These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

38 files changed, 1068 insertions, 1169 deletions

diff --git a/kernel/fs/ocfs2/acl.c b/kernel/fs/ocfs2/acl.c
index c58a1bcfd..0cdf497c9 100644
--- a/kernel/fs/ocfs2/acl.c
+++ b/kernel/fs/ocfs2/acl.c
@@ -284,7 +284,19 @@ int ocfs2_set_acl(handle_t *handle,
 
 int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	return ocfs2_set_acl(NULL, inode, NULL, type, acl, NULL, NULL);
+	struct buffer_head *bh = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &bh, 1);
+	if (status < 0) {
+		if (status != -ENOENT)
+			mlog_errno(status);
+		return status;
+	}
+	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
+	ocfs2_inode_unlock(inode, 1);
+	brelse(bh);
+	return status;
 }
 
 struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
@@ -292,19 +304,21 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 	struct ocfs2_super *osb;
 	struct buffer_head *di_bh = NULL;
 	struct posix_acl *acl;
-	int ret = -EAGAIN;
+	int ret;
 
 	osb = OCFS2_SB(inode->i_sb);
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
 		return NULL;
-
-	ret = ocfs2_read_inode_block(inode, &di_bh);
-	if (ret < 0)
+	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			mlog_errno(ret);
 		return ERR_PTR(ret);
+	}
 
 	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
 
+	ocfs2_inode_unlock(inode, 0);
 	brelse(di_bh);
-
 	return acl;
 }
diff --git a/kernel/fs/ocfs2/alloc.c b/kernel/fs/ocfs2/alloc.c
index 2d7f76e52..86181d652 100644
--- a/kernel/fs/ocfs2/alloc.c
+++ b/kernel/fs/ocfs2/alloc.c
@@ -908,32 +908,30 @@ static int ocfs2_validate_extent_block(struct super_block *sb,
 	 */
 
 	if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
-		ocfs2_error(sb,
-			    "Extent block #%llu has bad signature %.*s",
-			    (unsigned long long)bh->b_blocknr, 7,
-			    eb->h_signature);
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Extent block #%llu has bad signature %.*s\n",
+				 (unsigned long long)bh->b_blocknr, 7,
+				 eb->h_signature);
+		goto bail;
 	}
 
 	if (le64_to_cpu(eb->h_blkno) != bh->b_blocknr) {
-		ocfs2_error(sb,
-			    "Extent block #%llu has an invalid h_blkno "
-			    "of %llu",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)le64_to_cpu(eb->h_blkno));
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Extent block #%llu has an invalid h_blkno of %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 (unsigned long long)le64_to_cpu(eb->h_blkno));
+		goto bail;
 	}
 
 	if (le32_to_cpu(eb->h_fs_generation) != OCFS2_SB(sb)->fs_generation) {
-		ocfs2_error(sb,
-			    "Extent block #%llu has an invalid "
-			    "h_fs_generation of #%u",
-			    (unsigned long long)bh->b_blocknr,
-			    le32_to_cpu(eb->h_fs_generation));
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Extent block #%llu has an invalid h_fs_generation of #%u\n",
+				 (unsigned long long)bh->b_blocknr,
+				 le32_to_cpu(eb->h_fs_generation));
+		goto bail;
 	}
-
-	return 0;
+bail:
+	return rc;
 }
 
 int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno,
@@ -1446,8 +1444,7 @@ static int ocfs2_find_branch_target(struct ocfs2_extent_tree *et,
 	while(le16_to_cpu(el->l_tree_depth) > 1) {
 		if (le16_to_cpu(el->l_next_free_rec) == 0) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu has empty "
-				    "extent list (next_free_rec == 0)",
+				    "Owner %llu has empty extent list (next_free_rec == 0)\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci));
 			status = -EIO;
 			goto bail;
@@ -1456,9 +1453,7 @@ static int ocfs2_find_branch_target(struct ocfs2_extent_tree *et,
 		blkno = le64_to_cpu(el->l_recs[i].e_blkno);
 		if (!blkno) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu has extent "
-				    "list where extent # %d has no physical "
-				    "block start",
+				    "Owner %llu has extent list where extent # %d has no physical block start\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci), i);
 			status = -EIO;
 			goto bail;
@@ -1788,8 +1783,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
 	while (el->l_tree_depth) {
 		if (le16_to_cpu(el->l_next_free_rec) == 0) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(ci),
-				    "Owner %llu has empty extent list at "
-				    "depth %u\n",
+				    "Owner %llu has empty extent list at depth %u\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(ci),
 				    le16_to_cpu(el->l_tree_depth));
 			ret = -EROFS;
@@ -1814,8 +1808,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
 		blkno = le64_to_cpu(el->l_recs[i].e_blkno);
 		if (blkno == 0) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(ci),
-				    "Owner %llu has bad blkno in extent list "
-				    "at depth %u (index %d)\n",
+				    "Owner %llu has bad blkno in extent list at depth %u (index %d)\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(ci),
 				    le16_to_cpu(el->l_tree_depth), i);
 			ret = -EROFS;
@@ -1836,8 +1829,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
 		if (le16_to_cpu(el->l_next_free_rec) >
 		    le16_to_cpu(el->l_count)) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(ci),
-				    "Owner %llu has bad count in extent list "
-				    "at block %llu (next free=%u, count=%u)\n",
+				    "Owner %llu has bad count in extent list at block %llu (next free=%u, count=%u)\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(ci),
 				    (unsigned long long)bh->b_blocknr,
 				    le16_to_cpu(el->l_next_free_rec),
@@ -2116,8 +2108,7 @@ static int ocfs2_rotate_subtree_right(handle_t *handle,
 
