
+ * a free inode available.
+ *
+ * Once we successfully pick an inode its number is returned and the on-disk
+ * data structures are updated.  The inode itself is not read in, since doing so
+ * would break ordering constraints with xfs_reclaim.
+ */
+int
+xfs_dialloc(
+	struct xfs_trans	*tp,
+	xfs_ino_t		parent,
+	umode_t			mode,
+	int			okalloc,
+	struct xfs_buf		**IO_agbp,
+	xfs_ino_t		*inop)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*agbp;
+	xfs_agnumber_t		agno;
+	int			error;
+	int			ialloced;
+	int			noroom = 0;
+	xfs_agnumber_t		start_agno;
+	struct xfs_perag	*pag;
+
+	if (*IO_agbp) {
+		/*
+		 * If the caller passes in a pointer to the AGI buffer,
+		 * continue where we left off before.  In this case, we
+		 * know that the allocation group has free inodes.
+		 */
+		agbp = *IO_agbp;
+		goto out_alloc;
+	}
+
+	/*
+	 * We do not have an agbp, so select an initial allocation
+	 * group for inode allocation.
+	 */
+	start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
+	if (start_agno == NULLAGNUMBER) {
+		*inop = NULLFSINO;
+		return 0;
+	}
+
+	/*
+	 * If we have already hit the ceiling of inode blocks then clear
+	 * okalloc so we scan all available agi structures for a free
+	 * inode.
+	 */
+	if (mp->m_maxicount &&
+	    mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
+		noroom = 1;
+		okalloc = 0;
+	}
+
+	/*
+	 * Loop until we find an allocation group that either has free inodes
+	 * or in which we can allocate some inodes.  Iterate through the
+	 * allocation groups upward, wrapping at the end.
+	 */
+	agno = start_agno;
+	for (;;) {
+		pag = xfs_perag_get(mp, agno);
+		if (!pag->pagi_inodeok) {
+			xfs_ialloc_next_ag(mp);
+			goto nextag;
+		}
+
+		if (!pag->pagi_init) {
+			error = xfs_ialloc_pagi_init(mp, tp, agno);
+			if (error)
+				goto out_error;
+		}
+
+		/*
+		 * Do a first racy fast path check if this AG is usable.
+		 */
+		if (!pag->pagi_freecount && !okalloc)
+			goto nextag;
+
+		error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+		if (error)
+			goto out_error;
+
+		/*
+		 * Once the AGI has been read in we have to recheck
+		 * pagi_freecount with the AGI buffer lock held.
+		 */
+		if (pag->pagi_freecount) {
+			xfs_perag_put(pag);
+			goto out_alloc;
+		}
+
+		if (!okalloc) {
+			xfs_trans_brelse(tp, agbp);
+			goto nextag;
+		}
+
+		error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced);
+		if (error) {
+			xfs_trans_brelse(tp, agbp);
+
+			if (error != ENOSPC)
+				goto out_error;
+
+			xfs_perag_put(pag);
+			*inop = NULLFSINO;
+			return 0;
+		}
+
+		if (ialloced) {
+			/*
+			 * We successfully allocated some inodes, return
+			 * the current context to the caller so that it
+			 * can commit the current transaction and call
+			 * us again where we left off.
+			 */
+			ASSERT(pag->pagi_freecount > 0);
+			xfs_perag_put(pag);
+
+			*IO_agbp = agbp;
+			*inop = NULLFSINO;
+			return 0;
+		}
+
+nextag:
+		xfs_perag_put(pag);
+		if (++agno == mp->m_sb.sb_agcount)
+			agno = 0;
+		if (agno == start_agno) {
+			*inop = NULLFSINO;
+			return noroom ? ENOSPC : 0;
+		}
+	}
+
+out_alloc:
+	*IO_agbp = NULL;
+	return xfs_dialloc_ag(tp, agbp, parent, inop);
+out_error:
+	xfs_perag_put(pag);
+	return XFS_ERROR(error);
+}
+
 /*
  * Free disk inode.  Carefully avoids touching the incore inode, all
  * manipulations incore are the caller's responsibility.

fs/xfs/xfs_ialloc.h

@@ -75,8 +75,6 @@ xfs_dialloc(
 	umode_t		mode,		/* mode bits for new inode */
 	int		okalloc,	/* ok to allocate more space */
 	struct xfs_buf	**agbp,		/* buf for a.g. inode header */
-	boolean_t	*alloc_done,	/* an allocation was done to replenish
-					   the free inodes */
 	xfs_ino_t	*inop);		/* inode number allocated */
 
 /*

fs/xfs/xfs_iget.c

@@ -40,17 +40,6 @@
 #include "xfs_trace.h"
 
 
-/*
- * Define xfs inode iolock lockdep classes. We need to ensure that all active
- * inodes are considered the same for lockdep purposes, including inodes that
- * are recycled through the XFS_IRECLAIMABLE state. This is the the only way to
- * guarantee the locks are considered the same when there are multiple lock
- * initialisation siteѕ. Also, define a reclaimable inode class so it is
- * obvious in lockdep reports which class the report is against.
- */
-static struct lock_class_key xfs_iolock_active;
-struct lock_class_key xfs_iolock_reclaimable;
-
 /*
  * Allocate and initialise an xfs_inode.
  */
@@ -80,8 +69,6 @@ xfs_inode_alloc(
 	ASSERT(ip->i_ino == 0);
 
 	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-	lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-			&xfs_iolock_active, "xfs_iolock_active");
 
 	/* initialise the xfs inode */
 	ip->i_ino = ino;
@@ -250,8 +237,6 @@ xfs_iget_cache_hit(
 
 		ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
 		mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-		lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-				&xfs_iolock_active, "xfs_iolock_active");
 
 		spin_unlock(&ip->i_flags_lock);
 		spin_unlock(&pag->pag_ici_lock);

fs/xfs/xfs_inode.c

@@ -132,23 +132,28 @@ xfs_inobp_check(
 #endif
 
 /*
- * Find the buffer associated with the given inode map
- * We do basic validation checks on the buffer once it has been
- * retrieved from disk.
+ * This routine is called to map an inode to the buffer containing the on-disk
+ * version of the inode.  It returns a pointer to the buffer containing the
+ * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
+ * pointer to the on-disk inode within that buffer.
+ *
+ * If a non-zero error is returned, then the contents of bpp and dipp are
+ * undefined.
  */
-STATIC int
+int
 xfs_imap_to_bp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	struct xfs_imap	*imap,
-	xfs_buf_t	**bpp,
-	uint		buf_flags,
-	uint		iget_flags)
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_imap		*imap,
+	struct xfs_dinode	**dipp,
+	struct xfs_buf		**bpp,
+	uint			buf_flags,
+	uint			iget_flags)
 {
-	int		error;
-	int		i;
-	int		ni;
-	xfs_buf_t	*bp;
+	struct xfs_buf		*bp;
+	int			error;
+	int			i;
+	int			ni;
 
 	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
@@ -189,8 +194,8 @@ xfs_imap_to_bp(
 				xfs_trans_brelse(tp, bp);
 				return XFS_ERROR(EINVAL);
 			}
-			XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
-						XFS_ERRLEVEL_HIGH, mp, dip);
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
+					     mp, dip);
 #ifdef DEBUG
 			xfs_emerg(mp,
 				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
@@ -204,96 +209,9 @@ xfs_imap_to_bp(
 	}
 
 	xfs_inobp_check(mp, bp);
-	*bpp = bp;
-	return 0;
-}
-
-/*
- * This routine is called to map an inode number within a file
- * system to the buffer containing the on-disk version of the
- * inode.  It returns a pointer to the buffer containing the
- * on-disk inode in the bpp parameter, and in the dip parameter
- * it returns a pointer to the on-disk inode within that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and
- * dipp are undefined.
- *
- * Use xfs_imap() to determine the size and location of the
- * buffer to read from disk.
- */
-int
-xfs_inotobp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	xfs_dinode_t	**dipp,
-	xfs_buf_t	**bpp,
-	int		*offset,
-	uint		imap_flags)
-{
-	struct xfs_imap	imap;
-	xfs_buf_t	*bp;
-	int		error;
-
-	imap.im_blkno = 0;
-	error = xfs_imap(mp, tp, ino, &imap, imap_flags);
-	if (error)
-		return error;
-
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, 0, imap_flags);
-	if (error)
-		return error;
-
-	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
-	*bpp = bp;
-	*offset = imap.im_boffset;
-	return 0;
-}
-
-
-/*
- * This routine is called to map an inode to the buffer containing
- * the on-disk version of the inode.  It returns a pointer to the
- * buffer containing the on-disk inode in the bpp parameter, and in
- * the dip parameter it returns a pointer to the on-disk inode within
- * that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and
- * dipp are undefined.
- *
- * The inode is expected to already been mapped to its buffer and read
- * in once, thus we can use the mapping information stored in the inode
- * rather than calling xfs_imap().  This allows us to avoid the overhead
- * of looking at the inode btree for small block file systems
- * (see xfs_imap()).
- */
-int
-xfs_itobp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	xfs_dinode_t	**dipp,
-	xfs_buf_t	**bpp,
-	uint		buf_flags)
-{
-	xfs_buf_t	*bp;
-	int		error;
-
-	ASSERT(ip->i_imap.im_blkno != 0);
-
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, buf_flags, 0);
-	if (error)
-		return error;
 
