Merge tag 'xfs-delay-ready-attrs-v20.1' of https://github.com/allisonhenderson/xfs_work into xfs-5.14-merge4

xfs: Delay Ready Attributes

Hi all,

This set is a subset of a larger series for Dealyed Attributes. Which is a
subset of a yet larger series for parent pointers. Delayed attributes allow
attribute operations (set and remove) to be logged and committed in the same
way that other delayed operations do. This allows more complex operations (like
parent pointers) to be broken up into multiple smaller transactions. To do
this, the existing attr operations must be modified to operate as a delayed
operation.  This means that they cannot roll, commit, or finish transactions.
Instead, they return -EAGAIN to allow the calling function to handle the
transaction.  In this series, we focus on only the delayed attribute portion.
We will introduce parent pointers in a later set.

The set as a whole is a bit much to digest at once, so I usually send out the
smaller sub series to reduce reviewer burn out.  But the entire extended series
is visible through the included github links.

Updates since v19: Added Darricks fix for the remote block accounting as well as
some minor nits about the default assert in xfs_attr_set_iter.  Spent quite
a bit of time testing this cycle to weed out any more unexpected bugs.  No new
test failures were observed with the addition of this set.

xfs: Fix default ASSERT in xfs_attr_set_iter
  Replaced the assert with ASSERT(0);

xfs: Add delay ready attr remove routines
  Added Darricks fix for remote block accounting

This series can be viewed on github here:
https://github.com/allisonhenderson/xfs_work/tree/delay_ready_attrs_v20

As well as the extended delayed attribute and parent pointer series:
https://github.com/allisonhenderson/xfs_work/tree/delay_ready_attrs_v20_extended

And the test cases:
https://github.com/allisonhenderson/xfs_work/tree/pptr_xfstestsv3
In order to run the test cases, you will need have the corresponding xfsprogs

changes as well.  Which can be found here:
https://github.com/allisonhenderson/xfs_work/tree/delay_ready_attrs_xfsprogs_v20
https://github.com/allisonhenderson/xfs_work/tree/delay_ready_attrs_xfsprogs_v20_extended

To run the xfs attributes tests run:
check -g attr

To run as delayed attributes run:
export MOUNT_OPTIONS="-o delattr"
check -g attr

To run parent pointer tests:
check -g parent

I've also made the corresponding updates to the user space side as well, and ported anything
they need to seat correctly.

Questions, comment and feedback appreciated!

Thanks all!
Allison

* tag 'xfs-delay-ready-attrs-v20.1' of https://github.com/allisonhenderson/xfs_work:
  xfs: Make attr name schemes consistent
  xfs: Fix default ASSERT in xfs_attr_set_iter
  xfs: Clean up xfs_attr_node_addname_clear_incomplete
  xfs: Remove xfs_attr_rmtval_set
  xfs: Add delay ready attr set routines
  xfs: Add delay ready attr remove routines
  xfs: Hoist node transaction handling
  xfs: Hoist xfs_attr_leaf_addname
  xfs: Hoist xfs_attr_node_addname
  xfs: Add helper xfs_attr_node_addname_find_attr
  xfs: Separate xfs_attr_node_addname and xfs_attr_node_addname_clear_incomplete
  xfs: Refactor xfs_attr_set_shortform
  xfs: Add xfs_attr_node_remove_name
  xfs: Reverse apply 72b97ea40d

8 files changed, 1032 insertions, 466 deletions

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 96146f425e50..611dc67234a6 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -44,20 +44,27 @@ 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);
 STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp);
+STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args, struct xfs_buf *bp);
 
 /*
  * 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 void xfs_attr_restore_rmt_blk(struct xfs_da_args *args);
+STATIC int xfs_attr_node_addname(struct xfs_delattr_context *dac);
+STATIC int xfs_attr_node_addname_find_attr(struct xfs_delattr_context *dac);
+STATIC int xfs_attr_node_addname_clear_incomplete(
+				struct xfs_delattr_context *dac);
 STATIC int xfs_attr_node_hasname(xfs_da_args_t *args,
 				 struct xfs_da_state **state);
 STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
 STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
+STATIC int xfs_attr_set_iter(struct xfs_delattr_context *dac,
+			     struct xfs_buf **leaf_bp);
+STATIC int xfs_attr_node_removename(struct xfs_da_args *args,
+				    struct xfs_da_state *state);
 
 int
 xfs_inode_hasattr(
@@ -237,27 +244,77 @@ xfs_attr_is_shortform(
 }
 
 /*
- * Attempts to set an attr in shortform, or converts short form to leaf form if
- * there is not enough room.  If the attr is set, the transaction is committed
- * and set to NULL.
+ * Checks to see if a delayed attribute transaction should be rolled.  If so,
+ * transaction is finished or rolled as needed.
  */
 STATIC int
-xfs_attr_set_shortform(
-	struct xfs_da_args	*args,
-	struct xfs_buf		**leaf_bp)
+xfs_attr_trans_roll(
+	struct xfs_delattr_context	*dac)
 {
-	struct xfs_inode	*dp = args->dp;
-	int			error, error2 = 0;
+	struct xfs_da_args		*args = dac->da_args;
+	int				error;
+
+	if (dac->flags & XFS_DAC_DEFER_FINISH) {
+		/*
+		 * The caller wants us to finish all the deferred ops so that we
+		 * avoid pinning the log tail with a large number of deferred
+		 * ops.
+		 */
+		dac->flags &= ~XFS_DAC_DEFER_FINISH;
+		error = xfs_defer_finish(&args->trans);
+	} else
+		error = xfs_trans_roll_inode(&args->trans, args->dp);
+
+	return error;
+}
+
+/*
+ * Set the attribute specified in @args.
+ */
+int
+xfs_attr_set_args(
+	struct xfs_da_args		*args)
+{
+	struct xfs_buf			*leaf_bp = NULL;
+	int				error = 0;
+	struct xfs_delattr_context	dac = {
+		.da_args	= args,
+	};
+
+	do {
+		error = xfs_attr_set_iter(&dac, &leaf_bp);
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_attr_trans_roll(&dac);
+		if (error) {
+			if (leaf_bp)
+				xfs_trans_brelse(args->trans, leaf_bp);
+			return error;
+		}
+	} while (true);
+
+	return error;
+}
+
+STATIC int
+xfs_attr_sf_addname(
+	struct xfs_delattr_context	*dac,
+	struct xfs_buf			**leaf_bp)
+{
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_inode		*dp = args->dp;
+	int				error = 0;
 