 	if (left_el->l_next_free_rec != left_el->l_count) {
 		ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-			    "Inode %llu has non-full interior leaf node %llu"
-			    "(next free = %u)",
+			    "Inode %llu has non-full interior leaf node %llu (next free = %u)\n",
 			    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
 			    (unsigned long long)left_leaf_bh->b_blocknr,
 			    le16_to_cpu(left_el->l_next_free_rec));
@@ -2256,8 +2247,7 @@ int ocfs2_find_cpos_for_left_leaf(struct super_block *sb,
 		 * If we got here, we never found a valid node where
 		 * the tree indicated one should be.
 		 */
-		ocfs2_error(sb,
-			    "Invalid extent tree at extent block %llu\n",
+		ocfs2_error(sb, "Invalid extent tree at extent block %llu\n",
 			    (unsigned long long)blkno);
 		ret = -EROFS;
 		goto out;
@@ -2872,8 +2862,7 @@ int ocfs2_find_cpos_for_right_leaf(struct super_block *sb,
 		 * If we got here, we never found a valid node where
 		 * the tree indicated one should be.
 		 */
-		ocfs2_error(sb,
-			    "Invalid extent tree at extent block %llu\n",
+		ocfs2_error(sb, "Invalid extent tree at extent block %llu\n",
 			    (unsigned long long)blkno);
 		ret = -EROFS;
 		goto out;
@@ -2925,7 +2914,8 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
 	struct ocfs2_path *right_path = NULL;
 	struct super_block *sb = ocfs2_metadata_cache_get_super(et->et_ci);
 
-	BUG_ON(!ocfs2_is_empty_extent(&(path_leaf_el(path)->l_recs[0])));
+	if (!ocfs2_is_empty_extent(&(path_leaf_el(path)->l_recs[0])))
+		return 0;
 
 	*empty_extent_path = NULL;
 
@@ -3130,6 +3120,30 @@ out:
 	return ret;
 }
 
+static int ocfs2_remove_rightmost_empty_extent(struct ocfs2_super *osb,
+				struct ocfs2_extent_tree *et,
+				struct ocfs2_path *path,
+				struct ocfs2_cached_dealloc_ctxt *dealloc)
+{
+	handle_t *handle;
+	int ret;
+	int credits = path->p_tree_depth * 2 + 1;
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		return ret;
+	}
+
+	ret = ocfs2_remove_rightmost_path(handle, et, path, dealloc);
+	if (ret)
+		mlog_errno(ret);
+
+	ocfs2_commit_trans(osb, handle);
+	return ret;
+}
+
 /*
  * Left rotation of btree records.
  *
@@ -3199,7 +3213,7 @@ rightmost_no_delete:
 		if (le16_to_cpu(el->l_next_free_rec) == 0) {
 			ret = -EIO;
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu has empty extent block at %llu",
+				    "Owner %llu has empty extent block at %llu\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
 				    (unsigned long long)le64_to_cpu(eb->h_blkno));
 			goto out;
@@ -3929,7 +3943,7 @@ static void ocfs2_adjust_rightmost_records(handle_t *handle,
 		next_free = le16_to_cpu(el->l_next_free_rec);
 		if (next_free == 0) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu has a bad extent list",
+				    "Owner %llu has a bad extent list\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci));
 			ret = -EIO;
 			return;
@@ -4311,13 +4325,13 @@ out:
 	return ret;
 }
 