-	if (!bp) {
-		ASSERT(buf_flags & XBF_TRYLOCK);
-		ASSERT(tp == NULL);
-		*bpp = NULL;
-		return EAGAIN;
-	}
-
-	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 	*bpp = bp;
+	*dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
 	return 0;
 }
 
@@ -796,10 +714,9 @@ xfs_iread(
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, 0, iget_flags);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
 	if (error)
 		return error;
-	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	/*
 	 * If we got something that isn't an inode it means someone
@@ -876,7 +793,7 @@ xfs_iread(
 	/*
 	 * Use xfs_trans_brelse() to release the buffer containing the
 	 * on-disk inode, because it was acquired with xfs_trans_read_buf()
-	 * in xfs_itobp() above.  If tp is NULL, this is just a normal
+	 * in xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
 	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
 	 * will only release the buffer if it is not dirty within the
 	 * transaction.  It will be OK to release the buffer in this case,
@@ -970,7 +887,6 @@ xfs_ialloc(
 	prid_t		prid,
 	int		okalloc,
 	xfs_buf_t	**ialloc_context,
-	boolean_t	*call_again,
 	xfs_inode_t	**ipp)
 {
 	xfs_ino_t	ino;
@@ -985,10 +901,10 @@ xfs_ialloc(
 	 * the on-disk inode to be allocated.
 	 */
 	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
-			    ialloc_context, call_again, &ino);
+			    ialloc_context, &ino);
 	if (error)
 		return error;
-	if (*call_again || ino == NULLFSINO) {
+	if (*ialloc_context || ino == NULLFSINO) {
 		*ipp = NULL;
 		return 0;
 	}
@@ -1207,7 +1123,9 @@ xfs_itruncate_extents(
 	int			error = 0;
 	int			done = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
+	       xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
@@ -1226,7 +1144,7 @@ xfs_itruncate_extents(
 	 * then there is nothing to do.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (first_unmap_block == last_block)
 		return 0;
 
@@ -1355,7 +1273,8 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error)
 			return error;
 
@@ -1429,16 +1348,16 @@ xfs_iunlink_remove(
 
 	if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
 		/*
-		 * We're at the head of the list.  Get the inode's
-		 * on-disk buffer to see if there is anyone after us
-		 * on the list.  Only modify our next pointer if it
-		 * is not already NULLAGINO.  This saves us the overhead
-		 * of dealing with the buffer when there is no need to
-		 * change it.
+		 * We're at the head of the list.  Get the inode's on-disk
+		 * buffer to see if there is anyone after us on the list.
+		 * Only modify our next pointer if it is not already NULLAGINO.
+		 * This saves us the overhead of dealing with the buffer when
+		 * there is no need to change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error) {
-			xfs_warn(mp, "%s: xfs_itobp() returned error %d.",
+			xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
 				__func__, error);
 			return error;
 		}
@@ -1472,34 +1391,45 @@ xfs_iunlink_remove(
 		next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
 		last_ibp = NULL;
 		while (next_agino != agino) {
-			/*
-			 * If the last inode wasn't the one pointing to
-			 * us, then release its buffer since we're not
-			 * going to do anything with it.
-			 */
-			if (last_ibp != NULL) {
+			struct xfs_imap	imap;
+
+			if (last_ibp)
 				xfs_trans_brelse(tp, last_ibp);
-			}
+
+			imap.im_blkno = 0;
 			next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
-			error = xfs_inotobp(mp, tp, next_ino, &last_dip,
-					    &last_ibp, &last_offset, 0);
+
+			error = xfs_imap(mp, tp, next_ino, &imap, 0);
+			if (error) {
+				xfs_warn(mp,
+	"%s: xfs_imap returned error %d.",
+					 __func__, error);
+				return error;
+			}
+
+			error = xfs_imap_to_bp(mp, tp, &imap, &last_dip,
+					       &last_ibp, 0, 0);
 			if (error) {
 				xfs_warn(mp,
-					"%s: xfs_inotobp() returned error %d.",
+	"%s: xfs_imap_to_bp returned error %d.",
 					__func__, error);
 				return error;
 			}
+
+			last_offset = imap.im_boffset;
 			next_agino = be32_to_cpu(last_dip->di_next_unlinked);
 			ASSERT(next_agino != NULLAGINO);
 			ASSERT(next_agino != 0);
 		}
+
 		/*
-		 * Now last_ibp points to the buffer previous to us on
-		 * the unlinked list.  Pull us from the list.
+		 * Now last_ibp points to the buffer previous to us on the
+		 * unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error) {
-			xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.",
+			xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.",
 				__func__, error);
 			return error;
 		}
@@ -1749,7 +1679,8 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &dip, &ibp,
+			       0, 0);
 	if (error)
 		return error;
 
@@ -2428,7 +2359,7 @@ xfs_iflush(
 	/*
 	 * For stale inodes we cannot rely on the backing buffer remaining
 	 * stale in cache for the remaining life of the stale inode and so
-	 * xfs_itobp() below may give us a buffer that no longer contains
+	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
 	 * inodes below. We have to check this after ensuring the inode is
 	 * unpinned so that it is safe to reclaim the stale inode after the
 	 * flush call.
@@ -2454,7 +2385,8 @@ xfs_iflush(
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK);
+	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
+			       0);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;

fs/xfs/xfs_inode.h

@@ -487,8 +487,6 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
 #define XFS_IOLOCK_DEP(flags)	(((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT)
 #define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT)
 
-extern struct lock_class_key xfs_iolock_reclaimable;
-
 /*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
@@ -517,7 +515,7 @@ void		xfs_inode_free(struct xfs_inode *ip);
  */
 int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, umode_t,
 			   xfs_nlink_t, xfs_dev_t, prid_t, int,
-			   struct xfs_buf **, boolean_t *, xfs_inode_t **);
+			   struct xfs_buf **, xfs_inode_t **);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
 uint		xfs_dic2xflags(struct xfs_dinode *);
@@ -557,12 +555,9 @@ do { \
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
 
-int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
-			    xfs_ino_t, struct xfs_dinode **,
-			    struct xfs_buf **, int *, uint);
-int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
-			  struct xfs_inode *, struct xfs_dinode **,
-			  struct xfs_buf **, uint);
+int		xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
+			       struct xfs_imap *, struct xfs_dinode **,
+			       struct xfs_buf **, uint, uint);
 int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
 			  struct xfs_inode *, uint);
 void		xfs_dinode_to_disk(struct xfs_dinode *,

fs/xfs/xfs_iomap.c

@@ -285,7 +285,7 @@ xfs_iomap_eof_want_preallocate(
 	 * do any speculative allocation.
 	 */
 	start_fsb = XFS_B_TO_FSBT(mp, ((xfs_ufsize_t)(offset + count - 1)));
-	count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	count_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	while (count_fsb > 0) {
 		imaps = nimaps;
 		firstblock = NULLFSBLOCK;
@@ -416,8 +416,8 @@ retry:
 	 * Make sure preallocation does not create extents beyond the range we
 	 * actually support in this filesystem.
 	 */
-	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_maxioffset))
-		last_fsb = XFS_B_TO_FSB(mp, mp->m_maxioffset);
+	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes))
+		last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 
 	ASSERT(last_fsb > offset_fsb);
 

fs/xfs/xfs_iops.c

@@ -897,6 +897,47 @@ xfs_vn_setattr(
 	return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0);
 }
 
+STATIC int
+xfs_vn_update_time(
+	struct inode		*inode,
+	struct timespec		*now,
+	int			flags)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	trace_xfs_update_time(ip);
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return -error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	if (flags & S_CTIME) {
+		inode->i_ctime = *now;
+		ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
+		ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
+	}
+	if (flags & S_MTIME) {
+		inode->i_mtime = *now;
+		ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
+		ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
+	}
+	if (flags & S_ATIME) {
+		inode->i_atime = *now;
+		ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
+		ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
+	}
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
+	return -xfs_trans_commit(tp, 0);
+}
+
 #define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
 /*
@@ -991,6 +1032,7 @@ static const struct inode_operations xfs_inode_operations = {
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
 	.fiemap			= xfs_vn_fiemap,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_dir_inode_operations = {
@@ -1016,6 +1058,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1041,6 +1084,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_symlink_inode_operations = {
@@ -1054,6 +1098,7 @@ static const struct inode_operations xfs_symlink_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 STATIC void

fs/xfs/xfs_itable.c

@@ -555,7 +555,7 @@ xfs_bulkstat_single(
 
 	/*
 	 * note that requesting valid inode numbers which are not allocated
-	 * to inodes will most likely cause xfs_itobp to generate warning
+	 * to inodes will most likely cause xfs_imap_to_bp to generate warning
 	 * messages about bad magic numbers. This is ok. The fact that
 	 * the inode isn't actually an inode is handled by the
 	 * error check below. Done this way to make the usual case faster

fs/xfs/xfs_log.c

@@ -45,51 +45,85 @@ xlog_commit_record(
 	struct xlog_in_core	**iclog,
 	xfs_lsn_t		*commitlsnp);
 
