v4.19.13 snapshot.
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
new file mode 100644
index 0000000..c6299f8
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -0,0 +1,1302 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr_sf.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_trans.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_error.h"
+#include "xfs_quota.h"
+#include "xfs_trans_space.h"
+#include "xfs_trace.h"
+
+/*
+ * xfs_attr.c
+ *
+ * Provide the external interfaces to manage attribute lists.
+ */
+
+/*========================================================================
+ * Function prototypes for the kernel.
+ *========================================================================*/
+
+/*
+ * Internal routines when attribute list fits inside the inode.
+ */
+STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args);
+
+/*
+ * Internal routines when attribute list is one block.
+ */
+STATIC int xfs_attr_leaf_get(xfs_da_args_t *args);
+STATIC int xfs_attr_leaf_addname(xfs_da_args_t *args);
+STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args);
+
+/*
+ * Internal routines when attribute list is more than one block.
+ */
+STATIC int xfs_attr_node_get(xfs_da_args_t *args);
+STATIC int xfs_attr_node_addname(xfs_da_args_t *args);
+STATIC int xfs_attr_node_removename(xfs_da_args_t *args);
+STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
+STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
+
+
+STATIC int
+xfs_attr_args_init(
+	struct xfs_da_args	*args,
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	int			flags)
+{
+
+	if (!name)
+		return -EINVAL;
+
+	memset(args, 0, sizeof(*args));
+	args->geo = dp->i_mount->m_attr_geo;
+	args->whichfork = XFS_ATTR_FORK;
+	args->dp = dp;
+	args->flags = flags;
+	args->name = name;
+	args->namelen = strlen((const char *)name);
+	if (args->namelen >= MAXNAMELEN)
+		return -EFAULT;		/* match IRIX behaviour */
+
+	args->hashval = xfs_da_hashname(args->name, args->namelen);
+	return 0;
+}
+
+int
+xfs_inode_hasattr(
+	struct xfs_inode	*ip)
+{
+	if (!XFS_IFORK_Q(ip) ||
+	    (ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+	     ip->i_d.di_anextents == 0))
+		return 0;
+	return 1;
+}
+
+/*========================================================================
+ * Overall external interface routines.
+ *========================================================================*/
+
+/* Retrieve an extended attribute and its value.  Must have ilock. */
+int
+xfs_attr_get_ilocked(
+	struct xfs_inode	*ip,
+	struct xfs_da_args	*args)
+{
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	if (!xfs_inode_hasattr(ip))
+		return -ENOATTR;
+	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_getvalue(args);
+	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
+		return xfs_attr_leaf_get(args);
+	else
+		return xfs_attr_node_get(args);
+}
+
+/* Retrieve an extended attribute by name, and its value. */
+int
+xfs_attr_get(
+	struct xfs_inode	*ip,
+	const unsigned char	*name,
+	unsigned char		*value,
+	int			*valuelenp,
+	int			flags)
+{
+	struct xfs_da_args	args;
+	uint			lock_mode;
+	int			error;
+
+	XFS_STATS_INC(ip->i_mount, xs_attr_get);
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	error = xfs_attr_args_init(&args, ip, name, flags);
+	if (error)
+		return error;
+
+	args.value = value;
+	args.valuelen = *valuelenp;
+	/* Entirely possible to look up a name which doesn't exist */
+	args.op_flags = XFS_DA_OP_OKNOENT;
+
+	lock_mode = xfs_ilock_attr_map_shared(ip);
+	error = xfs_attr_get_ilocked(ip, &args);
+	xfs_iunlock(ip, lock_mode);
+
+	*valuelenp = args.valuelen;
+	return error == -EEXIST ? 0 : error;
+}
+
+/*
+ * Calculate how many blocks we need for the new attribute,
+ */
+STATIC int
+xfs_attr_calc_size(
+	struct xfs_da_args	*args,
+	int			*local)
+{
+	struct xfs_mount	*mp = args->dp->i_mount;
+	int			size;
+	int			nblks;
+
+	/*
+	 * Determine space new attribute will use, and if it would be
+	 * "local" or "remote" (note: local != inline).
+	 */
+	size = xfs_attr_leaf_newentsize(args, local);
+	nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
+	if (*local) {
+		if (size > (args->geo->blksize / 2)) {
+			/* Double split possible */
+			nblks *= 2;
+		}
+	} else {
+		/*
+		 * Out of line attribute, cannot double split, but
+		 * make room for the attribute value itself.