-static enum ocfs2_contig_type
-ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
+static int ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 			       struct ocfs2_path *path,
 			       struct ocfs2_extent_list *el, int index,
-			       struct ocfs2_extent_rec *split_rec)
+			       struct ocfs2_extent_rec *split_rec,
+			       struct ocfs2_merge_ctxt *ctxt)
 {
-	int status;
+	int status = 0;
 	enum ocfs2_contig_type ret = CONTIG_NONE;
 	u32 left_cpos, right_cpos;
 	struct ocfs2_extent_rec *rec = NULL;
@@ -4336,8 +4350,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 
 		if (left_cpos != 0) {
 			left_path = ocfs2_new_path_from_path(path);
-			if (!left_path)
+			if (!left_path) {
+				status = -ENOMEM;
+				mlog_errno(status);
 				goto exit;
+			}
 
 			status = ocfs2_find_path(et->et_ci, left_path,
 						 left_cpos);
@@ -4351,10 +4368,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 				bh = path_leaf_bh(left_path);
 				eb = (struct ocfs2_extent_block *)bh->b_data;
 				ocfs2_error(sb,
-					    "Extent block #%llu has an "
-					    "invalid l_next_free_rec of "
-					    "%d.  It should have "
-					    "matched the l_count of %d",
+					    "Extent block #%llu has an invalid l_next_free_rec of %d.  It should have matched the l_count of %d\n",
 					    (unsigned long long)le64_to_cpu(eb->h_blkno),
 					    le16_to_cpu(new_el->l_next_free_rec),
 					    le16_to_cpu(new_el->l_count));
@@ -4392,8 +4406,11 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 			goto free_left_path;
 
 		right_path = ocfs2_new_path_from_path(path);
-		if (!right_path)
+		if (!right_path) {
+			status = -ENOMEM;
+			mlog_errno(status);
 			goto free_left_path;
+		}
 
 		status = ocfs2_find_path(et->et_ci, right_path, right_cpos);
 		if (status)
@@ -4406,8 +4423,7 @@ ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
 				bh = path_leaf_bh(right_path);
 				eb = (struct ocfs2_extent_block *)bh->b_data;
 				ocfs2_error(sb,
-					    "Extent block #%llu has an "
-					    "invalid l_next_free_rec of %d",
+					    "Extent block #%llu has an invalid l_next_free_rec of %d\n",
 					    (unsigned long long)le64_to_cpu(eb->h_blkno),
 					    le16_to_cpu(new_el->l_next_free_rec));
 				status = -EINVAL;
@@ -4433,7 +4449,10 @@ free_right_path:
 free_left_path:
 	ocfs2_free_path(left_path);
 exit:
-	return ret;
+	if (status == 0)
+		ctxt->c_contig_type = ret;
+
+	return status;
 }
 
 static void ocfs2_figure_contig_type(struct ocfs2_extent_tree *et,
@@ -4960,10 +4979,9 @@ leftright:
 		split_index = ocfs2_search_extent_list(el, cpos);
 		if (split_index == -1) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-					"Owner %llu has an extent at cpos %u "
-					"which can no longer be found.\n",
-					(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
-					cpos);
+				    "Owner %llu has an extent at cpos %u which can no longer be found\n",
+				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
+				    cpos);
 			ret = -EROFS;
 			goto out;
 		}
@@ -5039,9 +5057,14 @@ int ocfs2_split_extent(handle_t *handle,
 		goto out;
 	}
 
-	ctxt.c_contig_type = ocfs2_figure_merge_contig_type(et, path, el,
-							    split_index,
-							    split_rec);
+	ret = ocfs2_figure_merge_contig_type(et, path, el,
+					     split_index,
+					     split_rec,
+					     &ctxt);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
 
 	/*
 	 * The core merge / split code wants to know how much room is
@@ -5143,10 +5166,9 @@ int ocfs2_change_extent_flag(handle_t *handle,
 	index = ocfs2_search_extent_list(el, cpos);
 	if (index == -1) {
 		ocfs2_error(sb,
-			    "Owner %llu has an extent at cpos %u which can no "
-			    "longer be found.\n",
-			     (unsigned long long)
-			     ocfs2_metadata_cache_owner(et->et_ci), cpos);
+			    "Owner %llu has an extent at cpos %u which can no longer be found\n",
+			    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
+			    cpos);
 		ret = -EROFS;
 		goto out;
 	}
@@ -5213,9 +5235,7 @@ int ocfs2_mark_extent_written(struct inode *inode,
 		cpos, len, phys);
 