 	/*
 	 * Try to add the attr to the attribute list in the inode.
 	 */
 	error = xfs_attr_try_sf_addname(dp, args);
-	if (error != -ENOSPC) {
-		error2 = xfs_trans_commit(args->trans);
-		args->trans = NULL;
-		return error ? error : error2;
-	}
+
+	/* Should only be 0, -EEXIST or -ENOSPC */
+	if (error != -ENOSPC)
+		return error;
+
 	/*
 	 * It won't fit in the shortform, transform to a leaf block.  GROT:
 	 * another possible req'mt for a double-split btree op.
@@ -269,85 +326,300 @@ xfs_attr_set_shortform(
 	/*
 	 * 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. Once we're done rolling the transaction we
-	 * can release the hold and add the attr to the leaf.
+	 * with the write verifier.
 	 */
 	xfs_trans_bhold(args->trans, *leaf_bp);
-	error = xfs_defer_finish(&args->trans);
-	xfs_trans_bhold_release(args->trans, *leaf_bp);
-	if (error) {
-		xfs_trans_brelse(args->trans, *leaf_bp);
-		return error;
-	}
 
-	return 0;
+	/*
+	 * We're still in XFS_DAS_UNINIT state here.  We've converted
+	 * the attr fork to leaf format and will restart with the leaf
+	 * add.
+	 */
+	dac->flags |= XFS_DAC_DEFER_FINISH;
+	return -EAGAIN;
 }
 
 /*
  * Set the attribute specified in @args.
+ * This routine is meant to function as a delayed operation, and may return
+ * -EAGAIN when the transaction needs to be rolled.  Calling functions will need
+ * to handle this, and recall the function until a successful error code is
+ * returned.
  */
 int
-xfs_attr_set_args(
-	struct xfs_da_args	*args)
+xfs_attr_set_iter(
+	struct xfs_delattr_context	*dac,
+	struct xfs_buf			**leaf_bp)
 {
-	struct xfs_inode	*dp = args->dp;
-	struct xfs_buf          *leaf_bp = NULL;
-	int			error = 0;
+	struct xfs_da_args              *args = dac->da_args;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_buf			*bp = NULL;
+	int				forkoff, error = 0;
+
+	/* State machine switch */
+	switch (dac->dela_state) {
+	case XFS_DAS_UNINIT:
+		/*
+		 * If the fork is shortform, attempt to add the attr. If there
+		 * is no space, this converts to leaf format and returns
+		 * -EAGAIN with the leaf buffer held across the roll. The caller
+		 * will deal with a transaction roll error, but otherwise
+		 * release the hold once we return with a clean transaction.
+		 */
+		if (xfs_attr_is_shortform(dp))
+			return xfs_attr_sf_addname(dac, leaf_bp);
+		if (*leaf_bp != NULL) {
+			xfs_trans_bhold_release(args->trans, *leaf_bp);
+			*leaf_bp = NULL;
+		}
 
-	/*
-	 * If the attribute list is already in leaf format, jump straight to
-	 * leaf handling.  Otherwise, try to add the attribute to the shortform
-	 * list; if there's no room then convert the list to leaf format and try
-	 * again.
-	 */
-	if (xfs_attr_is_shortform(dp)) {
+		if (xfs_attr_is_leaf(dp)) {
+			error = xfs_attr_leaf_try_add(args, *leaf_bp);
+			if (error == -ENOSPC) {
+				error = xfs_attr3_leaf_to_node(args);
+				if (error)
+					return error;
+
+				/*
+				 * Finish any deferred work items and roll the
+				 * transaction once more.  The goal here is to
+				 * call node_addname with the inode and
+				 * transaction in the same state (inode locked
+				 * and joined, transaction clean) no matter how
+				 * we got to this step.
+				 *
+				 * At this point, we are still in
+				 * XFS_DAS_UNINIT, but when we come back, we'll
+				 * be a node, so we'll fall down into the node
+				 * handling code below
+				 */
+				dac->flags |= XFS_DAC_DEFER_FINISH;
+				return -EAGAIN;
+			} else if (error) {
+				return error;
+			}
+
+			dac->dela_state = XFS_DAS_FOUND_LBLK;
+		} else {
+			error = xfs_attr_node_addname_find_attr(dac);
+			if (error)
+				return error;
+
+			error = xfs_attr_node_addname(dac);
+			if (error)
+				return error;
+
+			dac->dela_state = XFS_DAS_FOUND_NBLK;
+		}
+		return -EAGAIN;
+	case XFS_DAS_FOUND_LBLK:
+		/*
+		 * 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.
+		 */
+
+		/* Open coded xfs_attr_rmtval_set without trans handling */
+		if ((dac->flags & XFS_DAC_LEAF_ADDNAME_INIT) == 0) {
+			dac->flags |= XFS_DAC_LEAF_ADDNAME_INIT;
+			if (args->rmtblkno > 0) {
+				error = xfs_attr_rmtval_find_space(dac);
+				if (error)
+					return error;
+			}
+		}
 
 		/*
-		 * If the attr was successfully set in shortform, the
-		 * transaction is committed and set to NULL.  Otherwise, is it
-		 * converted from shortform to leaf, and the transaction is
-		 * retained.
+		 * Repeat allocating remote blocks for the attr value until
+		 * blkcnt drops to zero.
 		 */
-		error = xfs_attr_set_shortform(args, &leaf_bp);
-		if (error || !args->trans)
+		if (dac->blkcnt > 0) {
+			error = xfs_attr_rmtval_set_blk(dac);
+			if (error)
+				return error;
+			return -EAGAIN;
+		}
+
+		error = xfs_attr_rmtval_set_value(args);
+		if (error)
 			return error;
-	}
 
-	if (xfs_attr_is_leaf(dp)) {
-		error = xfs_attr_leaf_addname(args);
-		if (error != -ENOSPC)
+		/*
+		 * If this is not a rename, clear the incomplete flag and we're
+		 * done.
+		 */
+		if (!(args->op_flags & XFS_DA_OP_RENAME)) {
+			if (args->rmtblkno > 0)
+				error = xfs_attr3_leaf_clearflag(args);
 			return error;
+		}
 
 		/*
-		 * Promote the attribute list to the Btree format.
+		 * 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.
+		 *
+		 * 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_to_node(args);
+		error = xfs_attr3_leaf_flipflags(args);
 		if (error)
 			return error;
+		/*
+		 * Commit the flag value change and start the next trans in
+		 * series.
+		 */
+		dac->dela_state = XFS_DAS_FLIP_LFLAG;
+		return -EAGAIN;
+	case XFS_DAS_FLIP_LFLAG:
+		/*
+		 * Dismantle the "old" attribute/value pair by removing a
+		 * "remote" value (if it exists).
+		 */
+		xfs_attr_restore_rmt_blk(args);
+		error = xfs_attr_rmtval_invalidate(args);
+		if (error)
+			return error;
+
+		/* fallthrough */
+	case XFS_DAS_RM_LBLK:
+		/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
+		dac->dela_state = XFS_DAS_RM_LBLK;
+		if (args->rmtblkno) {
+			error = __xfs_attr_rmtval_remove(dac);
+			if (error)
+				return error;
+
+			dac->dela_state = XFS_DAS_RD_LEAF;
+			return -EAGAIN;
+		}
 