+		 */
+		uint	dblocks = xfs_attr3_rmt_blocks(mp, args->valuelen);
+		nblks += dblocks;
+		nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
+	}
+
+	return nblks;
+}
+
+int
+xfs_attr_set(
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	unsigned char		*value,
+	int			valuelen,
+	int			flags)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_buf		*leaf_bp = NULL;
+	struct xfs_da_args	args;
+	struct xfs_trans_res	tres;
+	int			rsvd = (flags & ATTR_ROOT) != 0;
+	int			error, err2, local;
+
+	XFS_STATS_INC(mp, xs_attr_set);
+
+	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+		return -EIO;
+
+	error = xfs_attr_args_init(&args, dp, name, flags);
+	if (error)
+		return error;
+
+	args.value = value;
+	args.valuelen = valuelen;
+	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+	args.total = xfs_attr_calc_size(&args, &local);
+
+	error = xfs_qm_dqattach(dp);
+	if (error)
+		return error;
+
+	/*
+	 * If the inode doesn't have an attribute fork, add one.
+	 * (inode must not be locked when we call this routine)
+	 */
+	if (XFS_IFORK_Q(dp) == 0) {
+		int sf_size = sizeof(xfs_attr_sf_hdr_t) +
+			XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
+
+		error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
+		if (error)
+			return error;
+	}
+
+	tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+			 M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
+	tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
+	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
+
+	/*
+	 * Root fork attributes can use reserved data blocks for this
+	 * operation if necessary
+	 */
+	error = xfs_trans_alloc(mp, &tres, args.total, 0,
+			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
+	if (error)
+		return error;
+
+	xfs_ilock(dp, XFS_ILOCK_EXCL);
+	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
+				rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
+				       XFS_QMOPT_RES_REGBLKS);
+	if (error) {
+		xfs_iunlock(dp, XFS_ILOCK_EXCL);
+		xfs_trans_cancel(args.trans);
+		return error;
+	}
+
+	xfs_trans_ijoin(args.trans, dp, 0);
+
+	/*
+	 * If the attribute list is non-existent or a shortform list,
+	 * upgrade it to a single-leaf-block attribute list.
+	 */
+	if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
+	    (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+	     dp->i_d.di_anextents == 0)) {
+
+		/*
+		 * Build initial attribute list (if required).
+		 */
+		if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
+			xfs_attr_shortform_create(&args);
+
+		/*
+		 * Try to add the attr to the attribute list in
+		 * the inode.
+		 */
+		error = xfs_attr_shortform_addname(&args);
+		if (error != -ENOSPC) {
+			/*
+			 * Commit the shortform mods, and we're done.
+			 * NOTE: this is also the error path (EEXIST, etc).
+			 */
+			ASSERT(args.trans != NULL);
+
+			/*
+			 * If this is a synchronous mount, make sure that
+			 * the transaction goes to disk before returning
+			 * to the user.
+			 */
+			if (mp->m_flags & XFS_MOUNT_WSYNC)
+				xfs_trans_set_sync(args.trans);
+
+			if (!error && (flags & ATTR_KERNOTIME) == 0) {
+				xfs_trans_ichgtime(args.trans, dp,
+							XFS_ICHGTIME_CHG);
+			}
+			err2 = xfs_trans_commit(args.trans);
+			xfs_iunlock(dp, XFS_ILOCK_EXCL);
+
+			return error ? error : err2;
+		}
+
+		/*
+		 * It won't fit in the shortform, transform to a leaf block.
+		 * GROT: another possible req'mt for a double-split btree op.
+		 */
+		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
+		if (error)
+			goto out;
+		/*
+		 * Prevent the leaf buffer from being unlocked so that a
+		 * concurrent AIL push cannot grab the half-baked leaf
+		 * buffer and run into problems with the write verifier.
+		 */
+		xfs_trans_bhold(args.trans, leaf_bp);
+		error = xfs_defer_finish(&args.trans);
+		if (error)
+			goto out;
+
+		/*
+		 * Commit the leaf transformation.  We'll need another (linked)
+		 * transaction to add the new attribute to the leaf, which
+		 * means that we have to hold & join the leaf buffer here too.