 	if (!ocfs2_writes_unwritten_extents(OCFS2_SB(inode->i_sb))) {
-		ocfs2_error(inode->i_sb, "Inode %llu has unwritten extents "
-			    "that are being written to, but the feature bit "
-			    "is not set in the super block.",
+		ocfs2_error(inode->i_sb, "Inode %llu has unwritten extents that are being written to, but the feature bit is not set in the super block\n",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno);
 		ret = -EROFS;
 		goto out;
@@ -5499,8 +5519,7 @@ int ocfs2_remove_extent(handle_t *handle,
 	index = ocfs2_search_extent_list(el, cpos);
 	if (index == -1) {
 		ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-			    "Owner %llu has an extent at cpos %u which can no "
-			    "longer be found.\n",
+			    "Owner %llu has an extent at cpos %u which can no longer be found\n",
 			    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
 			    cpos);
 		ret = -EROFS;
@@ -5565,7 +5584,7 @@ int ocfs2_remove_extent(handle_t *handle,
 		index = ocfs2_search_extent_list(el, cpos);
 		if (index == -1) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu: split at cpos %u lost record.",
+				    "Owner %llu: split at cpos %u lost record\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
 				    cpos);
 			ret = -EROFS;
@@ -5581,8 +5600,7 @@ int ocfs2_remove_extent(handle_t *handle,
 			ocfs2_rec_clusters(el, rec);
 		if (rec_range != trunc_range) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
-				    "Owner %llu: error after split at cpos %u"
-				    "trunc len %u, existing record is (%u,%u)",
+				    "Owner %llu: error after split at cpos %u trunc len %u, existing record is (%u,%u)\n",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
 				    cpos, len, le32_to_cpu(rec->e_cpos),
 				    ocfs2_rec_clusters(el, rec));
@@ -6160,7 +6178,7 @@ bail:
 		iput(tl_inode);
 	brelse(tl_bh);
 
-	if (status < 0 && (*tl_copy)) {
+	if (status < 0) {
 		kfree(*tl_copy);
 		*tl_copy = NULL;
 		mlog_errno(status);
@@ -7093,15 +7111,23 @@ start:
 		 * to check it up here before changing the tree.
 		*/
 		if (root_el->l_tree_depth && rec->e_int_clusters == 0) {
-			ocfs2_error(inode->i_sb, "Inode %lu has an empty "
+			mlog(ML_ERROR, "Inode %lu has an empty "
 				    "extent record, depth %u\n", inode->i_ino,
 				    le16_to_cpu(root_el->l_tree_depth));
-			status = -EROFS;
-			goto bail;
+			status = ocfs2_remove_rightmost_empty_extent(osb,
+					&et, path, &dealloc);
+			if (status) {
+				mlog_errno(status);
+				goto bail;
+			}
+
+			ocfs2_reinit_path(path, 1);
+			goto start;
+		} else {
+			trunc_cpos = le32_to_cpu(rec->e_cpos);
+			trunc_len = 0;
+			blkno = 0;
 		}
-		trunc_cpos = le32_to_cpu(rec->e_cpos);
-		trunc_len = 0;
-		blkno = 0;
 	} else if (le32_to_cpu(rec->e_cpos) >= new_highest_cpos) {
 		/*
 		 * Truncate entire record.
@@ -7189,8 +7215,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 	    !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
 	    !ocfs2_supports_inline_data(osb)) {
 		ocfs2_error(inode->i_sb,
-			    "Inline data flags for inode %llu don't agree! "
-			    "Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n",
+			    "Inline data flags for inode %llu don't agree! Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
 			    le16_to_cpu(di->i_dyn_features),
 			    OCFS2_I(inode)->ip_dyn_features,
diff --git a/kernel/fs/ocfs2/aops.c b/kernel/fs/ocfs2/aops.c
index 9ea701270..e6795c7c7 100644
--- a/kernel/fs/ocfs2/aops.c
+++ b/kernel/fs/ocfs2/aops.c
@@ -227,7 +227,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
 	if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
-		ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag",
+		ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag\n",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno);
 		return -EROFS;
 	}
@@ -237,7 +237,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 	if (size > PAGE_CACHE_SIZE ||
 	    size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
 		ocfs2_error(inode->i_sb,
-			    "Inode %llu has with inline data has bad size: %Lu",
+			    "Inode %llu has with inline data has bad size: %Lu\n",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
 			    (unsigned long long)size);
 		return -EROFS;
@@ -523,7 +523,7 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
 	unsigned long len = bh_result->b_size;
-	unsigned int clusters_to_alloc = 0;
+	unsigned int clusters_to_alloc = 0, contig_clusters = 0;
 
 	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
@@ -533,10 +533,14 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 
 	inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
 