+		/* fallthrough */
+	case XFS_DAS_RD_LEAF:
 		/*
-		 * Finish any deferred work items and roll the transaction once
-		 * more.  The goal here is to call node_addname with the inode
-		 * and transaction in the same state (inode locked and joined,
-		 * transaction clean) no matter how we got to this step.
+		 * This is the last step for leaf format. Read the block with
+		 * the old attr, remove the old attr, check for shortform
+		 * conversion and return.
 		 */
-		error = xfs_defer_finish(&args->trans);
+		error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
+					   &bp);
 		if (error)
 			return error;
 
+		xfs_attr3_leaf_remove(bp, args);
+
+		forkoff = xfs_attr_shortform_allfit(bp, dp);
+		if (forkoff)
+			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+			/* bp is gone due to xfs_da_shrink_inode */
+
+		return error;
+
+	case XFS_DAS_FOUND_NBLK:
+		/*
+		 * Find space for remote blocks and fall into the allocation
+		 * state.
+		 */
+		if (args->rmtblkno > 0) {
+			error = xfs_attr_rmtval_find_space(dac);
+			if (error)
+				return error;
+		}
+
+		/* fallthrough */
+	case XFS_DAS_ALLOC_NODE:
+		/*
+		 * 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.
+		 */
+		dac->dela_state = XFS_DAS_ALLOC_NODE;
+		if (args->rmtblkno > 0) {
+			if (dac->blkcnt > 0) {
+				error = xfs_attr_rmtval_set_blk(dac);
+				if (error)
+					return error;
+				return -EAGAIN;
+			}
+
+			error = xfs_attr_rmtval_set_value(args);
+			if (error)
+				return error;
+		}
+
 		/*
-		 * Commit the current trans (including the inode) and
-		 * start a new one.
+		 * If this was not a rename, clear the incomplete flag and we're
+		 * done.
 		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (!(args->op_flags & XFS_DA_OP_RENAME)) {
+			if (args->rmtblkno > 0)
+				error = xfs_attr3_leaf_clearflag(args);
+			goto out;
+		}
+
+		/*
+		 * 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.
+		 *
+		 * 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;
+		/*
+		 * Commit the flag value change and start the next trans in
+		 * series
+		 */
+		dac->dela_state = XFS_DAS_FLIP_NFLAG;
+		return -EAGAIN;
+
+	case XFS_DAS_FLIP_NFLAG:
+		/*
+		 * Dismantle the "old" attribute/value pair by removing a
+		 * "remote" value (if it exists).
+		 */
+		xfs_attr_restore_rmt_blk(args);
+
+		error = xfs_attr_rmtval_invalidate(args);
 		if (error)
 			return error;
-	}
 
-	error = xfs_attr_node_addname(args);
+		/* fallthrough */
+	case XFS_DAS_RM_NBLK:
+		/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
+		dac->dela_state = XFS_DAS_RM_NBLK;
+		if (args->rmtblkno) {
+			error = __xfs_attr_rmtval_remove(dac);
+			if (error)
+				return error;
+
+			dac->dela_state = XFS_DAS_CLR_FLAG;
+			return -EAGAIN;
+		}
+
+		/* fallthrough */
+	case XFS_DAS_CLR_FLAG:
+		/*
+		 * The last state for node format. Look up the old attr and
+		 * remove it.
+		 */
+		error = xfs_attr_node_addname_clear_incomplete(dac);
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+out:
 	return error;
 }
 
+
 /*
  * Return EEXIST if attr is found, or ENOATTR if not
  */
@@ -382,16 +654,25 @@ xfs_has_attr(
  */
 int
 xfs_attr_remove_args(
-	struct xfs_da_args      *args)
+	struct xfs_da_args	*args)
 {
-	if (!xfs_inode_hasattr(args->dp))
-		return -ENOATTR;
+	int				error;
+	struct xfs_delattr_context	dac = {
+		.da_args	= args,
+	};
 
-	if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
-		return xfs_attr_shortform_remove(args);
-	if (xfs_attr_is_leaf(args->dp))
-		return xfs_attr_leaf_removename(args);
-	return xfs_attr_node_removename(args);
+	do {
+		error = xfs_attr_remove_iter(&dac);
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_attr_trans_roll(&dac);
+		if (error)
+			return error;
+
+	} while (true);
+
+	return error;
 }
 
 /*
@@ -559,7 +840,7 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 	if (retval == -EEXIST) {
 		if (args->attr_flags & XATTR_CREATE)
 			return retval;
-		retval = xfs_attr_shortform_remove(args);
+		retval = xfs_attr_sf_removename(args);
 		if (retval)
 			return retval;
 		/*
@@ -670,115 +951,6 @@ out_brelse:
 	return retval;
 }
 
-
-/*
- * 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)
-{
-	int			error, forkoff;
-	struct xfs_buf		*bp = NULL;
-	struct xfs_inode	*dp = args->dp;
-
-	trace_xfs_attr_leaf_addname(args);
-
-	error = xfs_attr_leaf_try_add(args, bp);
-	if (error)
-		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 (!(args->op_flags & XFS_DA_OP_RENAME)) {
-		/*
-		 * Added a "remote" value, just clear the incomplete flag.
-		 */
-		if (args->rmtblkno > 0)
-			error = xfs_attr3_leaf_clearflag(args);
-
-		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.
-	 *
-	 * 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;
-	/*
-	 * Commit the flag value change and start the next trans in series.
-	 */
-	error = xfs_trans_roll_inode(&args->trans, args->dp);
-	if (error)
-		return error;
-
-	/*
-	 * Dismantle the "old" attribute/value pair by removing a "remote" value
-	 * (if it exists).
-	 */
-	xfs_attr_restore_rmt_blk(args);
-
-	if (args->rmtblkno) {
-		error = xfs_attr_rmtval_invalidate(args);
-		if (error)
-			return error;
-
-		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,
-				   &bp);
-	if (error)
-		return error;
-
-	xfs_attr3_leaf_remove(bp, args);
-
-	/*
-	 * If the result is small enough, shrink it all into the inode.
-	 */
-	forkoff = xfs_attr_shortform_allfit(bp, dp);
-	if (forkoff)
-		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
-		/* bp is gone due to xfs_da_shrink_inode */
-
-	return error;
-}
-
 /*
  * Return EEXIST if attr is found, or ENOATTR if not
  */
@@ -909,48 +1081,26 @@ xfs_attr_node_hasname(
  * 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)
+xfs_attr_node_addname_find_attr(
+	struct xfs_delattr_context	*dac)
 {
-	struct xfs_da_state	*state;
-	struct xfs_da_state_blk	*blk;
-	struct xfs_inode	*dp;
-	int			retval, error;
-
-	trace_xfs_attr_node_addname(args);
+	struct xfs_da_args		*args = dac->da_args;
+	int				retval;
 