-STATIC xlog_t *  xlog_alloc_log(xfs_mount_t	*mp,
-				xfs_buftarg_t	*log_target,
-				xfs_daddr_t	blk_offset,
-				int		num_bblks);
+STATIC struct xlog *
+xlog_alloc_log(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*log_target,
+	xfs_daddr_t		blk_offset,
+	int			num_bblks);
 STATIC int
 xlog_space_left(
 	struct xlog		*log,
 	atomic64_t		*head);
-STATIC int	 xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
-STATIC void	 xlog_dealloc_log(xlog_t *log);
+STATIC int
+xlog_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
+STATIC void
+xlog_dealloc_log(
+	struct xlog		*log);
 
 /* local state machine functions */
 STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int);
-STATIC void xlog_state_do_callback(xlog_t *log,int aborted, xlog_in_core_t *iclog);
-STATIC int  xlog_state_get_iclog_space(xlog_t		*log,
-				       int		len,
-				       xlog_in_core_t	**iclog,
-				       xlog_ticket_t	*ticket,
-				       int		*continued_write,
-				       int		*logoffsetp);
-STATIC int  xlog_state_release_iclog(xlog_t		*log,
-				     xlog_in_core_t	*iclog);
-STATIC void xlog_state_switch_iclogs(xlog_t		*log,
-				     xlog_in_core_t *iclog,
-				     int		eventual_size);
-STATIC void xlog_state_want_sync(xlog_t	*log, xlog_in_core_t *iclog);
+STATIC void
+xlog_state_do_callback(
+	struct xlog		*log,
+	int			aborted,
+	struct xlog_in_core	*iclog);
+STATIC int
+xlog_state_get_iclog_space(
+	struct xlog		*log,
+	int			len,
+	struct xlog_in_core	**iclog,
+	struct xlog_ticket	*ticket,
+	int			*continued_write,
+	int			*logoffsetp);
+STATIC int
+xlog_state_release_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
+STATIC void
+xlog_state_switch_iclogs(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			eventual_size);
+STATIC void
+xlog_state_want_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
 
 STATIC void
 xlog_grant_push_ail(
-	struct xlog	*log,
-	int		need_bytes);
-STATIC void xlog_regrant_reserve_log_space(xlog_t	 *log,
-					   xlog_ticket_t *ticket);
-STATIC void xlog_ungrant_log_space(xlog_t	 *log,
-				   xlog_ticket_t *ticket);
+	struct xlog		*log,
+	int			need_bytes);
+STATIC void
+xlog_regrant_reserve_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket);
+STATIC void
+xlog_ungrant_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket);
 
 #if defined(DEBUG)
-STATIC void	xlog_verify_dest_ptr(xlog_t *log, char *ptr);
+STATIC void
+xlog_verify_dest_ptr(
+	struct xlog		*log,
+	char			*ptr);
 STATIC void
 xlog_verify_grant_tail(
-	struct xlog	*log);
-STATIC void	xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog,
-				  int count, boolean_t syncing);
-STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
-				     xfs_lsn_t tail_lsn);
+	struct xlog *log);
+STATIC void
+xlog_verify_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			count,
+	boolean_t		syncing);
+STATIC void
+xlog_verify_tail_lsn(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	xfs_lsn_t		tail_lsn);
 #else
 #define xlog_verify_dest_ptr(a,b)
 #define xlog_verify_grant_tail(a)
@@ -97,7 +131,9 @@ STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
 #define xlog_verify_tail_lsn(a,b,c)
 #endif
 
-STATIC int	xlog_iclogs_empty(xlog_t *log);
+STATIC int
+xlog_iclogs_empty(
+	struct xlog		*log);
 
 static void
 xlog_grant_sub_space(
@@ -684,7 +720,7 @@ xfs_log_mount_finish(xfs_mount_t *mp)
 int
 xfs_log_unmount_write(xfs_mount_t *mp)
 {
-	xlog_t		 *log = mp->m_log;
+	struct xlog	 *log = mp->m_log;
 	xlog_in_core_t	 *iclog;
 #ifdef DEBUG
 	xlog_in_core_t	 *first_iclog;
@@ -893,7 +929,7 @@ int
 xfs_log_need_covered(xfs_mount_t *mp)
 {
 	int		needed = 0;
-	xlog_t		*log = mp->m_log;
+	struct xlog	*log = mp->m_log;
 
 	if (!xfs_fs_writable(mp))
 		return 0;
@@ -1024,9 +1060,9 @@ xlog_space_left(
 void
 xlog_iodone(xfs_buf_t *bp)
 {
-	xlog_in_core_t	*iclog = bp->b_fspriv;
-	xlog_t		*l = iclog->ic_log;
-	int		aborted = 0;
+	struct xlog_in_core	*iclog = bp->b_fspriv;
+	struct xlog		*l = iclog->ic_log;
+	int			aborted = 0;
 
 	/*
 	 * Race to shutdown the filesystem if we see an error.
@@ -1067,8 +1103,9 @@ xlog_iodone(xfs_buf_t *bp)
  */
 
 STATIC void
-xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
-			   xlog_t	*log)
+xlog_get_iclog_buffer_size(
+	struct xfs_mount	*mp,
+	struct xlog		*log)
 {
 	int size;
 	int xhdrs;
@@ -1129,13 +1166,14 @@ done:
  * Its primary purpose is to fill in enough, so recovery can occur.  However,
  * some other stuff may be filled in too.
  */
-STATIC xlog_t *
-xlog_alloc_log(xfs_mount_t	*mp,
-	       xfs_buftarg_t	*log_target,
-	       xfs_daddr_t	blk_offset,
-	       int		num_bblks)
+STATIC struct xlog *
+xlog_alloc_log(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*log_target,
+	xfs_daddr_t		blk_offset,
+	int			num_bblks)
 {
-	xlog_t			*log;
+	struct xlog		*log;
 	xlog_rec_header_t	*head;
 	xlog_in_core_t		**iclogp;
 	xlog_in_core_t		*iclog, *prev_iclog=NULL;
@@ -1144,7 +1182,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	int			error = ENOMEM;
 	uint			log2_size = 0;
 
-	log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
+	log = kmem_zalloc(sizeof(struct xlog), KM_MAYFAIL);
 	if (!log) {
 		xfs_warn(mp, "Log allocation failed: No memory!");
 		goto out;
@@ -1434,8 +1472,9 @@ xlog_bdstrat(
  */
 
 STATIC int
-xlog_sync(xlog_t		*log,
-	  xlog_in_core_t	*iclog)
+xlog_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	xfs_caddr_t	dptr;		/* pointer to byte sized element */
 	xfs_buf_t	*bp;
@@ -1584,7 +1623,8 @@ xlog_sync(xlog_t		*log,
  * Deallocate a log structure
  */
 STATIC void
-xlog_dealloc_log(xlog_t *log)
+xlog_dealloc_log(
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog, *next_iclog;
 	int		i;
@@ -1616,10 +1656,11 @@ xlog_dealloc_log(xlog_t *log)
  */
 /* ARGSUSED */
 static inline void
-xlog_state_finish_copy(xlog_t		*log,
-		       xlog_in_core_t	*iclog,
-		       int		record_cnt,
-		       int		copy_bytes)
+xlog_state_finish_copy(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			record_cnt,
+	int			copy_bytes)
 {
 	spin_lock(&log->l_icloglock);
 
@@ -2142,7 +2183,8 @@ xlog_write(
  * State Change: DIRTY -> ACTIVE
  */
 STATIC void
-xlog_state_clean_log(xlog_t *log)
+xlog_state_clean_log(
+	struct xlog *log)
 {
 	xlog_in_core_t	*iclog;
 	int changed = 0;
@@ -2222,7 +2264,7 @@ xlog_state_clean_log(xlog_t *log)
 
 STATIC xfs_lsn_t
 xlog_get_lowest_lsn(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xlog_in_core_t  *lsn_log;
 	xfs_lsn_t	lowest_lsn, lsn;
@@ -2245,9 +2287,9 @@ xlog_get_lowest_lsn(
 