+	down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
 	/* This figures out the size of the next contiguous block, and
 	 * our logical offset */
 	ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
 					  &contig_blocks, &ext_flags);
+	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
 	if (ret) {
 		mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
 		     (unsigned long long)iblock);
@@ -557,16 +561,21 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 
 		alloc_locked = 1;
 
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
+
 		/* fill hole, allocate blocks can't be larger than the size
 		 * of the hole */
 		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
-		if (clusters_to_alloc > contig_blocks)
-			clusters_to_alloc = contig_blocks;
+		contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
+				contig_blocks);
+		if (clusters_to_alloc > contig_clusters)
+			clusters_to_alloc = contig_clusters;
 
 		/* allocate extent and insert them into the extent tree */
 		ret = ocfs2_extend_allocation(inode, cpos,
 				clusters_to_alloc, 0);
 		if (ret < 0) {
+			up_write(&OCFS2_I(inode)->ip_alloc_sem);
 			mlog_errno(ret);
 			goto bail;
 		}
@@ -574,11 +583,14 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
 				&contig_blocks, &ext_flags);
 		if (ret < 0) {
+			up_write(&OCFS2_I(inode)->ip_alloc_sem);
 			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
 					(unsigned long long)iblock);
 			ret = -EIO;
 			goto bail;
 		}
+		set_buffer_new(bh_result);
+		up_write(&OCFS2_I(inode)->ip_alloc_sem);
 	}
 
 	/*
@@ -619,19 +631,19 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
-	if (ocfs2_iocb_is_sem_locked(iocb))
-		ocfs2_iocb_clear_sem_locked(iocb);
-
 	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
 		ocfs2_iocb_clear_unaligned_aio(iocb);
 
 		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
 	}
 
-	ocfs2_iocb_clear_rw_locked(iocb);
+	/* Let rw unlock to be done later to protect append direct io write */
+	if (offset + bytes <= i_size_read(inode)) {
+		ocfs2_iocb_clear_rw_locked(iocb);
 
-	level = ocfs2_iocb_rw_locked_level(iocb);
-	ocfs2_rw_unlock(inode, level);
+		level = ocfs2_iocb_rw_locked_level(iocb);
+		ocfs2_rw_unlock(inode, level);
+	}
 }
 
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
@@ -833,12 +845,17 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 		/* zeroing out the previously allocated cluster tail
 		 * that but not zeroed */
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
+			down_read(&OCFS2_I(inode)->ip_alloc_sem);
 			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
 					zero_len_tail, cluster_align_tail);
-		else
+			up_read(&OCFS2_I(inode)->ip_alloc_sem);
+		} else {
+			down_write(&OCFS2_I(inode)->ip_alloc_sem);
 			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
 					offset);
+			up_write(&OCFS2_I(inode)->ip_alloc_sem);
+		}
 		if (ret < 0) {
 			mlog_errno(ret);
 			ocfs2_inode_unlock(inode, 1);
@@ -848,6 +865,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
 		if (is_overwrite < 0) {
 			mlog_errno(is_overwrite);
+			ret = is_overwrite;
 			ocfs2_inode_unlock(inode, 1);
 			goto clean_orphan;
 		}
@@ -858,7 +876,8 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				       offset, ocfs2_direct_IO_get_blocks,
 				       ocfs2_dio_end_io, NULL, 0);
-	if (unlikely(written < 0)) {
+	/* overwrite aio may return -EIOCBQUEUED, and it is not an error */
+	if ((written < 0) && (written != -EIOCBQUEUED)) {
 		loff_t i_size = i_size_read(inode);
 
 		if (offset + count > i_size) {
@@ -877,12 +896,14 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 					ocfs2_inode_unlock(inode, 1);
 					brelse(di_bh);
+					di_bh = NULL;
 					goto clean_orphan;
 				}
 			}
 
 			ocfs2_inode_unlock(inode, 1);
 			brelse(di_bh);
+			di_bh = NULL;
 
 			ret = jbd2_journal_force_commit(journal);
 			if (ret < 0)
@@ -925,13 +946,26 @@ clean_orphan:
 		int update_isize = written > 0 ? 1 : 0;
 		loff_t end = update_isize ? offset + written : 0;
 
-		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+		tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(ret);
+			goto out;
+		}
+
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
 				update_isize, end);
 		if (tmp_ret < 0) {
+			ocfs2_inode_unlock(inode, 1);
 			ret = tmp_ret;
+			mlog_errno(ret);
+			brelse(di_bh);
 			goto out;
 		}
 