 	/*
-	 * Fill in bucket of arguments/results/context to carry around.
-	 */
-	dp = args->dp;
-restart:
-	/*
 	 * Search to see if name already exists, and get back a pointer
 	 * to where it should go.
 	 */
-	error = 0;
-	retval = xfs_attr_node_hasname(args, &state);
+	retval = xfs_attr_node_hasname(args, &dac->da_state);
 	if (retval != -ENOATTR && retval != -EEXIST)
-		goto out;
+		return retval;
 
-	blk = &state->path.blk[ state->path.active-1 ];
-	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
 	if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
-		goto out;
+		goto error;
 	if (retval == -EEXIST) {
 		if (args->attr_flags & XATTR_CREATE)
-			goto out;
+			goto error;
 
 		trace_xfs_attr_node_replace(args);
 
@@ -968,8 +1118,44 @@ restart:
 		args->rmtvaluelen = 0;
 	}
 
-	retval = xfs_attr3_leaf_add(blk->bp, state->args);
-	if (retval == -ENOSPC) {
+	return 0;
+error:
+	if (dac->da_state)
+		xfs_da_state_free(dac->da_state);
+	return retval;
+}
+
+/*
+ * 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.
+ *
+ * This routine is meant to function as a delayed operation, and may return
+ * -EAGAIN when the transaction needs to be rolled.  Calling functions will need
+ * to handle this, and recall the function until a successful error code is
+ *returned.
+ */
+STATIC int
+xfs_attr_node_addname(
+	struct xfs_delattr_context	*dac)
+{
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_state		*state = dac->da_state;
+	struct xfs_da_state_blk		*blk;
+	int				error;
+
+	trace_xfs_attr_node_addname(args);
+
+	blk = &state->path.blk[state->path.active-1];
+	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+
+	error = xfs_attr3_leaf_add(blk->bp, state->args);
+	if (error == -ENOSPC) {
 		if (state->path.active == 1) {
 			/*
 			 * Its really a single leaf node, but it had
@@ -981,19 +1167,16 @@ restart:
 			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.
+			 * Now that we have converted the leaf to a node, we can
+			 * roll the transaction, and try xfs_attr3_leaf_add
+			 * again on re-entry.  No need to set dela_state to do
+			 * this. dela_state is still unset by this function at
+			 * this point.
 			 */
-			error = xfs_trans_roll_inode(&args->trans, dp);
-			if (error)
-				goto out;
-
-			goto restart;
+			dac->flags |= XFS_DAC_DEFER_FINISH;
+			return -EAGAIN;
 		}
 
 		/*
@@ -1005,9 +1188,7 @@ restart:
 		error = xfs_da3_split(state);
 		if (error)
 			goto out;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			goto out;
+		dac->flags |= XFS_DAC_DEFER_FINISH;
 	} else {
 		/*
 		 * Addition succeeded, update Btree hashvals.
@@ -1015,77 +1196,21 @@ restart:
 		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 (!(args->op_flags & XFS_DA_OP_RENAME)) {
-		/*
-		 * Added a "remote" value, just clear the incomplete flag.
-		 */
-		if (args->rmtblkno > 0)
-			error = xfs_attr3_leaf_clearflag(args);
-		retval = error;
-		goto out;
-	}
-
-	/*
-	 * 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.
-	 *
-	 * 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;
-	/*
-	 * Commit the flag value change and start the next trans in series
-	 */
-	error = xfs_trans_roll_inode(&args->trans, args->dp);
-	if (error)
-		goto out;
-
-	/*
-	 * Dismantle the "old" attribute/value pair by removing a "remote" value
-	 * (if it exists).
-	 */
-	xfs_attr_restore_rmt_blk(args);
+out:
+	if (state)
+		xfs_da_state_free(state);
+	return error;
+}
 
-	if (args->rmtblkno) {
-		error = xfs_attr_rmtval_invalidate(args);
-		if (error)
-			return error;
 
-		error = xfs_attr_rmtval_remove(args);
-		if (error)
-			return error;
-	}
+STATIC int
+xfs_attr_node_addname_clear_incomplete(
+	struct xfs_delattr_context	*dac)
+{
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_state		*state = NULL;
+	int				retval = 0;
+	int				error = 0;
 
 	/*
 	 * Re-find the "old" attribute entry after any split ops. The INCOMPLETE
@@ -1098,13 +1223,7 @@ restart:
 	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);
+	error = xfs_attr_node_removename(args, state);
 
 	/*
 	 * Check to see if the tree needs to be collapsed.
@@ -1190,14 +1309,16 @@ xfs_attr_leaf_mark_incomplete(
  */
 STATIC
 int xfs_attr_node_removename_setup(
-	struct xfs_da_args	*args,
-	struct xfs_da_state	**state)
+	struct xfs_delattr_context	*dac)
 {
-	int			error;
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_state		**state = &dac->da_state;
+	int				error;
 
 	error = xfs_attr_node_hasname(args, state);
 	if (error != -EEXIST)
 		return error;
+	error = 0;
 
 	ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL);
 	ASSERT((*state)->path.blk[(*state)->path.active - 1].magic ==
@@ -1206,97 +1327,164 @@ int xfs_attr_node_removename_setup(
 	if (args->rmtblkno > 0) {
 		error = xfs_attr_leaf_mark_incomplete(args, *state);
 		if (error)
-			return error;
+			goto out;
 
-		return xfs_attr_rmtval_invalidate(args);
+		error = xfs_attr_rmtval_invalidate(args);
 	}
+out:
+	if (error)
+		xfs_da_state_free(*state);
 
-	return 0;
+	return error;
 }
 
 STATIC int
-xfs_attr_node_remove_rmt(
+xfs_attr_node_removename(
 	struct xfs_da_args	*args,
 	struct xfs_da_state	*state)
 {
-	int			error = 0;
-
-	error = xfs_attr_rmtval_remove(args);
-	if (error)
-		return error;
+	struct xfs_da_state_blk	*blk;
+	int			retval;
 
 	/*
-	 * Refill the state structure with buffers, the prior calls released our
-	 * buffers.
+	 * Remove the name and update the hashvals in the tree.
 	 */
-	return xfs_attr_refillstate(state);
+	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);
+
+	return retval;
 }
 
 /*
- * Remove a name from a B-tree attribute list.
+ * Remove the attribute specified in @args.
  *
  * 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).
+ *
+ * This routine is meant to function as either an in-line or delayed operation,
+ * and may return -EAGAIN when the transaction needs to be rolled.  Calling
+ * functions will need to handle this, and call the function until a
+ * successful error code is returned.
  */
-STATIC int
-xfs_attr_node_removename(
-	struct xfs_da_args	*args)
+int
+xfs_attr_remove_iter(
+	struct xfs_delattr_context	*dac)
 {
-	struct xfs_da_state	*state;
-	struct xfs_da_state_blk	*blk;
-	int			retval, error;
-	struct xfs_inode	*dp = args->dp;
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_state		*state = dac->da_state;
+	int				retval, error;
+	struct xfs_inode		*dp = args->dp;
 
 	trace_xfs_attr_node_removename(args);
 
