1 files changed, 126 insertions, 195 deletions

diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index be0b79d8900f..319004bf089f 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2005 Silicon Graphics, Inc.
  * Copyright (c) 2013 Red Hat, Inc.
  * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
 #include "xfs_fs.h"
@@ -27,35 +15,29 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_inode.h"
-#include "xfs_alloc.h"
+#include "xfs_attr.h"
 #include "xfs_attr_remote.h"
 #include "xfs_trans.h"
-#include "xfs_inode_item.h"
 #include "xfs_bmap.h"
-#include "xfs_attr.h"
 #include "xfs_attr_leaf.h"
-#include "xfs_error.h"
 #include "xfs_quota.h"
-#include "xfs_trace.h"
 #include "xfs_dir2.h"
+#include "xfs_error.h"
+#include "xfs_health.h"
 
 /*
- * Look at all the extents for this logical region,
- * invalidate any buffers that are incore/in transactions.
+ * Invalidate any incore buffers associated with this remote attribute value
+ * extent.   We never log remote attribute value buffers, which means that they
+ * won't be attached to a transaction and are therefore safe to mark stale.
+ * The actual bunmapi will be taken care of later.
  */
 STATIC int
-xfs_attr3_leaf_freextent(
-	struct xfs_trans	**trans,
+xfs_attr3_rmt_stale(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		blkno,
 	int			blkcnt)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_buf		*bp;
-	xfs_dablk_t		tblkno;
-	xfs_daddr_t		dblkno;
-	int			tblkcnt;
-	int			dblkcnt;
 	int			nmap;
 	int			error;
 
@@ -63,47 +45,29 @@ xfs_attr3_leaf_freextent(
 	 * Roll through the "value", invalidating the attribute value's
 	 * blocks.
 	 */
-	tblkno = blkno;
-	tblkcnt = blkcnt;
-	while (tblkcnt > 0) {
+	while (blkcnt > 0) {
 		/*
 		 * Try to remember where we decided to put the value.
 		 */
 		nmap = 1;
-		error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
+		error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt,
 				       &map, &nmap, XFS_BMAPI_ATTRFORK);
-		if (error) {
+		if (error)
 			return error;
-		}
-		ASSERT(nmap == 1);
-		ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+		if (XFS_IS_CORRUPT(dp->i_mount, nmap != 1))
+			return -EFSCORRUPTED;
 
 		/*
-		 * If it's a hole, these are already unmapped
-		 * so there's nothing to invalidate.
+		 * Mark any incore buffers for the remote value as stale.  We
+		 * never log remote attr value buffers, so the buffer should be
+		 * easy to kill.
 		 */
-		if (map.br_startblock != HOLESTARTBLOCK) {
-
-			dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
-						  map.br_startblock);
-			dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
-						map.br_blockcount);
-			bp = xfs_trans_get_buf(*trans,
-					dp->i_mount->m_ddev_targp,
-					dblkno, dblkcnt, 0);
-			if (!bp)
-				return -ENOMEM;
-			xfs_trans_binval(*trans, bp);
-			/*
-			 * Roll to next transaction.
-			 */
-			error = xfs_trans_roll(trans, dp);
-			if (error)
-				return error;
-		}
+		error = xfs_attr_rmtval_stale(dp, &map, 0);
+		if (error)
+			return error;
 