+		 */
+		error = xfs_trans_roll_inode(&args.trans, dp);
+		if (error)
+			goto out;
+		xfs_trans_bjoin(args.trans, leaf_bp);
+		leaf_bp = NULL;
+	}
+
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+		error = xfs_attr_leaf_addname(&args);
+	else
+		error = xfs_attr_node_addname(&args);
+	if (error)
+		goto out;
+
+	/*
+	 * If this is a synchronous mount, make sure that the
+	 * transaction goes to disk before returning to the user.
+	 */
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(args.trans);
+
+	if ((flags & ATTR_KERNOTIME) == 0)
+		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
+
+	/*
+	 * Commit the last in the sequence of transactions.
+	 */
+	xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
+	error = xfs_trans_commit(args.trans);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+
+	return error;
+
+out:
+	if (leaf_bp)
+		xfs_trans_brelse(args.trans, leaf_bp);
+	if (args.trans)
+		xfs_trans_cancel(args.trans);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+	return error;
+}
+
+/*
+ * Generic handler routine to remove a name from an attribute list.
+ * Transitions attribute list from Btree to shortform as necessary.
+ */
+int
+xfs_attr_remove(
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	int			flags)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_args	args;
+	int			error;
+
+	XFS_STATS_INC(mp, xs_attr_remove);
+
+	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+		return -EIO;
+
+	error = xfs_attr_args_init(&args, dp, name, flags);
+	if (error)
+		return error;
+
+	/*
+	 * we have no control over the attribute names that userspace passes us
+	 * to remove, so we have to allow the name lookup prior to attribute
+	 * removal to fail.
+	 */
+	args.op_flags = XFS_DA_OP_OKNOENT;
+
+	error = xfs_qm_dqattach(dp);
+	if (error)
+		return error;
+
+	/*
+	 * Root fork attributes can use reserved data blocks for this
+	 * operation if necessary
+	 */
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrrm,
+			XFS_ATTRRM_SPACE_RES(mp), 0,
+			(flags & ATTR_ROOT) ? XFS_TRANS_RESERVE : 0,
+			&args.trans);
+	if (error)
+		return error;
+
+	xfs_ilock(dp, XFS_ILOCK_EXCL);
+	/*
+	 * No need to make quota reservations here. We expect to release some
+	 * blocks not allocate in the common case.
+	 */
+	xfs_trans_ijoin(args.trans, dp, 0);
+
+	if (!xfs_inode_hasattr(dp)) {
+		error = -ENOATTR;
+	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
+		error = xfs_attr_shortform_remove(&args);
+	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+		error = xfs_attr_leaf_removename(&args);
+	} else {
+		error = xfs_attr_node_removename(&args);
+	}
+
+	if (error)
+		goto out;
+
+	/*
+	 * If this is a synchronous mount, make sure that the
+	 * transaction goes to disk before returning to the user.
+	 */
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(args.trans);
+
+	if ((flags & ATTR_KERNOTIME) == 0)
+		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
+
+	/*
+	 * Commit the last in the sequence of transactions.
+	 */
+	xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
+	error = xfs_trans_commit(args.trans);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+
+	return error;
+
+out:
+	if (args.trans)
+		xfs_trans_cancel(args.trans);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+	return error;
+}
+
+/*========================================================================
+ * External routines when attribute list is inside the inode
+ *========================================================================*/
+
+/*
+ * Add a name to the shortform attribute list structure
+ * This is the external routine.
+ */
+STATIC int
+xfs_attr_shortform_addname(xfs_da_args_t *args)
+{
+	int newsize, forkoff, retval;
+
+	trace_xfs_attr_sf_addname(args);
+
+	retval = xfs_attr_shortform_lookup(args);
+	if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
+		return retval;
+	} else if (retval == -EEXIST) {
+		if (args->flags & ATTR_CREATE)
+			return retval;
+		retval = xfs_attr_shortform_remove(args);
+		if (retval)
+			return retval;
+		/*
+		 * Since we have removed the old attr, clear ATTR_REPLACE so
+		 * that the leaf format add routine won't trip over the attr
+		 * not being around.
