xfs: Add delay ready attr set routines

This patch modifies the attr set routines to be delay ready. This means
they no longer roll or commit transactions, but instead return -EAGAIN
to have the calling routine roll and refresh the transaction.  In this
series, xfs_attr_set_args has become xfs_attr_set_iter, which uses a
state machine like switch to keep track of where it was when EAGAIN was
returned. See xfs_attr.h for a more detailed diagram of the states.

Two new helper functions have been added: xfs_attr_rmtval_find_space and
xfs_attr_rmtval_set_blk.  They provide a subset of logic similar to
xfs_attr_rmtval_set, but they store the current block in the delay attr
context to allow the caller to roll the transaction between allocations.
This helps to simplify and consolidate code used by
xfs_attr_leaf_addname and xfs_attr_node_addname. xfs_attr_set_args has
now become a simple loop to refresh the transaction until the operation
is completed.  Lastly, xfs_attr_rmtval_remove is no longer used, and is
removed.

Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Brian Foster <bfoster@redhat.com>

1 files changed, 267 insertions, 183 deletions

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 513d9caab21e..df20537c5533 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -53,15 +53,16 @@ STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args, struct xfs_buf *bp);
  */
 STATIC int xfs_attr_node_get(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_da_args *args,
-				 struct xfs_da_state *state);
-STATIC int xfs_attr_node_addname_find_attr(struct xfs_da_args *args,
-				 struct xfs_da_state **state);
-STATIC int xfs_attr_node_addname_clear_incomplete(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);
 
 int
 xfs_inode_hasattr(
@@ -244,7 +245,7 @@ xfs_attr_is_shortform(
  * Checks to see if a delayed attribute transaction should be rolled.  If so,
  * transaction is finished or rolled as needed.
  */
-int
+STATIC int
 xfs_attr_trans_roll(
 	struct xfs_delattr_context	*dac)
 {
@@ -265,29 +266,58 @@ xfs_attr_trans_roll(
 	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_set_fmt(
-	struct xfs_da_args	*args)
+	struct xfs_delattr_context	*dac,
+	struct xfs_buf			**leaf_bp)
 {
-	struct xfs_buf          *leaf_bp = NULL;
-	struct xfs_inode	*dp = args->dp;
-	int			error, error2 = 0;
+	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.
 	 */
-	error = xfs_attr_shortform_to_leaf(args, &leaf_bp);
+	error = xfs_attr_shortform_to_leaf(args, leaf_bp);
 	if (error)
 		return error;
 
@@ -296,102 +326,130 @@ xfs_attr_set_fmt(
 	 * 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);
-	xfs_trans_bhold_release(args->trans, leaf_bp);
-	if (error) {
-		xfs_trans_brelse(args->trans, leaf_bp);
-		return error;
-	}
+	xfs_trans_bhold(args->trans, *leaf_bp);
 
+	/*
+	 * 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		*bp = NULL;
-	struct xfs_da_state     *state = NULL;
-	int			forkoff, 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;
 
-	/*
-	 * 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)) {
-		error = xfs_attr_set_fmt(args);
-		if (error != -EAGAIN)
-			return error;
-	}
+	/* 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_set_fmt(dac, leaf_bp);
+		if (*leaf_bp != NULL) {
+			xfs_trans_bhold_release(args->trans, *leaf_bp);
+			*leaf_bp = NULL;
+		}
 
-	if (xfs_attr_is_leaf(dp)) {
-		error = xfs_attr_leaf_try_add(args, bp);
-		if (error == -ENOSPC) {
-			/*
-			 * Promote the attribute list to the Btree format.
-			 */
-			error = xfs_attr3_leaf_to_node(args);
-			if (error)
+		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;
+			}
 
-			/*
-			 * 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.
-			 */
-			error = xfs_defer_finish(&args->trans);
+			dac->dela_state = XFS_DAS_FOUND_LBLK;
+		} else {
+			error = xfs_attr_node_addname_find_attr(dac);
 			if (error)
 				return error;
 
-			/*
-			 * Commit the current trans (including the inode) and
-			 * start a new one.
-			 */
-			error = xfs_trans_roll_inode(&args->trans, dp);
+			error = xfs_attr_node_addname(dac);
 			if (error)
 				return error;
 
-			goto node;
-		} else if (error) {
-			return error;
+			dac->dela_state = XFS_DAS_FOUND_NBLK;
 		}
-
-		/*
-		 * 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;
-
+		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.
 		 */
-		if (args->rmtblkno > 0) {
-			error = xfs_attr_rmtval_set(args);
+
+		/* 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;
+			}
+		}
+
+		/*
+		 * Repeat allocating remote blocks for the attr value until
+		 * blkcnt drops to zero.
+		 */
+		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 this is not a rename, clear the incomplete flag and we're
+		 * done.
+		 */
 		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;
 		}
 