 STATIC void
 xlog_state_do_callback(
-	xlog_t		*log,
-	int		aborted,
-	xlog_in_core_t	*ciclog)
+	struct xlog		*log,
+	int			aborted,
+	struct xlog_in_core	*ciclog)
 {
 	xlog_in_core_t	   *iclog;
 	xlog_in_core_t	   *first_iclog;	/* used to know when we've
@@ -2467,7 +2509,7 @@ xlog_state_done_syncing(
 	xlog_in_core_t	*iclog,
 	int		aborted)
 {
-	xlog_t		   *log = iclog->ic_log;
+	struct xlog	   *log = iclog->ic_log;
 
 	spin_lock(&log->l_icloglock);
 
@@ -2521,12 +2563,13 @@ xlog_state_done_syncing(
  *		is copied.
  */
 STATIC int
-xlog_state_get_iclog_space(xlog_t	  *log,
-			   int		  len,
-			   xlog_in_core_t **iclogp,
-			   xlog_ticket_t  *ticket,
-			   int		  *continued_write,
-			   int		  *logoffsetp)
+xlog_state_get_iclog_space(
+	struct xlog		*log,
+	int			len,
+	struct xlog_in_core	**iclogp,
+	struct xlog_ticket	*ticket,
+	int			*continued_write,
+	int			*logoffsetp)
 {
 	int		  log_offset;
 	xlog_rec_header_t *head;
@@ -2631,8 +2674,9 @@ restart:
  * move grant reservation head forward.
  */
 STATIC void
-xlog_regrant_reserve_log_space(xlog_t	     *log,
-			       xlog_ticket_t *ticket)
+xlog_regrant_reserve_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket)
 {
 	trace_xfs_log_regrant_reserve_enter(log, ticket);
 
@@ -2677,8 +2721,9 @@ xlog_regrant_reserve_log_space(xlog_t	     *log,
  * in the current reservation field.
  */
 STATIC void
-xlog_ungrant_log_space(xlog_t	     *log,
-		       xlog_ticket_t *ticket)
+xlog_ungrant_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket)
 {
 	int	bytes;
 
@@ -2717,8 +2762,8 @@ xlog_ungrant_log_space(xlog_t	     *log,
  */
 STATIC int
 xlog_state_release_iclog(
-	xlog_t		*log,
-	xlog_in_core_t	*iclog)
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	int		sync = 0;	/* do we sync? */
 
@@ -2768,9 +2813,10 @@ xlog_state_release_iclog(
  * that every data block.  We have run out of space in this log record.
  */
 STATIC void
-xlog_state_switch_iclogs(xlog_t		*log,
-			 xlog_in_core_t *iclog,
-			 int		eventual_size)
+xlog_state_switch_iclogs(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			eventual_size)
 {
 	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
 	if (!eventual_size)
@@ -3114,7 +3160,9 @@ xfs_log_force_lsn(
  * disk.
  */
 STATIC void
-xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
+xlog_state_want_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	assert_spin_locked(&log->l_icloglock);
 
@@ -3158,7 +3206,7 @@ xfs_log_ticket_get(
 /*
  * Allocate and initialise a new log ticket.
  */
-xlog_ticket_t *
+struct xlog_ticket *
 xlog_ticket_alloc(
 	struct xlog	*log,
 	int		unit_bytes,
@@ -3346,9 +3394,10 @@ xlog_verify_grant_tail(
 
 /* check if it will fit */
 STATIC void
-xlog_verify_tail_lsn(xlog_t	    *log,
-		     xlog_in_core_t *iclog,
-		     xfs_lsn_t	    tail_lsn)
+xlog_verify_tail_lsn(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	xfs_lsn_t		tail_lsn)
 {
     int blocks;
 
@@ -3385,10 +3434,11 @@ xlog_verify_tail_lsn(xlog_t	    *log,
  *	the cycle numbers agree with the current cycle number.
  */
 STATIC void
-xlog_verify_iclog(xlog_t	 *log,
-		  xlog_in_core_t *iclog,
-		  int		 count,
-		  boolean_t	 syncing)
+xlog_verify_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			count,
+	boolean_t		syncing)
 {
 	xlog_op_header_t	*ophead;
 	xlog_in_core_t		*icptr;
@@ -3482,7 +3532,7 @@ xlog_verify_iclog(xlog_t	 *log,
  */
 STATIC int
 xlog_state_ioerror(
-	xlog_t	*log)
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog, *ic;
 
@@ -3527,7 +3577,7 @@ xfs_log_force_umount(
 	struct xfs_mount	*mp,
 	int			logerror)
 {
-	xlog_t		*log;
+	struct xlog	*log;
 	int		retval;
 
 	log = mp->m_log;
@@ -3634,7 +3684,8 @@ xfs_log_force_umount(
 }
 
 STATIC int
-xlog_iclogs_empty(xlog_t *log)
+xlog_iclogs_empty(
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog;
 

fs/xfs/xfs_log_priv.h

@@ -487,7 +487,7 @@ struct xlog_grant_head {
  * overflow 31 bits worth of byte offset, so using a byte number will mean
  * that round off problems won't occur when releasing partial reservations.
  */
-typedef struct xlog {
+struct xlog {
 	/* The following fields don't need locking */
 	struct xfs_mount	*l_mp;	        /* mount point */
 	struct xfs_ail		*l_ailp;	/* AIL log is working with */
@@ -540,7 +540,7 @@ typedef struct xlog {
 	char			*l_iclog_bak[XLOG_MAX_ICLOGS];
 #endif
 
-} xlog_t;
+};
 
 #define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
 	((log)->l_buf_cancel_table + ((__uint64_t)blkno % XLOG_BC_TABLE_SIZE))
@@ -548,9 +548,17 @@ typedef struct xlog {
 #define XLOG_FORCED_SHUTDOWN(log)	((log)->l_flags & XLOG_IO_ERROR)
 
 /* common routines */
-extern int	 xlog_recover(xlog_t *log);
-extern int	 xlog_recover_finish(xlog_t *log);
-extern void	 xlog_pack_data(xlog_t *log, xlog_in_core_t *iclog, int);
+extern int
+xlog_recover(
+	struct xlog		*log);
+extern int
+xlog_recover_finish(
+	struct xlog		*log);
+extern void
+xlog_pack_data(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int);
 
 extern kmem_zone_t *xfs_log_ticket_zone;
 struct xlog_ticket *

fs/xfs/xfs_log_recover.c

@@ -43,10 +43,18 @@
 #include "xfs_utils.h"
 #include "xfs_trace.h"
 
-STATIC int	xlog_find_zeroed(xlog_t *, xfs_daddr_t *);
-STATIC int	xlog_clear_stale_blocks(xlog_t *, xfs_lsn_t);
+STATIC int
+xlog_find_zeroed(
+	struct xlog	*,
+	xfs_daddr_t	*);
+STATIC int
+xlog_clear_stale_blocks(
+	struct xlog	*,
+	xfs_lsn_t);
 #if defined(DEBUG)
-STATIC void	xlog_recover_check_summary(xlog_t *);
+STATIC void
+xlog_recover_check_summary(
+	struct xlog *);
 #else
 #define	xlog_recover_check_summary(log)
 #endif
@@ -74,7 +82,7 @@ struct xfs_buf_cancel {
 
 static inline int
 xlog_buf_bbcount_valid(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		bbcount)
 {
 	return bbcount > 0 && bbcount <= log->l_logBBsize;
@@ -87,7 +95,7 @@ xlog_buf_bbcount_valid(
  */
 STATIC xfs_buf_t *
 xlog_get_bp(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		nbblks)
 {
 	struct xfs_buf	*bp;
@@ -138,10 +146,10 @@ xlog_put_bp(
  */
 STATIC xfs_caddr_t
 xlog_align(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	xfs_daddr_t	offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1);
 
@@ -155,10 +163,10 @@ xlog_align(
  */
 STATIC int
 xlog_bread_noalign(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	int		error;
 
@@ -189,10 +197,10 @@ xlog_bread_noalign(
 
 STATIC int
 xlog_bread(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp,
+	struct xfs_buf	*bp,
 	xfs_caddr_t	*offset)
 {
 	int		error;
@@ -211,10 +219,10 @@ xlog_bread(
  */
 STATIC int
 xlog_bread_offset(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,		/* block to read from */
 	int		nbblks,		/* blocks to read */
-	xfs_buf_t	*bp,
+	struct xfs_buf	*bp,
 	xfs_caddr_t	offset)
 {
 	xfs_caddr_t	orig_offset = bp->b_addr;
@@ -241,10 +249,10 @@ xlog_bread_offset(
  */
 STATIC int
 xlog_bwrite(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	int		error;
 