+		 */
+		args->flags &= ~ATTR_REPLACE;
+	}
+
+	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
+	    args->valuelen >= XFS_ATTR_SF_ENTSIZE_MAX)
+		return -ENOSPC;
+
+	newsize = XFS_ATTR_SF_TOTSIZE(args->dp);
+	newsize += XFS_ATTR_SF_ENTSIZE_BYNAME(args->namelen, args->valuelen);
+
+	forkoff = xfs_attr_shortform_bytesfit(args->dp, newsize);
+	if (!forkoff)
+		return -ENOSPC;
+
+	xfs_attr_shortform_add(args, forkoff);
+	return 0;
+}
+
+
+/*========================================================================
+ * External routines when attribute list is one block
+ *========================================================================*/
+
+/*
+ * Add a name to the leaf attribute list structure
+ *
+ * This leaf block cannot have a "remote" value, we only call this routine
+ * if bmap_one_block() says there is only one block (ie: no remote blks).
+ */
+STATIC int
+xfs_attr_leaf_addname(
+	struct xfs_da_args	*args)
+{
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
+
+	trace_xfs_attr_leaf_addname(args);
+
+	/*
+	 * Read the (only) block in the attribute list in.
+	 */
+	dp = args->dp;
+	args->blkno = 0;
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+	if (error)
+		return error;
+
+	/*
+	 * Look up the given attribute in the leaf block.  Figure out if
+	 * the given flags produce an error or call for an atomic rename.
+	 */
+	retval = xfs_attr3_leaf_lookup_int(bp, args);
+	if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
+		xfs_trans_brelse(args->trans, bp);
+		return retval;
+	} else if (retval == -EEXIST) {
+		if (args->flags & ATTR_CREATE) {	/* pure create op */
+			xfs_trans_brelse(args->trans, bp);
+			return retval;
+		}
+
+		trace_xfs_attr_leaf_replace(args);
+
+		/* save the attribute state for later removal*/
+		args->op_flags |= XFS_DA_OP_RENAME;	/* an atomic rename */
+		args->blkno2 = args->blkno;		/* set 2nd entry info*/
+		args->index2 = args->index;
+		args->rmtblkno2 = args->rmtblkno;
+		args->rmtblkcnt2 = args->rmtblkcnt;
+		args->rmtvaluelen2 = args->rmtvaluelen;
+
+		/*
+		 * clear the remote attr state now that it is saved so that the
+		 * values reflect the state of the attribute we are about to
+		 * add, not the attribute we just found and will remove later.
+		 */
+		args->rmtblkno = 0;
+		args->rmtblkcnt = 0;
+		args->rmtvaluelen = 0;
+	}
+
+	/*
+	 * Add the attribute to the leaf block, transitioning to a Btree
+	 * if required.
+	 */
+	retval = xfs_attr3_leaf_add(bp, args);
+	if (retval == -ENOSPC) {
+		/*
+		 * Promote the attribute list to the Btree format, then
+		 * Commit that transaction so that the node_addname() call
+		 * can manage its own transactions.
+		 */
+		error = xfs_attr3_leaf_to_node(args);
+		if (error)
+			return error;
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			return error;
+
+		/*
+		 * Commit the current trans (including the inode) and start
+		 * a new one.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			return error;
+
+		/*
+		 * Fob the whole rest of the problem off on the Btree code.
+		 */
+		error = xfs_attr_node_addname(args);
+		return error;
+	}
+
+	/*
+	 * Commit the transaction that added the attr name so that
+	 * later routines can manage their own transactions.
+	 */
+	error = xfs_trans_roll_inode(&args->trans, dp);
+	if (error)
+		return error;
+
+	/*
+	 * If there was an out-of-line value, allocate the blocks we
+	 * identified for its storage and copy the value.  This is done
+	 * after we create the attribute so that we don't overflow the
+	 * maximum size of a transaction and/or hit a deadlock.
+	 */
+	if (args->rmtblkno > 0) {
+		error = xfs_attr_rmtval_set(args);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If this is an atomic rename operation, we must "flip" the
+	 * incomplete flags on the "new" and "old" attribute/value pairs
+	 * so that one disappears and one appears atomically.  Then we
+	 * must remove the "old" attribute/value pair.
+	 */
+	if (args->op_flags & XFS_DA_OP_RENAME) {
+		/*
+		 * In a separate transaction, set the incomplete flag on the
+		 * "old" attr and clear the incomplete flag on the "new" attr.
+		 */
+		error = xfs_attr3_leaf_flipflags(args);
+		if (error)
+			return error;
+
+		/*
+		 * Dismantle the "old" attribute/value pair by removing
+		 * a "remote" value (if it exists).