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+
 		tmp_ret = jbd2_journal_force_commit(journal);
 		if (tmp_ret < 0) {
 			ret = tmp_ret;
@@ -2176,10 +2210,7 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
+
 	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
@@ -2336,7 +2367,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2345,6 +2376,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	handle_t *handle = wc->w_handle;
 	struct page *tmppage;
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
 		ocfs2_write_end_inline(inode, pos, len, &copied, di, wc);
 		goto out_write_size;
@@ -2400,6 +2439,7 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
 	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
 	 * lock, or it will cause a deadlock since journal commit threads holds
 	 * this lock and will ask for the page lock when flushing the data.
diff --git a/kernel/fs/ocfs2/aops.h b/kernel/fs/ocfs2/aops.h
index dd59599b0..24e496d6b 100644
--- a/kernel/fs/ocfs2/aops.h
+++ b/kernel/fs/ocfs2/aops.h
@@ -79,7 +79,6 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
-	OCFS2_IOCB_SEM,
 	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
@@ -88,12 +87,6 @@ enum ocfs2_iocb_lock_bits {
 	clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_rw_locked_level(iocb) \
 	test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_set_sem_locked(iocb) \
-	set_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_clear_sem_locked(iocb) \
-	clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_is_sem_locked(iocb) \
-	test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
 
 #define ocfs2_iocb_set_unaligned_aio(iocb) \
 	set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
diff --git a/kernel/fs/ocfs2/buffer_head_io.c b/kernel/fs/ocfs2/buffer_head_io.c
index 1edcb141f..fe50ded1b 100644
--- a/kernel/fs/ocfs2/buffer_head_io.c
+++ b/kernel/fs/ocfs2/buffer_head_io.c
@@ -316,6 +316,12 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		bh = bhs[i];
 
 		if (!(flags & OCFS2_BH_READAHEAD)) {
+			if (status) {
+				/* Clear the rest of the buffers on error */
+				put_bh(bh);
+				bhs[i] = NULL;
+				continue;
+			}
 			/* We know this can't have changed as we hold the
 			 * owner sem. Avoid doing any work on the bh if the
 			 * journal has it. */
diff --git a/kernel/fs/ocfs2/cluster/heartbeat.c b/kernel/fs/ocfs2/cluster/heartbeat.c
index 16eff4572..709fbbd44 100644
--- a/kernel/fs/ocfs2/cluster/heartbeat.c
+++ b/kernel/fs/ocfs2/cluster/heartbeat.c
@@ -36,7 +36,7 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/bitmap.h>
-
+#include <linux/ktime.h>
 #include "heartbeat.h"
 #include "tcp.h"
 #include "nodemanager.h"
@@ -219,7 +219,8 @@ struct o2hb_region {
 	unsigned		hr_unclean_stop:1,
 				hr_aborted_start:1,
 				hr_item_pinned:1,
-				hr_item_dropped:1;
+				hr_item_dropped:1,
+				hr_node_deleted:1;
 
 	/* protected by the hr_callback_sem */
 	struct task_struct 	*hr_task;
@@ -372,14 +373,13 @@ static void o2hb_wait_on_io(struct o2hb_region *reg,
 	wait_for_completion(&wc->wc_io_complete);
 }
 
-static void o2hb_bio_end_io(struct bio *bio,
-			   int error)
+static void o2hb_bio_end_io(struct bio *bio)
 {
 	struct o2hb_bio_wait_ctxt *wc = bio->bi_private;
 
-	if (error) {
-		mlog(ML_ERROR, "IO Error %d\n", error);
-		wc->wc_error = error;
+	if (bio->bi_error) {
+		mlog(ML_ERROR, "IO Error %d\n", bio->bi_error);
+		wc->wc_error = bio->bi_error;
 	}
 