@@ -378,8 +386,8 @@ xlog_recover_iodone(
  */
 STATIC int
 xlog_find_cycle_start(
-	xlog_t		*log,
-	xfs_buf_t	*bp,
+	struct xlog	*log,
+	struct xfs_buf	*bp,
 	xfs_daddr_t	first_blk,
 	xfs_daddr_t	*last_blk,
 	uint		cycle)
@@ -421,7 +429,7 @@ xlog_find_cycle_start(
  */
 STATIC int
 xlog_find_verify_cycle(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	start_blk,
 	int		nbblks,
 	uint		stop_on_cycle_no,
@@ -490,7 +498,7 @@ out:
  */
 STATIC int
 xlog_find_verify_log_record(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		start_blk,
 	xfs_daddr_t		*last_blk,
 	int			extra_bblks)
@@ -600,7 +608,7 @@ out:
  */
 STATIC int
 xlog_find_head(
-	xlog_t 		*log,
+	struct xlog	*log,
 	xfs_daddr_t	*return_head_blk)
 {
 	xfs_buf_t	*bp;
@@ -871,7 +879,7 @@ validate_head:
  */
 STATIC int
 xlog_find_tail(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		*head_blk,
 	xfs_daddr_t		*tail_blk)
 {
@@ -1080,7 +1088,7 @@ done:
  */
 STATIC int
 xlog_find_zeroed(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	*blk_no)
 {
 	xfs_buf_t	*bp;
@@ -1183,7 +1191,7 @@ bp_err:
  */
 STATIC void
 xlog_add_record(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_caddr_t		buf,
 	int			cycle,
 	int			block,
@@ -1205,7 +1213,7 @@ xlog_add_record(
 
 STATIC int
 xlog_write_log_records(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		cycle,
 	int		start_block,
 	int		blocks,
@@ -1305,7 +1313,7 @@ xlog_write_log_records(
  */
 STATIC int
 xlog_clear_stale_blocks(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_lsn_t	tail_lsn)
 {
 	int		tail_cycle, head_cycle;
@@ -2050,11 +2058,11 @@ xfs_qm_dqcheck(
  */
 STATIC void
 xlog_recover_do_dquot_buffer(
-	xfs_mount_t		*mp,
-	xlog_t			*log,
-	xlog_recover_item_t	*item,
-	xfs_buf_t		*bp,
-	xfs_buf_log_format_t	*buf_f)
+	struct xfs_mount		*mp,
+	struct xlog			*log,
+	struct xlog_recover_item	*item,
+	struct xfs_buf			*bp,
+	struct xfs_buf_log_format	*buf_f)
 {
 	uint			type;
 
@@ -2108,9 +2116,9 @@ xlog_recover_do_dquot_buffer(
  */
 STATIC int
 xlog_recover_buffer_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_buf_log_format_t	*buf_f = item->ri_buf[0].i_addr;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2189,9 +2197,9 @@ xlog_recover_buffer_pass2(
 
 STATIC int
 xlog_recover_inode_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_inode_log_format_t	*in_f;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2452,14 +2460,14 @@ error:
 }
 
 /*
- * Recover QUOTAOFF records. We simply make a note of it in the xlog_t
+ * Recover QUOTAOFF records. We simply make a note of it in the xlog
  * structure, so that we know not to do any dquot item or dquot buffer recovery,
  * of that type.
  */
 STATIC int
 xlog_recover_quotaoff_pass1(
-	xlog_t			*log,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct xlog_recover_item	*item)
 {
 	xfs_qoff_logformat_t	*qoff_f = item->ri_buf[0].i_addr;
 	ASSERT(qoff_f);
@@ -2483,9 +2491,9 @@ xlog_recover_quotaoff_pass1(
  */
 STATIC int
 xlog_recover_dquot_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_mount_t		*mp = log->l_mp;
 	xfs_buf_t		*bp;
@@ -2578,9 +2586,9 @@ xlog_recover_dquot_pass2(
  */
 STATIC int
 xlog_recover_efi_pass2(
-	xlog_t			*log,
-	xlog_recover_item_t	*item,
-	xfs_lsn_t		lsn)
+	struct xlog			*log,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
 {
 	int			error;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2616,8 +2624,8 @@ xlog_recover_efi_pass2(
  */
 STATIC int
 xlog_recover_efd_pass2(
-	xlog_t			*log,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct xlog_recover_item	*item)
 {
 	xfs_efd_log_format_t	*efd_formatp;
 	xfs_efi_log_item_t	*efip = NULL;
@@ -2812,9 +2820,9 @@ xlog_recover_unmount_trans(
  */
 STATIC int
 xlog_recover_process_data(
-	xlog_t			*log,
+	struct xlog		*log,
 	struct hlist_head	rhash[],
-	xlog_rec_header_t	*rhead,
+	struct xlog_rec_header	*rhead,
 	xfs_caddr_t		dp,
 	int			pass)
 {
@@ -2986,7 +2994,7 @@ abort_error:
  */
 STATIC int
 xlog_recover_process_efis(
-	xlog_t			*log)
+	struct xlog	*log)
 {
 	xfs_log_item_t		*lip;
 	xfs_efi_log_item_t	*efip;
@@ -3098,7 +3106,7 @@ xlog_recover_process_one_iunlink(
 	/*
 	 * Get the on disk inode to find the next inode in the bucket.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &ibp, 0, 0);
 	if (error)
 		goto fail_iput;
 
@@ -3147,7 +3155,7 @@ xlog_recover_process_one_iunlink(
  */
 STATIC void
 xlog_recover_process_iunlinks(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_mount_t	*mp;
 	xfs_agnumber_t	agno;
@@ -3209,9 +3217,9 @@ xlog_recover_process_iunlinks(
 #ifdef DEBUG
 STATIC void
 xlog_pack_data_checksum(
-	xlog_t		*log,
-	xlog_in_core_t	*iclog,
-	int		size)
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			size)
 {
 	int		i;
 	__be32		*up;
@@ -3234,8 +3242,8 @@ xlog_pack_data_checksum(
  */
 void
 xlog_pack_data(
-	xlog_t			*log,
-	xlog_in_core_t		*iclog,
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
 	int			roundoff)
 {
 	int			i, j, k;
@@ -3274,9 +3282,9 @@ xlog_pack_data(
 
 STATIC void
 xlog_unpack_data(
-	xlog_rec_header_t	*rhead,
+	struct xlog_rec_header	*rhead,
 	xfs_caddr_t		dp,
-	xlog_t			*log)
+	struct xlog		*log)
 {
 	int			i, j, k;
 
@@ -3299,8 +3307,8 @@ xlog_unpack_data(
 
 STATIC int
 xlog_valid_rec_header(
-	xlog_t			*log,
-	xlog_rec_header_t	*rhead,
+	struct xlog		*log,
+	struct xlog_rec_header	*rhead,
 	xfs_daddr_t		blkno)
 {
 	int			hlen;
@@ -3343,7 +3351,7 @@ xlog_valid_rec_header(
  */
 STATIC int
 xlog_do_recovery_pass(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		head_blk,
 	xfs_daddr_t		tail_blk,
 	int			pass)
@@ -3595,7 +3603,7 @@ xlog_do_recovery_pass(
  */
 STATIC int
 xlog_do_log_recovery(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
@@ -3646,7 +3654,7 @@ xlog_do_log_recovery(
  */
 STATIC int
 xlog_do_recover(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
@@ -3721,7 +3729,7 @@ xlog_do_recover(
  */
 int
 xlog_recover(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_daddr_t	head_blk, tail_blk;
 	int		error;
@@ -3767,7 +3775,7 @@ xlog_recover(
  */
 int
 xlog_recover_finish(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	/*
 	 * Now we're ready to do the transactions needed for the
@@ -3814,7 +3822,7 @@ xlog_recover_finish(
  */
 void
 xlog_recover_check_summary(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_mount_t	*mp;
 	xfs_agf_t	*agfp;

fs/xfs/xfs_mount.c

@@ -1200,8 +1200,6 @@ xfs_mountfs(
 
 	xfs_set_maxicount(mp);
 
-	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);
-
 	error = xfs_uuid_mount(mp);
 	if (error)
 		goto out;
@@ -1531,6 +1529,15 @@ xfs_unmountfs(
 	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_wait_buftarg(mp->m_ddev_targp);
 
+	/*
+	 * The superblock buffer is uncached and xfsaild_push() will lock and
+	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
+	 * here but a lock on the superblock buffer will block until iodone()
+	 * has completed.
+	 */
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
+
 	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
 	xfs_uuid_unmount(mp);

fs/xfs/xfs_mount.h

@@ -176,7 +176,6 @@ typedef struct xfs_mount {
 	uint			m_qflags;	/* quota status flags */
 	xfs_trans_reservations_t m_reservations;/* precomputed res values */
 	__uint64_t		m_maxicount;	/* maximum inode count */
-	__uint64_t		m_maxioffset;	/* maximum inode offset */
 	__uint64_t		m_resblks;	/* total reserved blocks */
 	__uint64_t		m_resblks_avail;/* available reserved blocks */
 	__uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
@@ -297,8 +296,6 @@ xfs_preferred_iosize(xfs_mount_t *mp)
 			PAGE_CACHE_SIZE));
 }
 