-	error = xfs_attr_node_removename_setup(args, &state);
-	if (error)
-		goto out;
+	switch (dac->dela_state) {
+	case XFS_DAS_UNINIT:
+		if (!xfs_inode_hasattr(dp))
+			return -ENOATTR;
 
-	/*
-	 * 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.
-	 */
-	if (args->rmtblkno > 0) {
-		error = xfs_attr_node_remove_rmt(args, state);
-		if (error)
-			goto out;
-	}
+		/*
+		 * Shortform or leaf formats don't require transaction rolls and
+		 * thus state transitions. Call the right helper and return.
+		 */
+		if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
+			return xfs_attr_sf_removename(args);
 
-	/*
-	 * 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);
+		if (xfs_attr_is_leaf(dp))
+			return xfs_attr_leaf_removename(args);
 
-	/*
-	 * 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.
+		 * Node format may require transaction rolls. Set up the
+		 * state context and fall into the state machine.
 		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
-			goto out;
-	}
+		if (!dac->da_state) {
+			error = xfs_attr_node_removename_setup(dac);
+			if (error)
+				return error;
+			state = dac->da_state;
+		}
 
-	/*
-	 * If the result is small enough, push it all into the inode.
-	 */
-	if (xfs_attr_is_leaf(dp))
-		error = xfs_attr_node_shrink(args, state);
+		/* fallthrough */
+	case XFS_DAS_RMTBLK:
+		dac->dela_state = XFS_DAS_RMTBLK;
 
+		/*
+		 * 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.
+		 */
+		if (args->rmtblkno > 0) {
+			/*
+			 * May return -EAGAIN. Roll and repeat until all remote
+			 * blocks are removed.
+			 */
+			error = __xfs_attr_rmtval_remove(dac);
+			if (error == -EAGAIN)
+				return error;
+			else if (error)
+				goto out;
+
+			/*
+			 * Refill the state structure with buffers (the prior
+			 * calls released our buffers) and close out this
+			 * transaction before proceeding.
+			 */
+			ASSERT(args->rmtblkno == 0);
+			error = xfs_attr_refillstate(state);
+			if (error)
+				goto out;
+			dac->dela_state = XFS_DAS_RM_NAME;
+			dac->flags |= XFS_DAC_DEFER_FINISH;
+			return -EAGAIN;
+		}
+
+		/* fallthrough */
+	case XFS_DAS_RM_NAME:
+		/*
+		 * If we came here fresh from a transaction roll, reattach all
+		 * the buffers to the current transaction.
+		 */
+		if (dac->dela_state == XFS_DAS_RM_NAME) {
+			error = xfs_attr_refillstate(state);
+			if (error)
+				goto out;
+		}
+
+		retval = xfs_attr_node_removename(args, state);
+
+		/*
+		 * Check to see if the tree needs to be collapsed. If so, roll
+		 * the transacton and fall into the shrink state.
+		 */
+		if (retval && (state->path.active > 1)) {
+			error = xfs_da3_join(state);
+			if (error)
+				goto out;
+
+			dac->flags |= XFS_DAC_DEFER_FINISH;
+			dac->dela_state = XFS_DAS_RM_SHRINK;
+			return -EAGAIN;
+		}
+
+		/* fallthrough */
+	case XFS_DAS_RM_SHRINK:
+		/*
+		 * If the result is small enough, push it all into the inode.
+		 * This is our final state so it's safe to return a dirty
+		 * transaction.
+		 */
+		if (xfs_attr_is_leaf(dp))
+			error = xfs_attr_node_shrink(args, state);
+		ASSERT(error != -EAGAIN);
+		break;
+	default:
+		ASSERT(0);
+		error = -EINVAL;
+		goto out;
+	}
 out:
 	if (state)
 		xfs_da_state_free(state);
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 2b1f61987a9d..8de5d1d2733e 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -74,6 +74,406 @@ struct xfs_attr_list_context {
 };
 