+		 */
+		args->index = args->index2;
+		args->blkno = args->blkno2;
+		args->rmtblkno = args->rmtblkno2;
+		args->rmtblkcnt = args->rmtblkcnt2;
+		args->rmtvaluelen = args->rmtvaluelen2;
+		if (args->rmtblkno) {
+			error = xfs_attr_rmtval_remove(args);
+			if (error)
+				return error;
+		}
+
+		/*
+		 * Read in the block containing the "old" attr, then
+		 * remove the "old" attr from that block (neat, huh!)
+		 */
+		error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
+					   -1, &bp);
+		if (error)
+			return error;
+
+		xfs_attr3_leaf_remove(bp, args);
+
+		/*
+		 * If the result is small enough, shrink it all into the inode.
+		 */
+		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
+			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+			/* bp is gone due to xfs_da_shrink_inode */
+			if (error)
+				return error;
+			error = xfs_defer_finish(&args->trans);
+			if (error)
+				return error;
+		}
+
+		/*
+		 * Commit the remove and start the next trans in series.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+
+	} else if (args->rmtblkno > 0) {
+		/*
+		 * Added a "remote" value, just clear the incomplete flag.
+		 */
+		error = xfs_attr3_leaf_clearflag(args);
+	}
+	return error;
+}
+
+/*
+ * Remove a name from the leaf attribute list structure
+ *
+ * This leaf block cannot have a "remote" value, we only call this routine
+ * if bmap_one_block() says there is only one block (ie: no remote blks).
+ */
+STATIC int
+xfs_attr_leaf_removename(
+	struct xfs_da_args	*args)
+{
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			error, forkoff;
+
+	trace_xfs_attr_leaf_removename(args);
+
+	/*
+	 * Remove the attribute.
+	 */
+	dp = args->dp;
+	args->blkno = 0;
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+	if (error)
+		return error;
+
+	error = xfs_attr3_leaf_lookup_int(bp, args);
+	if (error == -ENOATTR) {
+		xfs_trans_brelse(args->trans, bp);
+		return error;
+	}
+
+	xfs_attr3_leaf_remove(bp, args);
+
+	/*
+	 * If the result is small enough, shrink it all into the inode.
+	 */
+	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
+		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+		/* bp is gone due to xfs_da_shrink_inode */
+		if (error)
+			return error;
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			return error;
+	}
+	return 0;
+}
+
+/*
+ * Look up a name in a leaf attribute list structure.
+ *
+ * This leaf block cannot have a "remote" value, we only call this routine
+ * if bmap_one_block() says there is only one block (ie: no remote blks).
+ */
+STATIC int
+xfs_attr_leaf_get(xfs_da_args_t *args)
+{
+	struct xfs_buf *bp;
+	int error;
+
+	trace_xfs_attr_leaf_get(args);
+
+	args->blkno = 0;
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+	if (error)
+		return error;
+
+	error = xfs_attr3_leaf_lookup_int(bp, args);
+	if (error != -EEXIST)  {
+		xfs_trans_brelse(args->trans, bp);
+		return error;
+	}
+	error = xfs_attr3_leaf_getvalue(bp, args);
+	xfs_trans_brelse(args->trans, bp);
+	if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
+		error = xfs_attr_rmtval_get(args);
+	}
+	return error;
+}
+
+/*========================================================================
+ * External routines when attribute list size > geo->blksize
+ *========================================================================*/
+
+/*
+ * Add a name to a Btree-format attribute list.
+ *
+ * This will involve walking down the Btree, and may involve splitting
+ * leaf nodes and even splitting intermediate nodes up to and including
+ * the root node (a special case of an intermediate node).
+ *
+ * "Remote" attribute values confuse the issue and atomic rename operations
+ * add a whole extra layer of confusion on top of that.
+ */
+STATIC int
+xfs_attr_node_addname(
+	struct xfs_da_args	*args)
+{
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_mount	*mp;
+	int			retval, error;
+
+	trace_xfs_attr_node_addname(args);
+
+	/*
+	 * Fill in bucket of arguments/results/context to carry around.
+	 */
+	dp = args->dp;
+	mp = dp->i_mount;
+restart:
+	state = xfs_da_state_alloc();
+	state->args = args;
+	state->mp = mp;
+
+	/*
+	 * Search to see if name already exists, and get back a pointer
+	 * to where it should go.