-#define XFS_MAXIOFFSET(mp)	((mp)->m_maxioffset)
-
 #define XFS_LAST_UNMOUNT_WAS_CLEAN(mp)	\
 				((mp)->m_flags & XFS_MOUNT_WAS_CLEAN)
 #define XFS_FORCED_SHUTDOWN(mp)	((mp)->m_flags & XFS_MOUNT_FS_SHUTDOWN)

fs/xfs/xfs_qm.c

@@ -940,7 +940,7 @@ xfs_qm_dqiterate(
 	map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), KM_SLEEP);
 
 	lblkno = 0;
-	maxlblkcnt = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	maxlblkcnt = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	do {
 		nmaps = XFS_DQITER_MAP_SIZE;
 		/*

fs/xfs/xfs_super.c

@@ -868,67 +868,14 @@ xfs_fs_inode_init_once(
 		     "xfsino", ip->i_ino);
 }
 
-/*
- * This is called by the VFS when dirtying inode metadata.  This can happen
- * for a few reasons, but we only care about timestamp updates, given that
- * we handled the rest ourselves.  In theory no other calls should happen,
- * but for example generic_write_end() keeps dirtying the inode after
- * updating i_size.  Thus we check that the flags are exactly I_DIRTY_SYNC,
- * and skip this call otherwise.
- *
- * We'll hopefull get a different method just for updating timestamps soon,
- * at which point this hack can go away, and maybe we'll also get real
- * error handling here.
- */
-STATIC void
-xfs_fs_dirty_inode(
-	struct inode		*inode,
-	int			flags)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	if (flags != I_DIRTY_SYNC)
-		return;
-
-	trace_xfs_dirty_inode(ip);
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
-	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		goto trouble;
-	}
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	/*
-	 * Grab all the latest timestamps from the Linux inode.
-	 */
-	ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
-	ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
-	ip->i_d.di_ctime.t_sec = (__int32_t)inode->i_ctime.tv_sec;
-	ip->i_d.di_ctime.t_nsec = (__int32_t)inode->i_ctime.tv_nsec;
-	ip->i_d.di_mtime.t_sec = (__int32_t)inode->i_mtime.tv_sec;
-	ip->i_d.di_mtime.t_nsec = (__int32_t)inode->i_mtime.tv_nsec;
-
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
-	error = xfs_trans_commit(tp, 0);
-	if (error)
-		goto trouble;
-	return;
-
-trouble:
-	xfs_warn(mp, "failed to update timestamps for inode 0x%llx", ip->i_ino);
-}
-
 STATIC void
 xfs_fs_evict_inode(
 	struct inode		*inode)
 {
 	xfs_inode_t		*ip = XFS_I(inode);
 
+	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+
 	trace_xfs_evict_inode(ip);
 
 	truncate_inode_pages(&inode->i_data, 0);
@@ -937,22 +884,6 @@ xfs_fs_evict_inode(
 	XFS_STATS_INC(vn_remove);
 	XFS_STATS_DEC(vn_active);
 
-	/*
-	 * The iolock is used by the file system to coordinate reads,
-	 * writes, and block truncates.  Up to this point the lock
-	 * protected concurrent accesses by users of the inode.  But
-	 * from here forward we're doing some final processing of the
-	 * inode because we're done with it, and although we reuse the
-	 * iolock for protection it is really a distinct lock class
-	 * (in the lockdep sense) from before.  To keep lockdep happy
-	 * (and basically indicate what we are doing), we explicitly
-	 * re-init the iolock here.
-	 */
-	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
-	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-	lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-			&xfs_iolock_reclaimable, "xfs_iolock_reclaimable");
-
 	xfs_inactive(ip);
 }
 
@@ -1436,7 +1367,6 @@ xfs_fs_free_cached_objects(
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
-	.dirty_inode		= xfs_fs_dirty_inode,
 	.evict_inode		= xfs_fs_evict_inode,
 	.drop_inode		= xfs_fs_drop_inode,
 	.put_super		= xfs_fs_put_super,
@@ -1491,13 +1421,9 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
-	if (!xfs_dabuf_zone)
-		goto out_destroy_da_state_zone;
-
 	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
 	if (!xfs_ifork_zone)
-		goto out_destroy_dabuf_zone;
+		goto out_destroy_da_state_zone;
 
 	xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
 	if (!xfs_trans_zone)
@@ -1514,9 +1440,8 @@ xfs_init_zones(void)
 	 * size possible under XFS.  This wastes a little bit of memory,
 	 * but it is much faster.
 	 */
-	xfs_buf_item_zone = kmem_zone_init((sizeof(xfs_buf_log_item_t) +
-				(((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) /
-				  NBWORD) * sizeof(int))), "xfs_buf_item");
+	xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
+					   "xfs_buf_item");
 	if (!xfs_buf_item_zone)
 		goto out_destroy_log_item_desc_zone;
 
@@ -1561,8 +1486,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_trans_zone);
  out_destroy_ifork_zone:
 	kmem_zone_destroy(xfs_ifork_zone);
- out_destroy_dabuf_zone:
-	kmem_zone_destroy(xfs_dabuf_zone);
  out_destroy_da_state_zone:
 	kmem_zone_destroy(xfs_da_state_zone);
  out_destroy_btree_cur_zone:
@@ -1590,7 +1513,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_log_item_desc_zone);
 	kmem_zone_destroy(xfs_trans_zone);
 	kmem_zone_destroy(xfs_ifork_zone);
-	kmem_zone_destroy(xfs_dabuf_zone);
 	kmem_zone_destroy(xfs_da_state_zone);
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);

fs/xfs/xfs_sync.c

@@ -359,6 +359,15 @@ xfs_quiesce_attr(
 	 * added an item to the AIL, thus flush it again.
 	 */
 	xfs_ail_push_all_sync(mp->m_ail);
+
+	/*
+	 * The superblock buffer is uncached and xfsaild_push() will lock and
+	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
+	 * here but a lock on the superblock buffer will block until iodone()
+	 * has completed.
+	 */
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
 }
 
 static void
@@ -712,8 +721,8 @@ restart:
 	 * Note that xfs_iflush will never block on the inode buffer lock, as
 	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
 	 * ip->i_lock, and we are doing the exact opposite here.  As a result,
-	 * doing a blocking xfs_itobp() to get the cluster buffer would result
-	 * in an ABBA deadlock with xfs_ifree_cluster().
+	 * doing a blocking xfs_imap_to_bp() to get the cluster buffer would
+	 * result in an ABBA deadlock with xfs_ifree_cluster().
 	 *
 	 * As xfs_ifree_cluser() must gather all inodes that are active in the
 	 * cache to mark them stale, if we hit this case we don't actually want

fs/xfs/xfs_trace.h

@@ -578,8 +578,8 @@ DEFINE_INODE_EVENT(xfs_ioctl_setattr);
 DEFINE_INODE_EVENT(xfs_dir_fsync);
 DEFINE_INODE_EVENT(xfs_file_fsync);
 DEFINE_INODE_EVENT(xfs_destroy_inode);
-DEFINE_INODE_EVENT(xfs_dirty_inode);
 DEFINE_INODE_EVENT(xfs_evict_inode);
+DEFINE_INODE_EVENT(xfs_update_time);
 
 DEFINE_INODE_EVENT(xfs_dquot_dqalloc);
 DEFINE_INODE_EVENT(xfs_dquot_dqdetach);

fs/xfs/xfs_trans.h

@@ -448,11 +448,51 @@ xfs_trans_t	*xfs_trans_dup(xfs_trans_t *);
 int		xfs_trans_reserve(xfs_trans_t *, uint, uint, uint,
 				  uint, uint);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
-struct xfs_buf	*xfs_trans_get_buf(xfs_trans_t *, struct xfs_buftarg *, xfs_daddr_t,
-				   int, uint);
-int		xfs_trans_read_buf(struct xfs_mount *, xfs_trans_t *,
-				   struct xfs_buftarg *, xfs_daddr_t, int, uint,
-				   struct xfs_buf **);
+
+struct xfs_buf	*xfs_trans_get_buf_map(struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       uint flags);
+
+static inline struct xfs_buf *
+xfs_trans_get_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	uint			flags)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_get_buf_map(tp, target, &map, 1, flags);
+}
+
+int		xfs_trans_read_buf_map(struct xfs_mount *mp,
+				       struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       xfs_buf_flags_t flags,
+				       struct xfs_buf **bpp);
+
+static inline int
+xfs_trans_read_buf(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	xfs_buf_flags_t		flags,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_read_buf_map(mp, tp, target, &map, 1, flags, bpp);
+}
+
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);

fs/xfs/xfs_trans_ail.c

@@ -383,6 +383,12 @@ xfsaild_push(
 	}
 
 	spin_lock(&ailp->xa_lock);
+
+	/* barrier matches the xa_target update in xfs_ail_push() */
+	smp_rmb();
+	target = ailp->xa_target;
+	ailp->xa_target_prev = target;
+
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
 	if (!lip) {
 		/*
@@ -397,7 +403,6 @@ xfsaild_push(
 	XFS_STATS_INC(xs_push_ail);
 
 	lsn = lip->li_lsn;
-	target = ailp->xa_target;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
 		int	lock_result;
 