-		tblkno += map.br_blockcount;
-		tblkcnt -= map.br_blockcount;
+		blkno += map.br_blockcount;
+		blkcnt -= map.br_blockcount;
 	}
 
 	return 0;
@@ -117,86 +81,45 @@ xfs_attr3_leaf_freextent(
  */
 STATIC int
 xfs_attr3_leaf_inactive(
-	struct xfs_trans	**trans,
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_trans		**trans,
+	struct xfs_inode		*dp,
+	struct xfs_buf			*bp)
 {
-	struct xfs_attr_leafblock *leaf;
-	struct xfs_attr3_icleaf_hdr ichdr;
-	struct xfs_attr_leaf_entry *entry;
+	struct xfs_attr3_icleaf_hdr	ichdr;
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_attr_leafblock	*leaf = bp->b_addr;
+	struct xfs_attr_leaf_entry	*entry;
 	struct xfs_attr_leaf_name_remote *name_rmt;
-	struct xfs_attr_inactive_list *list;
-	struct xfs_attr_inactive_list *lp;
-	int			error;
-	int			count;
-	int			size;
-	int			tmp;
-	int			i;
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	int				error = 0;
+	int				i;
 
-	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
 	/*
-	 * Count the number of "remote" value extents.
+	 * Find the remote value extents for this leaf and invalidate their
+	 * incore buffers.
 	 */
-	count = 0;
 	entry = xfs_attr3_leaf_entryp(leaf);
 	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk)
-				count++;
-		}
-	}
+		int		blkcnt;
 
-	/*
-	 * If there are no "remote" values, we're done.
-	 */
-	if (count == 0) {
-		xfs_trans_brelse(*trans, bp);
-		return 0;
-	}
+		if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL))
+			continue;
 
-	/*
-	 * Allocate storage for a list of all the "remote" value extents.
-	 */
-	size = count * sizeof(xfs_attr_inactive_list_t);
-	list = kmem_alloc(size, KM_SLEEP);
+		name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+		if (!name_rmt->valueblk)
+			continue;
 
-	/*
-	 * Identify each of the "remote" value extents.
-	 */
-	lp = list;
-	entry = xfs_attr3_leaf_entryp(leaf);
-	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk) {
-				lp->valueblk = be32_to_cpu(name_rmt->valueblk);
-				lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
-						    be32_to_cpu(name_rmt->valuelen));
-				lp++;
-			}
-		}
-	}
-	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
-
-	/*
-	 * Invalidate each of the "remote" value extents.
-	 */
-	error = 0;
-	for (lp = list, i = 0; i < count; i++, lp++) {
-		tmp = xfs_attr3_leaf_freextent(trans, dp,
-				lp->valueblk, lp->valuelen);
-
-		if (error == 0)
-			error = tmp;	/* save only the 1st errno */
+		blkcnt = xfs_attr3_rmt_blocks(dp->i_mount,
+				be32_to_cpu(name_rmt->valuelen));
+		error = xfs_attr3_rmt_stale(dp,
+				be32_to_cpu(name_rmt->valueblk), blkcnt);
+		if (error)
+			goto err;
 	}
 
-	kmem_free(list);
+	xfs_trans_brelse(*trans, bp);
+err:
 	return error;
 }
 
@@ -206,38 +129,38 @@ xfs_attr3_leaf_inactive(
  */
 STATIC int
 xfs_attr3_node_inactive(
-	struct xfs_trans **trans,
-	struct xfs_inode *dp,
-	struct xfs_buf	*bp,
-	int		level)
+	struct xfs_trans	**trans,
+	struct xfs_inode	*dp,
+	struct xfs_buf		*bp,
+	int			level)
 {
-	xfs_da_blkinfo_t *info;
-	xfs_da_intnode_t *node;
-	xfs_dablk_t child_fsb;
-	xfs_daddr_t parent_blkno, child_blkno;
-	int error, i;
-	struct xfs_buf *child_bp;
-	struct xfs_da_node_entry *btree;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_blkinfo	*info;
+	xfs_dablk_t		child_fsb;
+	xfs_daddr_t		parent_blkno, child_blkno;
+	struct xfs_buf		*child_bp;
 	struct xfs_da3_icnode_hdr ichdr;
+	int			error, i;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
 	 */
 	if (level > XFS_DA_NODE_MAXDEPTH) {
+		xfs_buf_mark_corrupt(bp);
 		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
-		return -EIO;
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+		return -EFSCORRUPTED;
 	}
 