+	 */
+	error = xfs_da3_node_lookup_int(state, &retval);
+	if (error)
+		goto out;
+	blk = &state->path.blk[ state->path.active-1 ];
+	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+	if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
+		goto out;
+	} else if (retval == -EEXIST) {
+		if (args->flags & ATTR_CREATE)
+			goto out;
+
+		trace_xfs_attr_node_replace(args);
+
+		/* save the attribute state for later removal*/
+		args->op_flags |= XFS_DA_OP_RENAME;	/* atomic rename op */
+		args->blkno2 = args->blkno;		/* set 2nd entry info*/
+		args->index2 = args->index;
+		args->rmtblkno2 = args->rmtblkno;
+		args->rmtblkcnt2 = args->rmtblkcnt;
+		args->rmtvaluelen2 = args->rmtvaluelen;
+
+		/*
+		 * clear the remote attr state now that it is saved so that the
+		 * values reflect the state of the attribute we are about to
+		 * add, not the attribute we just found and will remove later.
+		 */
+		args->rmtblkno = 0;
+		args->rmtblkcnt = 0;
+		args->rmtvaluelen = 0;
+	}
+
+	retval = xfs_attr3_leaf_add(blk->bp, state->args);
+	if (retval == -ENOSPC) {
+		if (state->path.active == 1) {
+			/*
+			 * Its really a single leaf node, but it had
+			 * out-of-line values so it looked like it *might*
+			 * have been a b-tree.
+			 */
+			xfs_da_state_free(state);
+			state = NULL;
+			error = xfs_attr3_leaf_to_node(args);
+			if (error)
+				goto out;
+			error = xfs_defer_finish(&args->trans);
+			if (error)
+				goto out;
+
+			/*
+			 * Commit the node conversion and start the next
+			 * trans in the chain.
+			 */
+			error = xfs_trans_roll_inode(&args->trans, dp);
+			if (error)
+				goto out;
+
+			goto restart;
+		}
+
+		/*
+		 * Split as many Btree elements as required.
+		 * This code tracks the new and old attr's location
+		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
+		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
+		 */
+		error = xfs_da3_split(state);
+		if (error)
+			goto out;
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			goto out;
+	} else {
+		/*
+		 * Addition succeeded, update Btree hashvals.
+		 */
+		xfs_da3_fixhashpath(state, &state->path);
+	}
+
+	/*
+	 * Kill the state structure, we're done with it and need to
+	 * allow the buffers to come back later.
+	 */
+	xfs_da_state_free(state);
+	state = NULL;
+
+	/*
+	 * Commit the leaf addition or btree split and start the next
+	 * trans in the chain.
+	 */
+	error = xfs_trans_roll_inode(&args->trans, dp);
+	if (error)
+		goto out;
+
+	/*
+	 * If there was an out-of-line value, allocate the blocks we
+	 * identified for its storage and copy the value.  This is done
+	 * after we create the attribute so that we don't overflow the
+	 * maximum size of a transaction and/or hit a deadlock.
+	 */
+	if (args->rmtblkno > 0) {
+		error = xfs_attr_rmtval_set(args);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If this is an atomic rename operation, we must "flip" the
+	 * incomplete flags on the "new" and "old" attribute/value pairs
+	 * so that one disappears and one appears atomically.  Then we
+	 * must remove the "old" attribute/value pair.
+	 */
+	if (args->op_flags & XFS_DA_OP_RENAME) {
+		/*
+		 * In a separate transaction, set the incomplete flag on the
+		 * "old" attr and clear the incomplete flag on the "new" attr.
+		 */
+		error = xfs_attr3_leaf_flipflags(args);
+		if (error)
+			goto out;
+
+		/*
+		 * Dismantle the "old" attribute/value pair by removing
+		 * a "remote" value (if it exists).
+		 */
+		args->index = args->index2;
+		args->blkno = args->blkno2;
+		args->rmtblkno = args->rmtblkno2;
+		args->rmtblkcnt = args->rmtblkcnt2;
+		args->rmtvaluelen = args->rmtvaluelen2;
+		if (args->rmtblkno) {
+			error = xfs_attr_rmtval_remove(args);
+			if (error)
+				return error;
+		}
+
+		/*
+		 * Re-find the "old" attribute entry after any split ops.
+		 * The INCOMPLETE flag means that we will find the "old"
+		 * attr, not the "new" one.
+		 */
+		args->flags |= XFS_ATTR_INCOMPLETE;
+		state = xfs_da_state_alloc();
+		state->args = args;
+		state->mp = mp;
+		state->inleaf = 0;
+		error = xfs_da3_node_lookup_int(state, &retval);
+		if (error)
+			goto out;
+
+		/*
+		 * Remove the name and update the hashvals in the tree.