@@ -527,8 +532,32 @@ xfsaild(
 			__set_current_state(TASK_KILLABLE);
 		else
 			__set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(tout ?
-				 msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+		spin_lock(&ailp->xa_lock);
+
+		/*
+		 * Idle if the AIL is empty and we are not racing with a target
+		 * update. We check the AIL after we set the task to a sleep
+		 * state to guarantee that we either catch an xa_target update
+		 * or that a wake_up resets the state to TASK_RUNNING.
+		 * Otherwise, we run the risk of sleeping indefinitely.
+		 *
+		 * The barrier matches the xa_target update in xfs_ail_push().
+		 */
+		smp_rmb();
+		if (!xfs_ail_min(ailp) &&
+		    ailp->xa_target == ailp->xa_target_prev) {
+			spin_unlock(&ailp->xa_lock);
+			schedule();
+			tout = 0;
+			continue;
+		}
+		spin_unlock(&ailp->xa_lock);
+
+		if (tout)
+			schedule_timeout(msecs_to_jiffies(tout));
+
+		__set_current_state(TASK_RUNNING);
 
 		try_to_freeze();
 

fs/xfs/xfs_trans_buf.c

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

fs/xfs/xfs_trans_priv.h

@@ -67,6 +67,7 @@ struct xfs_ail {
 	struct task_struct	*xa_task;
 	struct list_head	xa_ail;
 	xfs_lsn_t		xa_target;
+	xfs_lsn_t		xa_target_prev;
 	struct list_head	xa_cursors;
 	spinlock_t		xa_lock;
 	xfs_lsn_t		xa_last_pushed_lsn;

fs/xfs/xfs_types.h

@@ -132,6 +132,20 @@ typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 #define	MAXEXTNUM	((xfs_extnum_t)0x7fffffff)	/* signed int */
 #define	MAXAEXTNUM	((xfs_aextnum_t)0x7fff)		/* signed short */
 
+/*
+ * Minimum and maximum blocksize and sectorsize.
+ * The blocksize upper limit is pretty much arbitrary.
+ * The sectorsize upper limit is due to sizeof(sb_sectsize).
+ */
+#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
+#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
+#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
+#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
+#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
+#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
+
 /*
  * Min numbers of data/attr fork btree root pointers.
  */

fs/xfs/xfs_utils.c

@@ -65,7 +65,6 @@ xfs_dir_ialloc(
 	xfs_trans_t	*ntp;
 	xfs_inode_t	*ip;
 	xfs_buf_t	*ialloc_context = NULL;
-	boolean_t	call_again = B_FALSE;
 	int		code;
 	uint		log_res;
 	uint		log_count;
@@ -91,7 +90,7 @@ xfs_dir_ialloc(
 	 * the inode(s) that we've just allocated.
 	 */
 	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc,
-			  &ialloc_context, &call_again, &ip);
+			  &ialloc_context, &ip);
 
 	/*
 	 * Return an error if we were unable to allocate a new inode.
@@ -102,19 +101,18 @@ xfs_dir_ialloc(
 		*ipp = NULL;
 		return code;
 	}
-	if (!call_again && (ip == NULL)) {
+	if (!ialloc_context && !ip) {
 		*ipp = NULL;
 		return XFS_ERROR(ENOSPC);
 	}
 
 	/*
-	 * If call_again is set, then we were unable to get an
+	 * If the AGI buffer is non-NULL, then we were unable to get an
 	 * inode in one operation.  We need to commit the current
 	 * transaction and call xfs_ialloc() again.  It is guaranteed
 	 * to succeed the second time.
 	 */
-	if (call_again) {
-
+	if (ialloc_context) {
 		/*
 		 * Normally, xfs_trans_commit releases all the locks.
 		 * We call bhold to hang on to the ialloc_context across
@@ -195,7 +193,7 @@ xfs_dir_ialloc(
 		 * this call should always succeed.
 		 */
 		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
-				  okalloc, &ialloc_context, &call_again, &ip);
+				  okalloc, &ialloc_context, &ip);
 
 		/*
 		 * If we get an error at this point, return to the caller
@@ -206,12 +204,11 @@ xfs_dir_ialloc(
 			*ipp = NULL;
 			return code;
 		}
-		ASSERT ((!call_again) && (ip != NULL));
+		ASSERT(!ialloc_context && ip);
 
 	} else {
-		if (committed != NULL) {
+		if (committed != NULL)
 			*committed = 0;
-		}
 	}
 
 	*ipp = ip;

fs/xfs/xfs_vnodeops.c

@@ -145,11 +145,6 @@ xfs_readlink(
 	return error;
 }
 
-/*
- * Flags for xfs_free_eofblocks
- */
-#define XFS_FREE_EOF_TRYLOCK	(1<<0)
-
 /*
  * This is called by xfs_inactive to free any blocks beyond eof
  * when the link count isn't zero and by xfs_dm_punch_hole() when
@@ -159,7 +154,7 @@ STATIC int
 xfs_free_eofblocks(
 	xfs_mount_t	*mp,
 	xfs_inode_t	*ip,
-	int		flags)
+	bool		need_iolock)
 {
 	xfs_trans_t	*tp;
 	int		error;
@@ -174,7 +169,7 @@ xfs_free_eofblocks(
 	 * of the file.  If not, then there is nothing to do.
 	 */
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
-	last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (last_fsb <= end_fsb)
 		return 0;
 	map_len = last_fsb - end_fsb;
@@ -201,13 +196,11 @@ xfs_free_eofblocks(
 		 */
 		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
 
-		if (flags & XFS_FREE_EOF_TRYLOCK) {
+		if (need_iolock) {
 			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
 				xfs_trans_cancel(tp, 0);
 				return 0;
 			}
-		} else {
-			xfs_ilock(ip, XFS_IOLOCK_EXCL);
 		}
 
 		error = xfs_trans_reserve(tp, 0,
@@ -217,7 +210,8 @@ xfs_free_eofblocks(
 		if (error) {
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			xfs_trans_cancel(tp, 0);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+			if (need_iolock)
+				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return error;
 		}
 
@@ -244,7 +238,10 @@ xfs_free_eofblocks(
 			error = xfs_trans_commit(tp,
 						XFS_TRANS_RELEASE_LOG_RES);
 		}
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL);
+
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (need_iolock)
+			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	}
 	return error;
 }
@@ -282,23 +279,15 @@ xfs_inactive_symlink_rmt(
 	 * free them all in one bunmapi call.
 	 */
 	ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
-	if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
-			XFS_TRANS_PERM_LOG_RES, XFS_ITRUNCATE_LOG_COUNT))) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
-		xfs_trans_cancel(tp, 0);
-		*tpp = NULL;
-		return error;
-	}
+
 	/*
 	 * Lock the inode, fix the size, and join it to the transaction.
 	 * Hold it so in the normal path, we still have it locked for
 	 * the second transaction.  In the error paths we need it
 	 * held so the cancel won't rele it, see below.
 	 */
-	xfs_ilock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
 	size = (int)ip->i_d.di_size;
 	ip->i_d.di_size = 0;
-	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	/*
 	 * Find the block(s) so we can inval and unmap them.
@@ -385,114 +374,14 @@ xfs_inactive_symlink_rmt(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		goto error0;
 	}
-	/*
-	 * Return with the inode locked but not joined to the transaction.
-	 */
+
+	xfs_trans_ijoin(tp, ip, 0);
 	*tpp = tp;
 	return 0;
 