-	node = bp->b_addr;
-	dp->d_ops->node_hdr_from_disk(&ichdr, node);
-	parent_blkno = bp->b_bn;
+	xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr);
+	parent_blkno = xfs_buf_daddr(bp);
 	if (!ichdr.count) {
 		xfs_trans_brelse(*trans, bp);
 		return 0;
 	}
-	btree = dp->d_ops->node_tree_p(node);
-	child_fsb = be32_to_cpu(btree[0].before);
+	child_fsb = be32_to_cpu(ichdr.btree[0].before);
 	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
+	bp = NULL;
 
 	/*
 	 * If this is the node level just above the leaves, simply loop
@@ -251,64 +174,71 @@ xfs_attr3_node_inactive(
 		 * traversal of the tree so we may deal with many blocks
 		 * before we come back to this one.
 		 */
-		error = xfs_da3_node_read(*trans, dp, child_fsb, -2, &child_bp,
-						XFS_ATTR_FORK);
+		error = xfs_da3_node_read(*trans, dp, child_fsb, &child_bp,
+					  XFS_ATTR_FORK);
 		if (error)
 			return error;
-		if (child_bp) {
-						/* save for re-read later */
-			child_blkno = XFS_BUF_ADDR(child_bp);
-
-			/*
-			 * Invalidate the subtree, however we have to.
-			 */
-			info = child_bp->b_addr;
-			switch (info->magic) {
-			case cpu_to_be16(XFS_DA_NODE_MAGIC):
-			case cpu_to_be16(XFS_DA3_NODE_MAGIC):
-				error = xfs_attr3_node_inactive(trans, dp,
-							child_bp, level + 1);
-				break;
-			case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
-			case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
-				error = xfs_attr3_leaf_inactive(trans, dp,
-							child_bp);
-				break;
-			default:
-				error = -EIO;
-				xfs_trans_brelse(*trans, child_bp);
-				break;
-			}
-			if (error)
-				return error;
 
-			/*
-			 * Remove the subsidiary block from the cache
-			 * and from the log.
-			 */
-			error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
-				&child_bp, XFS_ATTR_FORK);
-			if (error)
-				return error;
-			xfs_trans_binval(*trans, child_bp);
+		/* save for re-read later */
+		child_blkno = xfs_buf_daddr(child_bp);
+
+		/*
+		 * Invalidate the subtree, however we have to.
+		 */
+		info = child_bp->b_addr;
+		switch (info->magic) {
+		case cpu_to_be16(XFS_DA_NODE_MAGIC):
+		case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+			error = xfs_attr3_node_inactive(trans, dp, child_bp,
+							level + 1);
+			break;
+		case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
+		case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+			error = xfs_attr3_leaf_inactive(trans, dp, child_bp);
+			break;
+		default:
+			xfs_buf_mark_corrupt(child_bp);
+			xfs_trans_brelse(*trans, child_bp);
+			xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+			error = -EFSCORRUPTED;
+			break;
 		}
+		if (error)
+			return error;
+
+		/*
+		 * Remove the subsidiary block from the cache and from the log.
+		 */
+		error = xfs_trans_get_buf(*trans, mp->m_ddev_targp,
+				child_blkno,
+				XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0,
+				&child_bp);
+		if (error)
+			return error;
+		xfs_trans_binval(*trans, child_bp);
+		child_bp = NULL;
 