+		 */
+		blk = &state->path.blk[ state->path.active-1 ];
+		ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+		error = xfs_attr3_leaf_remove(blk->bp, args);
+		xfs_da3_fixhashpath(state, &state->path);
+
+		/*
+		 * Check to see if the tree needs to be collapsed.
+		 */
+		if (retval && (state->path.active > 1)) {
+			error = xfs_da3_join(state);
+			if (error)
+				goto out;
+			error = xfs_defer_finish(&args->trans);
+			if (error)
+				goto out;
+		}
+
+		/*
+		 * Commit and start the next trans in the chain.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			goto out;
+
+	} else if (args->rmtblkno > 0) {
+		/*
+		 * Added a "remote" value, just clear the incomplete flag.
+		 */
+		error = xfs_attr3_leaf_clearflag(args);
+		if (error)
+			goto out;
+	}
+	retval = error = 0;
+
+out:
+	if (state)
+		xfs_da_state_free(state);
+	if (error)
+		return error;
+	return retval;
+}
+
+/*
+ * Remove a name from a B-tree attribute list.
+ *
+ * This will involve walking down the Btree, and may involve joining
+ * leaf nodes and even joining intermediate nodes up to and including
+ * the root node (a special case of an intermediate node).
+ */
+STATIC int
+xfs_attr_node_removename(
+	struct xfs_da_args	*args)
+{
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
+
+	trace_xfs_attr_node_removename(args);
+
+	/*
+	 * Tie a string around our finger to remind us where we are.
+	 */
+	dp = args->dp;
+	state = xfs_da_state_alloc();
+	state->args = args;
+	state->mp = dp->i_mount;
+
+	/*
+	 * Search to see if name exists, and get back a pointer to it.
+	 */
+	error = xfs_da3_node_lookup_int(state, &retval);
+	if (error || (retval != -EEXIST)) {
+		if (error == 0)
+			error = retval;
+		goto out;
+	}
+
+	/*
+	 * If there is an out-of-line value, de-allocate the blocks.
+	 * This is done before we remove the attribute so that we don't
+	 * overflow the maximum size of a transaction and/or hit a deadlock.
+	 */
+	blk = &state->path.blk[ state->path.active-1 ];
+	ASSERT(blk->bp != NULL);
+	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+	if (args->rmtblkno > 0) {
+		/*
+		 * Fill in disk block numbers in the state structure
+		 * so that we can get the buffers back after we commit
+		 * several transactions in the following calls.
+		 */
+		error = xfs_attr_fillstate(state);
+		if (error)
+			goto out;
+
+		/*
+		 * Mark the attribute as INCOMPLETE, then bunmapi() the
+		 * remote value.
+		 */
+		error = xfs_attr3_leaf_setflag(args);
+		if (error)
+			goto out;
+		error = xfs_attr_rmtval_remove(args);
+		if (error)
+			goto out;
+
+		/*
+		 * Refill the state structure with buffers, the prior calls
+		 * released our buffers.
+		 */
+		error = xfs_attr_refillstate(state);
+		if (error)
+			goto out;
+	}
+
+	/*
+	 * Remove the name and update the hashvals in the tree.
+	 */
+	blk = &state->path.blk[ state->path.active-1 ];
+	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+	retval = xfs_attr3_leaf_remove(blk->bp, args);
+	xfs_da3_fixhashpath(state, &state->path);
+
+	/*
+	 * Check to see if the tree needs to be collapsed.
+	 */
+	if (retval && (state->path.active > 1)) {
+		error = xfs_da3_join(state);
+		if (error)
+			goto out;
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			goto out;
+		/*
+		 * Commit the Btree join operation and start a new trans.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			goto out;
+	}
+
+	/*
+	 * If the result is small enough, push it all into the inode.
+	 */
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+		/*
+		 * Have to get rid of the copy of this dabuf in the state.
+		 */
+		ASSERT(state->path.active == 1);
+		ASSERT(state->path.blk[0].bp);
+		state->path.blk[0].bp = NULL;
+
+		error = xfs_attr3_leaf_read(args->trans, args->dp, 0, -1, &bp);
+		if (error)
+			goto out;
+
+		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
+			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+			/* bp is gone due to xfs_da_shrink_inode */
+			if (error)
+				goto out;
+			error = xfs_defer_finish(&args->trans);
+			if (error)
+				goto out;
+		} else
+			xfs_trans_brelse(args->trans, bp);
+	}
+	error = 0;
+
+out:
+	xfs_da_state_free(state);
+	return error;
+}
+
+/*
+ * Fill in the disk block numbers in the state structure for the buffers
+ * that are attached to the state structure.