 
+/*
+ * ========================================================================
+ * Structure used to pass context around among the delayed routines.
+ * ========================================================================
+ */
+
+/*
+ * Below is a state machine diagram for attr remove operations. The  XFS_DAS_*
+ * states indicate places where the function would return -EAGAIN, and then
+ * immediately resume from after being called by the calling function. States
+ * marked as a "subroutine state" indicate that they belong to a subroutine, and
+ * so the calling function needs to pass them back to that subroutine to allow
+ * it to finish where it left off. But they otherwise do not have a role in the
+ * calling function other than just passing through.
+ *
+ * xfs_attr_remove_iter()
+ *              │
+ *              v
+ *        have attr to remove? ──n──> done
+ *              │
+ *              y
+ *              │
+ *              v
+ *        are we short form? ──y──> xfs_attr_shortform_remove ──> done
+ *              │
+ *              n
+ *              │
+ *              V
+ *        are we leaf form? ──y──> xfs_attr_leaf_removename ──> done
+ *              │
+ *              n
+ *              │
+ *              V
+ *   ┌── need to setup state?
+ *   │          │
+ *   n          y
+ *   │          │
+ *   │          v
+ *   │ find attr and get state
+ *   │ attr has remote blks? ──n─┐
+ *   │          │                v
+ *   │          │         find and invalidate
+ *   │          y         the remote blocks.
+ *   │          │         mark attr incomplete
+ *   │          ├────────────────┘
+ *   └──────────┤
+ *              │
+ *              v
+ *   Have remote blks to remove? ───y─────┐
+ *              │        ^          remove the blks
+ *              │        │                │
+ *              │        │                v
+ *              │  XFS_DAS_RMTBLK <─n── done?
+ *              │  re-enter with          │
+ *              │  one less blk to        y
+ *              │      remove             │
+ *              │                         V
+ *              │                  refill the state
+ *              n                         │
+ *              │                         v
+ *              │                   XFS_DAS_RM_NAME
+ *              │                         │
+ *              ├─────────────────────────┘
+ *              │
+ *              v
+ *       remove leaf and
+ *       update hash with
+ *   xfs_attr_node_remove_cleanup
+ *              │
+ *              v
+ *           need to
+ *        shrink tree? ─n─┐
+ *              │         │
+ *              y         │
+ *              │         │
+ *              v         │
+ *          join leaf     │
+ *              │         │
+ *              v         │
+ *      XFS_DAS_RM_SHRINK │
+ *              │         │
+ *              v         │
+ *       do the shrink    │
+ *              │         │
+ *              v         │
+ *          free state <──┘
+ *              │
+ *              v
+ *            done
+ *
+ *
+ * Below is a state machine diagram for attr set operations.
+ *
+ * It seems the challenge with understanding this system comes from trying to
+ * absorb the state machine all at once, when really one should only be looking
+ * at it with in the context of a single function. Once a state sensitive
+ * function is called, the idea is that it "takes ownership" of the
+ * state machine. It isn't concerned with the states that may have belonged to
+ * it's calling parent. Only the states relevant to itself or any other
+ * subroutines there in. Once a calling function hands off the state machine to
+ * a subroutine, it needs to respect the simple rule that it doesn't "own" the
+ * state machine anymore, and it's the responsibility of that calling function
+ * to propagate the -EAGAIN back up the call stack. Upon reentry, it is
+ * committed to re-calling that subroutine until it returns something other than
+ * -EAGAIN. Once that subroutine signals completion (by returning anything other
+ * than -EAGAIN), the calling function can resume using the state machine.
+ *
+ *  xfs_attr_set_iter()
+ *              │
+ *              v
+ *   ┌─y─ has an attr fork?
+ *   │          |
+ *   │          n
+ *   │          |
+ *   │          V
+ *   │       add a fork
+ *   │          │
+ *   └──────────┤
+ *              │
+ *              V
+ *   ┌─── is shortform?
+ *   │          │
+ *   │          y
+ *   │          │
+ *   │          V
+ *   │   xfs_attr_set_fmt
+ *   │          |
+ *   │          V
+ *   │ xfs_attr_try_sf_addname
+ *   │          │
+ *   │          V
+ *   │      had enough ──y──> done
+ *   │        space?
+ *   n          │
+ *   │          n
+ *   │          │
+ *   │          V
+ *   │   transform to leaf
+ *   │          │
+ *   │          V
+ *   │   hold the leaf buffer
+ *   │          │
+ *   │          V
+ *   │     return -EAGAIN
+ *   │      Re-enter in
+ *   │       leaf form
+ *   │
+ *   └─> release leaf buffer
+ *          if needed
+ *              │
+ *              V
+ *   ┌───n── fork has
+ *   │      only 1 blk?
+ *   │          │
+ *   │          y
+ *   │          │
+ *   │          v
+ *   │ xfs_attr_leaf_try_add()
+ *   │          │
+ *   │          v
+ *   │      had enough ──────────────y─────────────┐
+ *   │        space?                               │
+ *   │          │                                  │
+ *   │          n                                  │
+ *   │          │                                  │
+ *   │          v                                  │
+ *   │    return -EAGAIN                           │
+ *   │      re-enter in                            │
+ *   │        node form                            │
+ *   │          │                                  │
+ *   └──────────┤                                  │
+ *              │                                  │
+ *              V                                  │
+ * xfs_attr_node_addname_find_attr                 │
+ *        determines if this                       │
+ *       is create or rename                       │
+ *     find space to store attr                    │
+ *              │                                  │
+ *              v                                  │
+ *     xfs_attr_node_addname                       │
+ *              │                                  │
+ *              v                                  │
+ *   fits in a node leaf? ────n─────┐              │
+ *              │     ^             v              │
+ *              │     │       single leaf node?    │
+ *              │     │         │            │     │
+ *              y     │         y            n     │
+ *              │     │         │            │     │
+ *              v     │         v            v     │
+ *            update  │    grow the leaf  split if │
+ *           hashvals └── return -EAGAIN   needed  │
+ *              │         retry leaf add     │     │
+ *              │           on reentry       │     │
+ *              ├────────────────────────────┘     │
+ *              │                                  │
+ *              v                                  │
+ *         need to alloc                           │
+ *   ┌─y── or flip flag?                           │
+ *   │          │                                  │
+ *   │          n                                  │
+ *   │          │                                  │
+ *   │          v                                  │
+ *   │         done                                │
+ *   │                                             │
+ *   │                                             │
+ *   │         XFS_DAS_FOUND_LBLK <────────────────┘
+ *   │                  │
+ *   │                  V
+ *   │        xfs_attr_leaf_addname()
+ *   │                  │
+ *   │                  v
+ *   │      ┌──first time through?
+ *   │      │          │
+ *   │      │          y
+ *   │      │          │
+ *   │      n          v
+ *   │      │    if we have rmt blks
+ *   │      │    find space for them
+ *   │      │          │
+ *   │      └──────────┤
+ *   │                 │
+ *   │                 v
+ *   │            still have
+ *   │      ┌─n─ blks to alloc? <──┐
+ *   │      │          │           │
+ *   │      │          y           │
+ *   │      │          │           │
+ *   │      │          v           │
+ *   │      │     alloc one blk    │
+ *   │      │     return -EAGAIN ──┘
+ *   │      │    re-enter with one
+ *   │      │    less blk to alloc
+ *   │      │
+ *   │      │
+ *   │      └───> set the rmt
+ *   │               value
+ *   │                 │
+ *   │                 v
+ *   │               was this
+ *   │              a rename? ──n─┐
+ *   │                 │          │
+ *   │                 y          │
+ *   │                 │          │
+ *   │                 v          │
+ *   │           flip incomplete  │
+ *   │               flag         │
+ *   │                 │          │
+ *   │                 v          │
+ *   │         XFS_DAS_FLIP_LFLAG │
+ *   │                 │          │
+ *   │                 v          │
+ *   │          need to remove    │
+ *   │              old bks? ──n──┤
+ *   │                 │          │
+ *   │                 y          │
+ *   │                 │          │
+ *   │                 V          │
+ *   │               remove       │
+ *   │        ┌───> old blks      │
+ *   │        │        │          │
+ *   │ XFS_DAS_RM_LBLK │          │
+ *   │        ^        │          │
+ *   │        │        v          │
+ *   │        └──y── more to      │
+ *   │              remove?       │
+ *   │                 │          │
+ *   │                 n          │
+ *   │                 │          │
+ *   │                 v          │
+ *   │          XFS_DAS_RD_LEAF   │
+ *   │                 │          │
+ *   │                 v          │
+ *   │            remove leaf     │
+ *   │                 │          │
+ *   │                 v          │
+ *   │            shrink to sf    │
+ *   │             if needed      │
+ *   │                 │          │
+ *   │                 v          │
+ *   │                done <──────┘
+ *   │
+ *   └──────> XFS_DAS_FOUND_NBLK
+ *                     │
+ *                     v
+ *       ┌─────n──  need to
+ *       │        alloc blks?
+ *       │             │
+ *       │             y
+ *       │             │
+ *       │             v
+ *       │        find space
+ *       │             │
+ *       │             v
+ *       │  ┌─>XFS_DAS_ALLOC_NODE
+ *       │  │          │
+ *       │  │          v
+ *       │  │      alloc blk
+ *       │  │          │
+ *       │  │          v
+ *       │  └──y── need to alloc
+ *       │         more blocks?
+ *       │             │
+ *       │             n
+ *       │             │
+ *       │             v
+ *       │      set the rmt value
+ *       │             │
+ *       │             v
+ *       │          was this
+ *       └────────> a rename? ──n─┐
+ *                     │          │
+ *                     y          │
+ *                     │          │
+ *                     v          │
+ *               flip incomplete  │
+ *                   flag         │
+ *                     │          │
+ *                     v          │
+ *             XFS_DAS_FLIP_NFLAG │
+ *                     │          │
+ *                     v          │
+ *                 need to        │
+ *               remove blks? ─n──┤
+ *                     │          │
+ *                     y          │
+ *                     │          │
+ *                     v          │
+ *                   remove       │
+ *        ┌────────> old blks     │
+ *        │            │          │
+ *  XFS_DAS_RM_NBLK    │          │
+ *        ^            │          │
+ *        │            v          │
+ *        └──────y── more to      │
+ *                   remove       │
+ *                     │          │
+ *                     n          │
+ *                     │          │
+ *                     v          │
+ *              XFS_DAS_CLR_FLAG  │
+ *                     │          │
+ *                     v          │
+ *                clear flags     │
+ *                     │          │
+ *                     ├──────────┘
+ *                     │
+ *                     v
+ *                   done
+ */
+
+/*
+ * Enum values for xfs_delattr_context.da_state
+ *
+ * These values are used by delayed attribute operations to keep track  of where
+ * they were before they returned -EAGAIN.  A return code of -EAGAIN signals the
+ * calling function to roll the transaction, and then call the subroutine to
+ * finish the operation.  The enum is then used by the subroutine to jump back
+ * to where it was and resume executing where it left off.
+ */
+enum xfs_delattr_state {
+	XFS_DAS_UNINIT		= 0,  /* No state has been set yet */
+	XFS_DAS_RMTBLK,		      /* Removing remote blks */
+	XFS_DAS_RM_NAME,	      /* Remove attr name */
+	XFS_DAS_RM_SHRINK,	      /* We are shrinking the tree */
+	XFS_DAS_FOUND_LBLK,	      /* We found leaf blk for attr */
+	XFS_DAS_FOUND_NBLK,	      /* We found node blk for attr */
+	XFS_DAS_FLIP_LFLAG,	      /* Flipped leaf INCOMPLETE attr flag */
+	XFS_DAS_RM_LBLK,	      /* A rename is removing leaf blocks */
+	XFS_DAS_RD_LEAF,	      /* Read in the new leaf */
+	XFS_DAS_ALLOC_NODE,	      /* We are allocating node blocks */
+	XFS_DAS_FLIP_NFLAG,	      /* Flipped node INCOMPLETE attr flag */
+	XFS_DAS_RM_NBLK,	      /* A rename is removing node blocks */
+	XFS_DAS_CLR_FLAG,	      /* Clear incomplete flag */
+};
+
+/*
+ * Defines for xfs_delattr_context.flags
+ */
+#define XFS_DAC_DEFER_FINISH		0x01 /* finish the transaction */
+#define XFS_DAC_LEAF_ADDNAME_INIT	0x02 /* xfs_attr_leaf_addname init*/
+
+/*
+ * Context used for keeping track of delayed attribute operations
+ */
+struct xfs_delattr_context {
+	struct xfs_da_args      *da_args;
+
+	/* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */
+	struct xfs_bmbt_irec	map;
+	xfs_dablk_t		lblkno;
+	int			blkcnt;
+
+	/* Used in xfs_attr_node_removename to roll through removing blocks */
+	struct xfs_da_state     *da_state;
+
+	/* Used to keep track of current state of delayed operation */
+	unsigned int            flags;
+	enum xfs_delattr_state  dela_state;
+};
+
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/
@@ -92,6 +492,9 @@ int xfs_attr_set(struct xfs_da_args *args);
 int xfs_attr_set_args(struct xfs_da_args *args);
 int xfs_has_attr(struct xfs_da_args *args);
 int xfs_attr_remove_args(struct xfs_da_args *args);
+int xfs_attr_remove_iter(struct xfs_delattr_context *dac);
 bool xfs_attr_namecheck(const void *name, size_t length);
+void xfs_delattr_context_init(struct xfs_delattr_context *dac,
+			      struct xfs_da_args *args);
 