 		/*
 		 * If we're not done, re-read the parent to get the next
 		 * child block number.
 		 */
 		if (i + 1 < ichdr.count) {
-			error = xfs_da3_node_read(*trans, dp, 0, parent_blkno,
-						 &bp, XFS_ATTR_FORK);
+			struct xfs_da3_icnode_hdr phdr;
+
+			error = xfs_da3_node_read_mapped(*trans, dp,
+					parent_blkno, &bp, XFS_ATTR_FORK);
 			if (error)
 				return error;
-			child_fsb = be32_to_cpu(btree[i + 1].before);
+			xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr,
+						  bp->b_addr);
+			child_fsb = be32_to_cpu(phdr.btree[i + 1].before);
 			xfs_trans_brelse(*trans, bp);
+			bp = NULL;
 		}
 		/*
 		 * Atomically commit the whole invalidate stuff.
 		 */
-		error = xfs_trans_roll(trans, dp);
+		error = xfs_trans_roll_inode(trans, dp);
 		if (error)
 			return  error;
 	}
@@ -327,6 +257,7 @@ xfs_attr3_root_inactive(
 	struct xfs_trans	**trans,
 	struct xfs_inode	*dp)
 {
+	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_blkinfo	*info;
 	struct xfs_buf		*bp;
 	xfs_daddr_t		blkno;
@@ -338,10 +269,10 @@ xfs_attr3_root_inactive(
 	 * the extents in reverse order the extent containing
 	 * block 0 must still be there.
 	 */
-	error = xfs_da3_node_read(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
+	error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK);
 	if (error)
 		return error;
-	blkno = bp->b_bn;
+	blkno = xfs_buf_daddr(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
@@ -358,7 +289,9 @@ xfs_attr3_root_inactive(
 		error = xfs_attr3_leaf_inactive(trans, dp, bp);
 		break;
 	default:
-		error = -EIO;
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+		error = -EFSCORRUPTED;
+		xfs_buf_mark_corrupt(bp);
 		xfs_trans_brelse(*trans, bp);
 		break;
 	}
@@ -368,14 +301,15 @@ xfs_attr3_root_inactive(
 	/*
 	 * Invalidate the incore copy of the root block.
 	 */
-	error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
+	error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno,
+			XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp);
 	if (error)
 		return error;
 	xfs_trans_binval(*trans, bp);	/* remove from cache */
 	/*
 	 * Commit the invalidate and start the next transaction.
 	 */
-	error = xfs_trans_roll(trans, dp);
+	error = xfs_trans_roll_inode(trans, dp);
 
 	return error;
 }
@@ -398,10 +332,9 @@ xfs_attr_inactive(
 	int			error = 0;
 
 	mp = dp->i_mount;
-	ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
 
 	xfs_ilock(dp, lock_mode);
-	if (!XFS_IFORK_Q(dp))
+	if (!xfs_inode_has_attr_fork(dp))
 		goto out_destroy_fork;
 	xfs_iunlock(dp, lock_mode);
 
@@ -414,7 +347,7 @@ xfs_attr_inactive(
 	lock_mode = XFS_ILOCK_EXCL;
 	xfs_ilock(dp, lock_mode);
 
-	if (!XFS_IFORK_Q(dp))
+	if (!xfs_inode_has_attr_fork(dp))
 		goto out_cancel;
 
 	/*
@@ -425,12 +358,11 @@ xfs_attr_inactive(
 
 	/*
 	 * Invalidate and truncate the attribute fork extents. Make sure the
-	 * fork actually has attributes as otherwise the invalidation has no
+	 * fork actually has xattr blocks as otherwise the invalidation has no
 	 * blocks to read and returns an error. In this case, just do the fork
 	 * removal below.
 	 */
-	if (xfs_inode_hasattr(dp) &&
-	    dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+	if (dp->i_af.if_nextents > 0) {
 		error = xfs_attr3_root_inactive(&trans, dp);
 		if (error)
 			goto out_cancel;
@@ -451,8 +383,7 @@ out_cancel:
 	xfs_trans_cancel(trans);
 out_destroy_fork:
 	/* kill the in-core attr fork before we drop the inode lock */
-	if (dp->i_afp)
-		xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+	xfs_ifork_zap_attr(dp);
 	if (lock_mode)
 		xfs_iunlock(dp, lock_mode);
 	return error;