+ * This is done so that we can quickly reattach ourselves to those buffers
+ * after some set of transaction commits have released these buffers.
+ */
+STATIC int
+xfs_attr_fillstate(xfs_da_state_t *state)
+{
+	xfs_da_state_path_t *path;
+	xfs_da_state_blk_t *blk;
+	int level;
+
+	trace_xfs_attr_fillstate(state->args);
+
+	/*
+	 * Roll down the "path" in the state structure, storing the on-disk
+	 * block number for those buffers in the "path".
+	 */
+	path = &state->path;
+	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_BUF_ADDR(blk->bp);
+			blk->bp = NULL;
+		} else {
+			blk->disk_blkno = 0;
+		}
+	}
+
+	/*
+	 * Roll down the "altpath" in the state structure, storing the on-disk
+	 * block number for those buffers in the "altpath".
+	 */
+	path = &state->altpath;
+	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_BUF_ADDR(blk->bp);
+			blk->bp = NULL;
+		} else {
+			blk->disk_blkno = 0;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Reattach the buffers to the state structure based on the disk block
+ * numbers stored in the state structure.
+ * This is done after some set of transaction commits have released those
+ * buffers from our grip.
+ */
+STATIC int
+xfs_attr_refillstate(xfs_da_state_t *state)
+{
+	xfs_da_state_path_t *path;
+	xfs_da_state_blk_t *blk;
+	int level, error;
+
+	trace_xfs_attr_refillstate(state->args);
+
+	/*
+	 * Roll down the "path" in the state structure, storing the on-disk
+	 * block number for those buffers in the "path".
+	 */
+	path = &state->path;
+	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+		if (blk->disk_blkno) {
+			error = xfs_da3_node_read(state->args->trans,
+						state->args->dp,
+						blk->blkno, blk->disk_blkno,
+						&blk->bp, XFS_ATTR_FORK);
+			if (error)
+				return error;
+		} else {
+			blk->bp = NULL;
+		}
+	}
+
+	/*
+	 * Roll down the "altpath" in the state structure, storing the on-disk
+	 * block number for those buffers in the "altpath".
+	 */
+	path = &state->altpath;
+	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+		if (blk->disk_blkno) {
+			error = xfs_da3_node_read(state->args->trans,
+						state->args->dp,
+						blk->blkno, blk->disk_blkno,
+						&blk->bp, XFS_ATTR_FORK);
+			if (error)
+				return error;
+		} else {
+			blk->bp = NULL;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Look up a filename in a node attribute list.
+ *
+ * This routine gets called for any attribute fork that has more than one
+ * block, ie: both true Btree attr lists and for single-leaf-blocks with
+ * "remote" values taking up more blocks.
+ */
+STATIC int
+xfs_attr_node_get(xfs_da_args_t *args)
+{
+	xfs_da_state_t *state;
+	xfs_da_state_blk_t *blk;
+	int error, retval;
+	int i;
+
+	trace_xfs_attr_node_get(args);
+
+	state = xfs_da_state_alloc();
+	state->args = args;
+	state->mp = args->dp->i_mount;
+
+	/*
+	 * Search to see if name exists, and get back a pointer to it.
+	 */
+	error = xfs_da3_node_lookup_int(state, &retval);
+	if (error) {
+		retval = error;
+	} else if (retval == -EEXIST) {
+		blk = &state->path.blk[ state->path.active-1 ];
+		ASSERT(blk->bp != NULL);
+		ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+
+		/*
+		 * Get the value, local or "remote"
+		 */
+		retval = xfs_attr3_leaf_getvalue(blk->bp, args);
+		if (!retval && (args->rmtblkno > 0)
+		    && !(args->flags & ATTR_KERNOVAL)) {
+			retval = xfs_attr_rmtval_get(args);
+		}
+	}
+
+	/*
+	 * If not in a transaction, we have to release all the buffers.
+	 */
+	for (i = 0; i < state->path.active; i++) {
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
+		state->path.blk[i].bp = NULL;
+	}
+
+	xfs_da_state_free(state);
+	return retval;
+}