 	o2hb_bio_wait_dec(wc, 1);
@@ -1061,37 +1061,6 @@ bail:
 	return ret;
 }
 
-/* Subtract b from a, storing the result in a. a *must* have a larger
- * value than b. */
-static void o2hb_tv_subtract(struct timeval *a,
-			     struct timeval *b)
-{
-	/* just return 0 when a is after b */
-	if (a->tv_sec < b->tv_sec ||
-	    (a->tv_sec == b->tv_sec && a->tv_usec < b->tv_usec)) {
-		a->tv_sec = 0;
-		a->tv_usec = 0;
-		return;
-	}
-
-	a->tv_sec -= b->tv_sec;
-	a->tv_usec -= b->tv_usec;
-	while ( a->tv_usec < 0 ) {
-		a->tv_sec--;
-		a->tv_usec += 1000000;
-	}
-}
-
-static unsigned int o2hb_elapsed_msecs(struct timeval *start,
-				       struct timeval *end)
-{
-	struct timeval res = *end;
-
-	o2hb_tv_subtract(&res, start);
-
-	return res.tv_sec * 1000 + res.tv_usec / 1000;
-}
-
 /*
  * we ride the region ref that the region dir holds.  before the region
  * dir is removed and drops it ref it will wait to tear down this
@@ -1102,7 +1071,7 @@ static int o2hb_thread(void *data)
 	int i, ret;
 	struct o2hb_region *reg = data;
 	struct o2hb_bio_wait_ctxt write_wc;
-	struct timeval before_hb, after_hb;
+	ktime_t before_hb, after_hb;
 	unsigned int elapsed_msec;
 
 	mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread running\n");
@@ -1110,7 +1079,13 @@ static int o2hb_thread(void *data)
 	set_user_nice(current, MIN_NICE);
 
 	/* Pin node */
-	o2nm_depend_this_node();
+	ret = o2nm_depend_this_node();
+	if (ret) {
+		mlog(ML_ERROR, "Node has been deleted, ret = %d\n", ret);
+		reg->hr_node_deleted = 1;
+		wake_up(&o2hb_steady_queue);
+		return 0;
+	}
 
 	while (!kthread_should_stop() &&
 	       !reg->hr_unclean_stop && !reg->hr_aborted_start) {
@@ -1119,18 +1094,18 @@ static int o2hb_thread(void *data)
 		 * hr_timeout_ms between disk writes. On busy systems
 		 * this should result in a heartbeat which is less
 		 * likely to time itself out. */
-		do_gettimeofday(&before_hb);
+		before_hb = ktime_get_real();
 
 		ret = o2hb_do_disk_heartbeat(reg);
 
-		do_gettimeofday(&after_hb);
-		elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
+		after_hb = ktime_get_real();
+
+		elapsed_msec = (unsigned int)
+				ktime_ms_delta(after_hb, before_hb);
 
 		mlog(ML_HEARTBEAT,
-		     "start = %lu.%lu, end = %lu.%lu, msec = %u, ret = %d\n",
-		     before_hb.tv_sec, (unsigned long) before_hb.tv_usec,
-		     after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
-		     elapsed_msec, ret);
+		     "start = %lld, end = %lld, msec = %u, ret = %d\n",
+		     before_hb.tv64, after_hb.tv64, elapsed_msec, ret);
 
 		if (!kthread_should_stop() &&
 		    elapsed_msec < reg->hr_timeout_ms) {
@@ -1505,16 +1480,17 @@ static int o2hb_read_block_input(struct o2hb_region *reg,
 	return 0;
 }
 
-static ssize_t o2hb_region_block_bytes_read(struct o2hb_region *reg,
+static ssize_t o2hb_region_block_bytes_show(struct config_item *item,
 					    char *page)
 {
-	return sprintf(page, "%u\n", reg->hr_block_bytes);
+	return sprintf(page, "%u\n", to_o2hb_region(item)->hr_block_bytes);
 }
 
-static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
 					     const char *page,
 					     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	int status;
 	unsigned long block_bytes;
 	unsigned int block_bits;
@@ -1533,16 +1509,17 @@ static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_start_block_read(struct o2hb_region *reg,
+static ssize_t o2hb_region_start_block_show(struct config_item *item,
 					    char *page)
 {
-	return sprintf(page, "%llu\n", reg->hr_start_block);
+	return sprintf(page, "%llu\n", to_o2hb_region(item)->hr_start_block);
 }
 
-static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_start_block_store(struct config_item *item,
 					     const char *page,
 					     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	unsigned long long tmp;
 	char *p = (char *)page;
 
@@ -1558,16 +1535,16 @@ static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_blocks_read(struct o2hb_region *reg,
-				       char *page)
+static ssize_t o2hb_region_blocks_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", reg->hr_blocks);
+	return sprintf(page, "%d\n", to_o2hb_region(item)->hr_blocks);
 }
 
-static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_blocks_store(struct config_item *item,
 					const char *page,
 					size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	unsigned long tmp;
 	char *p = (char *)page;
 
@@ -1586,13 +1563,12 @@ static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_dev_read(struct o2hb_region *reg,
-				    char *page)
+static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
 {
 	unsigned int ret = 0;
 