 #endif	/* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index aa371d005131..b910bd209949 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -19,8 +19,8 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_attr_sf.h"
-#include "xfs_attr_remote.h"
 #include "xfs_attr.h"
+#include "xfs_attr_remote.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
@@ -774,7 +774,7 @@ xfs_attr_fork_remove(
  * Remove an attribute from the shortform attribute list structure.
  */
 int
-xfs_attr_shortform_remove(
+xfs_attr_sf_removename(
 	struct xfs_da_args		*args)
 {
 	struct xfs_attr_shortform	*sf;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 9b1c59f40a26..efa757f1e912 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -51,7 +51,7 @@ int	xfs_attr_shortform_lookup(struct xfs_da_args *args);
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args,
 			struct xfs_buf **leaf_bp);
-int	xfs_attr_shortform_remove(struct xfs_da_args *args);
+int	xfs_attr_sf_removename(struct xfs_da_args *args);
 int	xfs_attr_sf_findname(struct xfs_da_args *args,
 			     struct xfs_attr_sf_entry **sfep,
 			     unsigned int *basep);
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 48d8e9caf86f..0c8bee3abc3b 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -439,9 +439,9 @@ xfs_attr_rmtval_get(
 
 /*
  * Find a "hole" in the attribute address space large enough for us to drop the
- * new attribute's value into
+ * new attributes value into
  */
-STATIC int
+int
 xfs_attr_rmt_find_hole(
 	struct xfs_da_args	*args)
 {
@@ -468,7 +468,7 @@ xfs_attr_rmt_find_hole(
 	return 0;
 }
 
-STATIC int
+int
 xfs_attr_rmtval_set_value(
 	struct xfs_da_args	*args)
 {
@@ -562,69 +562,66 @@ xfs_attr_rmtval_stale(
 }
 
 /*
- * Write the value associated with an attribute into the out-of-line buffer
- * that we have defined for it.
+ * Find a hole for the attr and store it in the delayed attr context.  This
+ * initializes the context to roll through allocating an attr extent for a
+ * delayed attr operation
  */
 int
-xfs_attr_rmtval_set(
-	struct xfs_da_args	*args)
+xfs_attr_rmtval_find_space(
+	struct xfs_delattr_context	*dac)
 {
-	struct xfs_inode	*dp = args->dp;
-	struct xfs_bmbt_irec	map;
-	xfs_dablk_t		lblkno;
-	int			blkcnt;
-	int			nmap;
-	int			error;
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_bmbt_irec		*map = &dac->map;
+	int				error;
 
-	trace_xfs_attr_rmtval_set(args);
+	dac->lblkno = 0;
+	dac->blkcnt = 0;
+	args->rmtblkcnt = 0;
+	args->rmtblkno = 0;
+	memset(map, 0, sizeof(struct xfs_bmbt_irec));
 
 	error = xfs_attr_rmt_find_hole(args);
 	if (error)
 		return error;
 