  error1:
 	xfs_bmap_cancel(&free_list);
  error0:
-	/*
-	 * Have to come here with the inode locked and either
-	 * (held and in the transaction) or (not in the transaction).
-	 * If the inode isn't held then cancel would iput it, but
-	 * that's wrong since this is inactive and the vnode ref
-	 * count is 0 already.
-	 * Cancel won't do anything to the inode if held, but it still
-	 * needs to be locked until the cancel is done, if it was
-	 * joined to the transaction.
-	 */
-	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-	*tpp = NULL;
-	return error;
-
-}
-
-STATIC int
-xfs_inactive_symlink_local(
-	xfs_inode_t	*ip,
-	xfs_trans_t	**tpp)
-{
-	int		error;
-
-	ASSERT(ip->i_d.di_size <= XFS_IFORK_DSIZE(ip));
-	/*
-	 * We're freeing a symlink which fit into
-	 * the inode.  Just free the memory used
-	 * to hold the old symlink.
-	 */
-	error = xfs_trans_reserve(*tpp, 0,
-				  XFS_ITRUNCATE_LOG_RES(ip->i_mount),
-				  0, XFS_TRANS_PERM_LOG_RES,
-				  XFS_ITRUNCATE_LOG_COUNT);
-
-	if (error) {
-		xfs_trans_cancel(*tpp, 0);
-		*tpp = NULL;
-		return error;
-	}
-	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-
-	/*
-	 * Zero length symlinks _can_ exist.
-	 */
-	if (ip->i_df.if_bytes > 0) {
-		xfs_idata_realloc(ip,
-				  -(ip->i_df.if_bytes),
-				  XFS_DATA_FORK);
-		ASSERT(ip->i_df.if_bytes == 0);
-	}
-	return 0;
-}
-
-STATIC int
-xfs_inactive_attrs(
-	xfs_inode_t	*ip,
-	xfs_trans_t	**tpp)
-{
-	xfs_trans_t	*tp;
-	int		error;
-	xfs_mount_t	*mp;
-
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-	tp = *tpp;
-	mp = ip->i_mount;
-	ASSERT(ip->i_d.di_forkoff != 0);
-	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		goto error_unlock;
-
-	error = xfs_attr_inactive(ip);
-	if (error)
-		goto error_unlock;
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	error = xfs_trans_reserve(tp, 0,
-				  XFS_IFREE_LOG_RES(mp),
-				  0, XFS_TRANS_PERM_LOG_RES,
-				  XFS_INACTIVE_LOG_COUNT);
-	if (error)
-		goto error_cancel;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-	xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
-	ASSERT(ip->i_d.di_anextents == 0);
-
-	*tpp = tp;
-	return 0;
-
-error_cancel:
-	ASSERT(XFS_FORCED_SHUTDOWN(mp));
-	xfs_trans_cancel(tp, 0);
-error_unlock:
-	*tpp = NULL;
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return error;
 }
 
@@ -574,8 +463,7 @@ xfs_release(
 		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
 			return 0;
 
-		error = xfs_free_eofblocks(mp, ip,
-					   XFS_FREE_EOF_TRYLOCK);
+		error = xfs_free_eofblocks(mp, ip, true);
 		if (error)
 			return error;
 
@@ -604,7 +492,7 @@ xfs_inactive(
 	xfs_trans_t	*tp;
 	xfs_mount_t	*mp;
 	int		error;
-	int		truncate;
+	int		truncate = 0;
 
 	/*
 	 * If the inode is already free, then there can be nothing
@@ -616,17 +504,6 @@ xfs_inactive(
 		return VN_INACTIVE_CACHE;
 	}
 
-	/*
-	 * Only do a truncate if it's a regular file with
-	 * some actual space in it.  It's OK to look at the
-	 * inode's fields without the lock because we're the
-	 * only one with a reference to the inode.
-	 */
-	truncate = ((ip->i_d.di_nlink == 0) &&
-	    ((ip->i_d.di_size != 0) || XFS_ISIZE(ip) != 0 ||
-	     (ip->i_d.di_nextents > 0) || (ip->i_delayed_blks > 0)) &&
-	    S_ISREG(ip->i_d.di_mode));
-
 	mp = ip->i_mount;
 
 	error = 0;
@@ -643,99 +520,100 @@ xfs_inactive(
 		    (!(ip->i_d.di_flags &
 				(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) ||
 		     ip->i_delayed_blks != 0))) {
-			error = xfs_free_eofblocks(mp, ip, 0);
+			error = xfs_free_eofblocks(mp, ip, false);
 			if (error)
 				return VN_INACTIVE_CACHE;
 		}
 		goto out;
 	}
 
-	ASSERT(ip->i_d.di_nlink == 0);
+	if (S_ISREG(ip->i_d.di_mode) &&
+	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
+	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
+		truncate = 1;
 
 	error = xfs_qm_dqattach(ip, 0);
 	if (error)
 		return VN_INACTIVE_CACHE;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	if (truncate) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-		error = xfs_trans_reserve(tp, 0,
-					  XFS_ITRUNCATE_LOG_RES(mp),
-					  0, XFS_TRANS_PERM_LOG_RES,
-					  XFS_ITRUNCATE_LOG_COUNT);
-		if (error) {
-			/* Don't call itruncate_cleanup */
-			ASSERT(XFS_FORCED_SHUTDOWN(mp));
-			xfs_trans_cancel(tp, 0);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			return VN_INACTIVE_CACHE;
-		}
+	error = xfs_trans_reserve(tp, 0,
+			(truncate || S_ISLNK(ip->i_d.di_mode)) ?
+				XFS_ITRUNCATE_LOG_RES(mp) :
+				XFS_IFREE_LOG_RES(mp),
+			0,
+			XFS_TRANS_PERM_LOG_RES,
+			XFS_ITRUNCATE_LOG_COUNT);
+	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);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
 
+	if (S_ISLNK(ip->i_d.di_mode)) {
+		/*
+		 * Zero length symlinks _can_ exist.
+		 */
+		if (ip->i_d.di_size > XFS_IFORK_DSIZE(ip)) {
+			error = xfs_inactive_symlink_rmt(ip, &tp);
+			if (error)
+				goto out_cancel;
+		} else if (ip->i_df.if_bytes > 0) {
+			xfs_idata_realloc(ip, -(ip->i_df.if_bytes),
+					  XFS_DATA_FORK);
+			ASSERT(ip->i_df.if_bytes == 0);
+		}
+	} 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) {
-			xfs_trans_cancel(tp,
-				XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-			return VN_INACTIVE_CACHE;
-		}
+		if (error)
+			goto out_cancel;
 
 		ASSERT(ip->i_d.di_nextents == 0);
-	} else if (S_ISLNK(ip->i_d.di_mode)) {
+	}
 
-		/*
-		 * If we get an error while cleaning up a
-		 * symlink we bail out.
-		 */
-		error = (ip->i_d.di_size > XFS_IFORK_DSIZE(ip)) ?
-			xfs_inactive_symlink_rmt(ip, &tp) :
-			xfs_inactive_symlink_local(ip, &tp);
+	/*
+	 * If there are attributes associated with the file then blow them away
+	 * now.  The code calls a routine that recursively deconstructs the
+	 * attribute fork.  We need to just commit the current transaction
+	 * because we can't use it for xfs_attr_inactive().
+	 */
+	if (ip->i_d.di_anextents > 0) {
+		ASSERT(ip->i_d.di_forkoff != 0);
 
-		if (error) {
-			ASSERT(tp == NULL);
-			return VN_INACTIVE_CACHE;
-		}
+		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		if (error)
+			goto out_unlock;
 
-		xfs_trans_ijoin(tp, ip, 0);
-	} else {
+		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, 0,
 					  XFS_IFREE_LOG_RES(mp),
 					  0, XFS_TRANS_PERM_LOG_RES,
 					  XFS_INACTIVE_LOG_COUNT);
 		if (error) {
-			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			xfs_trans_cancel(tp, 0);
-			return VN_INACTIVE_CACHE;
+			goto out;
 		}
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
 	}
 
-	/*
-	 * If there are attributes associated with the file
-	 * then blow them away now.  The code calls a routine
-	 * that recursively deconstructs the attribute fork.
-	 * We need to just commit the current transaction
-	 * because we can't use it for xfs_attr_inactive().
-	 */
-	if (ip->i_d.di_anextents > 0) {
-		error = xfs_inactive_attrs(ip, &tp);
-		/*
-		 * If we got an error, the transaction is already
-		 * cancelled, and the inode is unlocked. Just get out.
-		 */
-		 if (error)
-			 return VN_INACTIVE_CACHE;
-	} else if (ip->i_afp) {
+	if (ip->i_afp)
 		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-	}
+
+	ASSERT(ip->i_d.di_anextents == 0);
 
 	/*
 	 * Free the inode.
@@ -779,10 +657,13 @@ xfs_inactive(
 	 * Release the dquots held by inode, if any.
 	 */
 	xfs_qm_dqdetach(ip);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-
- out:
+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;
 }
 
 /*
@@ -2262,10 +2143,10 @@ xfs_change_file_space(
 
 	llen = bf->l_len > 0 ? bf->l_len - 1 : bf->l_len;
 
-	if (   (bf->l_start < 0)
-	    || (bf->l_start > XFS_MAXIOFFSET(mp))
-	    || (bf->l_start + llen < 0)
-	    || (bf->l_start + llen > XFS_MAXIOFFSET(mp)))
+	if (bf->l_start < 0 ||
+	    bf->l_start > mp->m_super->s_maxbytes ||
+	    bf->l_start + llen < 0 ||
+	    bf->l_start + llen > mp->m_super->s_maxbytes)
 		return XFS_ERROR(EINVAL);
 
 	bf->l_whence = 0;