@@ -404,7 +462,6 @@ xfs_attr_set_args(
 		 * 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;
@@ -412,29 +469,37 @@ xfs_attr_set_args(
 		 * 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;
-
+		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_invalidate(args);
+			error = __xfs_attr_rmtval_remove(dac);
 			if (error)
 				return error;
 
-			error = xfs_attr_rmtval_remove(args);
-			if (error)
-				return error;
+			dac->dela_state = XFS_DAS_RD_LEAF;
+			return -EAGAIN;
 		}
 
+		/* fallthrough */
+	case XFS_DAS_RD_LEAF:
 		/*
-		 * Read in the block containing the "old" attr, then remove the
-		 * "old" attr from that block (neat, huh!)
+		 * 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_attr3_leaf_read(args->trans, args->dp, args->blkno,
 					   &bp);
@@ -443,97 +508,116 @@ xfs_attr_set_args(
 
 		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;
-	}
-node:
 
+	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;
+		}
 
-	do {
-		error = xfs_attr_node_addname_find_attr(args, &state);
-		if (error)
-			return error;
-		error = xfs_attr_node_addname(args, state);
-	} while (error == -EAGAIN);
-	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 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 this was 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);
+			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 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;
-	}
-
-	if (!(args->op_flags & XFS_DA_OP_RENAME)) {
+			goto out;
 		/*
-		 * Added a "remote" value, just clear the incomplete flag.
+		 * Commit the flag value change and start the next trans in
+		 * series
 		 */
-		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
-	 */
-	error = xfs_trans_roll_inode(&args->trans, args->dp);
-	if (error)
-		goto out;
+		dac->dela_state = XFS_DAS_FLIP_NFLAG;
+		return -EAGAIN;
 
-	/*
-	 * Dismantle the "old" attribute/value pair by removing a "remote" value
-	 * (if it exists).
-	 */
-	xfs_attr_restore_rmt_blk(args);
+	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);
 
-	if (args->rmtblkno) {
 		error = xfs_attr_rmtval_invalidate(args);
 		if (error)
 			return error;
 
-		error = xfs_attr_rmtval_remove(args);
-		if (error)
-			return error;
-	}
+		/* 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;
+		}
 
-	error = xfs_attr_node_addname_clear_incomplete(args);
+		/* 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(dac->dela_state != XFS_DAS_RM_SHRINK);
+		break;
+	}
 out:
 	return error;
 }
 
+
 /*
  * Return EEXIST if attr is found, or ENOATTR if not
  */
@@ -997,18 +1081,18 @@ xfs_attr_node_hasname(
 
 STATIC int
 xfs_attr_node_addname_find_attr(
-	struct xfs_da_args	*args,
-	struct xfs_da_state     **state)
+	struct xfs_delattr_context	*dac)
 {
-	int			retval;
+	struct xfs_da_args		*args = dac->da_args;
+	int				retval;
 
 	/*
 	 * Search to see if name already exists, and get back a pointer
 	 * to where it should go.
 	 */
-	retval = xfs_attr_node_hasname(args, state);
+	retval = xfs_attr_node_hasname(args, &dac->da_state);
 	if (retval != -ENOATTR && retval != -EEXIST)
-		goto error;
+		return retval;
 
 	if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
 		goto error;
@@ -1034,8 +1118,8 @@ xfs_attr_node_addname_find_attr(
 
 	return 0;
 error:
-	if (*state)
-		xfs_da_state_free(*state);
+	if (dac->da_state)
+		xfs_da_state_free(dac->da_state);
 	return retval;
 }
 
@@ -1048,19 +1132,23 @@ error:
  *
  * "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_da_args	*args,
-	struct xfs_da_state	*state)
+	struct xfs_delattr_context	*dac)
 {
-	struct xfs_da_state_blk	*blk;
-	struct xfs_inode	*dp;
-	int			error;
+	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);
 
-	dp = args->dp;
 	blk = &state->path.blk[state->path.active-1];
 	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
 
@@ -1077,18 +1165,15 @@ xfs_attr_node_addname(
 			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;
-
+			dac->flags |= XFS_DAC_DEFER_FINISH;
 			return -EAGAIN;
 		}
 
@@ -1101,9 +1186,7 @@ xfs_attr_node_addname(
 		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.
@@ -1120,8 +1203,9 @@ out:
 
 STATIC int
 xfs_attr_node_addname_clear_incomplete(
-	struct xfs_da_args		*args)
+	struct xfs_delattr_context	*dac)
 {
+	struct xfs_da_args		*args = dac->da_args;
 	struct xfs_da_state		*state = NULL;
 	struct xfs_da_state_blk		*blk;
 	int				retval = 0;