-	blkcnt = args->rmtblkcnt;
-	lblkno = (xfs_dablk_t)args->rmtblkno;
-	/*
-	 * Roll through the "value", allocating blocks on disk as required.
-	 */
-	while (blkcnt > 0) {
-		/*
-		 * Allocate a single extent, up to the size of the value.
-		 *
-		 * Note that we have to consider this a data allocation as we
-		 * write the remote attribute without logging the contents.
-		 * Hence we must ensure that we aren't using blocks that are on
-		 * the busy list so that we don't overwrite blocks which have
-		 * recently been freed but their transactions are not yet
-		 * committed to disk. If we overwrite the contents of a busy
-		 * extent and then crash then the block may not contain the
-		 * correct metadata after log recovery occurs.
-		 */
-		nmap = 1;
-		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
-				  &nmap);
-		if (error)
-			return error;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
+	dac->blkcnt = args->rmtblkcnt;
+	dac->lblkno = args->rmtblkno;
 
-		ASSERT(nmap == 1);
-		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
-		       (map.br_startblock != HOLESTARTBLOCK));
-		lblkno += map.br_blockcount;
-		blkcnt -= map.br_blockcount;
+	return 0;
+}
 
-		/*
-		 * Start the next trans in the chain.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
-			return error;
-	}
+/*
+ * Write one block of the value associated with an attribute into the
+ * out-of-line buffer that we have defined for it. This is similar to a subset
+ * of xfs_attr_rmtval_set, but records the current block to the delayed attr
+ * context, and leaves transaction handling to the caller.
+ */
+int
+xfs_attr_rmtval_set_blk(
+	struct xfs_delattr_context	*dac)
+{
+	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_bmbt_irec		*map = &dac->map;
+	int nmap;
+	int error;
+
+	nmap = 1;
+	error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)dac->lblkno,
+			dac->blkcnt, XFS_BMAPI_ATTRFORK, args->total,
+			map, &nmap);
+	if (error)
+		return error;
+
+	ASSERT(nmap == 1);
+	ASSERT((map->br_startblock != DELAYSTARTBLOCK) &&
+	       (map->br_startblock != HOLESTARTBLOCK));
 
-	return xfs_attr_rmtval_set_value(args);
+	/* roll attribute extent map forwards */
+	dac->lblkno += map->br_blockcount;
+	dac->blkcnt -= map->br_blockcount;
+
+	return 0;
 }
 
 /*
@@ -669,47 +666,17 @@ xfs_attr_rmtval_invalidate(
 }
 
 /*
- * Remove the value associated with an attribute by deleting the
- * out-of-line buffer that it is stored on.
- */
-int
-xfs_attr_rmtval_remove(
-	struct xfs_da_args      *args)
-{
-	int			error;
-	int			retval;
-
-	trace_xfs_attr_rmtval_remove(args);
-
-	/*
-	 * Keep de-allocating extents until the remote-value region is gone.
-	 */
-	do {
-		retval = __xfs_attr_rmtval_remove(args);
-		if (retval && retval != -EAGAIN)
-			return retval;
-
-		/*
-		 * Close out trans and start the next one in the chain.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, args->dp);
-		if (error)
-			return error;
-	} while (retval == -EAGAIN);
-
-	return 0;
-}
-
-/*
  * Remove the value associated with an attribute by deleting the out-of-line
- * buffer that it is stored on. Returns EAGAIN for the caller to refresh the
- * transaction and re-call the function
+ * buffer that it is stored on. Returns -EAGAIN for the caller to refresh the
+ * transaction and re-call the function.  Callers should keep calling this
+ * routine until it returns something other than -EAGAIN.
  */
 int
 __xfs_attr_rmtval_remove(
-	struct xfs_da_args	*args)
+	struct xfs_delattr_context	*dac)
 {
-	int			error, done;
+	struct xfs_da_args		*args = dac->da_args;
+	int				error, done;
 
 	/*
 	 * Unmap value blocks for this attr.
@@ -719,12 +686,20 @@ __xfs_attr_rmtval_remove(
 	if (error)
 		return error;
 
-	error = xfs_defer_finish(&args->trans);
-	if (error)
-		return error;
-
-	if (!done)
+	/*
+	 * We don't need an explicit state here to pick up where we left off. We
+	 * can figure it out using the !done return code. The actual value of
+	 * attr->xattri_dela_state may be some value reminiscent of the calling
+	 * function, but it's value is irrelevant with in the context of this
+	 * function. Once we are done here, the next state is set as needed by
+	 * the parent
+	 */
+	if (!done) {
+		dac->flags |= XFS_DAC_DEFER_FINISH;
 		return -EAGAIN;
+	}
 
-	return error;
+	args->rmtblkno = 0;
+	args->rmtblkcnt = 0;
+	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h
index 9eee615da156..61b85b918db8 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.h
+++ b/fs/xfs/libxfs/xfs_attr_remote.h
@@ -9,10 +9,12 @@
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
-int xfs_attr_rmtval_set(struct xfs_da_args *args);
-int xfs_attr_rmtval_remove(struct xfs_da_args *args);
 int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
 		xfs_buf_flags_t incore_flags);
 int xfs_attr_rmtval_invalidate(struct xfs_da_args *args);
-int __xfs_attr_rmtval_remove(struct xfs_da_args *args);
+int __xfs_attr_rmtval_remove(struct xfs_delattr_context *dac);
+int xfs_attr_rmt_find_hole(struct xfs_da_args *args);
+int xfs_attr_rmtval_set_value(struct xfs_da_args *args);
+int xfs_attr_rmtval_set_blk(struct xfs_delattr_context *dac);
+int xfs_attr_rmtval_find_space(struct xfs_delattr_context *dac);
 #endif /* __XFS_ATTR_REMOTE_H__ */
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index bfad669e6b2f..aaa7e66c42d7 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -15,10 +15,10 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_inode.h"
+#include "xfs_attr.h"
 #include "xfs_attr_remote.h"
 #include "xfs_trans.h"
 #include "xfs_bmap.h"
-#include "xfs_attr.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_quota.h"
 #include "xfs_dir2.h"
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a10612155377..71dca776c110 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1912,7 +1912,6 @@ DEFINE_ATTR_EVENT(xfs_attr_leaf_add);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_add_old);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_add_new);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_add_work);
-DEFINE_ATTR_EVENT(xfs_attr_leaf_addname);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_create);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_compact);
 DEFINE_ATTR_EVENT(xfs_attr_leaf_get);
@@ -1942,7 +1941,6 @@ DEFINE_ATTR_EVENT(xfs_attr_refillstate);
 
 DEFINE_ATTR_EVENT(xfs_attr_rmtval_get);
 DEFINE_ATTR_EVENT(xfs_attr_rmtval_set);
-DEFINE_ATTR_EVENT(xfs_attr_rmtval_remove);
 
 #define DEFINE_DA_EVENT(name) \
 DEFINE_EVENT(xfs_da_class, name, \