-	if (reg->hr_bdev)
-		ret = sprintf(page, "%s\n", reg->hr_dev_name);
+	if (to_o2hb_region(item)->hr_bdev)
+		ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name);
 
 	return ret;
 }
@@ -1620,17 +1596,13 @@ static int o2hb_map_slot_data(struct o2hb_region *reg)
 	struct o2hb_disk_slot *slot;
 
 	reg->hr_tmp_block = kmalloc(reg->hr_block_bytes, GFP_KERNEL);
-	if (reg->hr_tmp_block == NULL) {
-		mlog_errno(-ENOMEM);
+	if (reg->hr_tmp_block == NULL)
 		return -ENOMEM;
-	}
 
 	reg->hr_slots = kcalloc(reg->hr_blocks,
 				sizeof(struct o2hb_disk_slot), GFP_KERNEL);
-	if (reg->hr_slots == NULL) {
-		mlog_errno(-ENOMEM);
+	if (reg->hr_slots == NULL)
 		return -ENOMEM;
-	}
 
 	for(i = 0; i < reg->hr_blocks; i++) {
 		slot = &reg->hr_slots[i];
@@ -1646,17 +1618,13 @@ static int o2hb_map_slot_data(struct o2hb_region *reg)
 
 	reg->hr_slot_data = kcalloc(reg->hr_num_pages, sizeof(struct page *),
 				    GFP_KERNEL);
-	if (!reg->hr_slot_data) {
-		mlog_errno(-ENOMEM);
+	if (!reg->hr_slot_data)
 		return -ENOMEM;
-	}
 
 	for(i = 0; i < reg->hr_num_pages; i++) {
 		page = alloc_page(GFP_KERNEL);
-		if (!page) {
-			mlog_errno(-ENOMEM);
+		if (!page)
 			return -ENOMEM;
-		}
 
 		reg->hr_slot_data[i] = page;
 
@@ -1688,10 +1656,8 @@ static int o2hb_populate_slot_data(struct o2hb_region *reg)
 	struct o2hb_disk_heartbeat_block *hb_block;
 
 	ret = o2hb_read_slots(reg, reg->hr_blocks);
-	if (ret) {
-		mlog_errno(ret);
+	if (ret)
 		goto out;
-	}
 
 	/* We only want to get an idea of the values initially in each
 	 * slot, so we do no verification - o2hb_check_slot will
@@ -1712,10 +1678,11 @@ out:
 }
 
 /* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */
-static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_dev_store(struct config_item *item,
 				     const char *page,
 				     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	struct task_struct *hb_task;
 	long fd;
 	int sectsize;
@@ -1829,7 +1796,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	spin_unlock(&o2hb_live_lock);
 
 	ret = wait_event_interruptible(o2hb_steady_queue,
-				atomic_read(&reg->hr_steady_iterations) == 0);
+				atomic_read(&reg->hr_steady_iterations) == 0 ||
+				reg->hr_node_deleted);
 	if (ret) {
 		atomic_set(&reg->hr_steady_iterations, 0);
 		reg->hr_aborted_start = 1;
@@ -1840,6 +1808,11 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		goto out3;
 	}
 
+	if (reg->hr_node_deleted) {
+		ret = -EINVAL;
+		goto out3;
+	}
+
 	/* Ok, we were woken.  Make sure it wasn't by drop_item() */
 	spin_lock(&o2hb_live_lock);
 	hb_task = reg->hr_task;
@@ -1870,9 +1843,9 @@ out:
 	return ret;
 }
 
-static ssize_t o2hb_region_pid_read(struct o2hb_region *reg,
-                                      char *page)
+static ssize_t o2hb_region_pid_show(struct config_item *item, char *page)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	pid_t pid = 0;
 
 	spin_lock(&o2hb_live_lock);
@@ -1886,92 +1859,23 @@ static ssize_t o2hb_region_pid_read(struct o2hb_region *reg,
 	return sprintf(page, "%u\n", pid);
 }
 
-struct o2hb_region_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2hb_region *, char *);
-	ssize_t (*store)(struct o2hb_region *, const char *, size_t);
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_block_bytes = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "block_bytes",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_block_bytes_read,
-	.store	= o2hb_region_block_bytes_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_start_block = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "start_block",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_start_block_read,
-	.store	= o2hb_region_start_block_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_blocks = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "blocks",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_blocks_read,
-	.store	= o2hb_region_blocks_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_dev = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "dev",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_dev_read,
-	.store	= o2hb_region_dev_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_pid = {
-       .attr   = { .ca_owner = THIS_MODULE,
-                   .ca_name = "pid",
-                   .ca_mode = S_IRUGO | S_IRUSR },
-       .show   = o2hb_region_pid_read,
-};
+CONFIGFS_ATTR(o2hb_region_, block_bytes);
+CONFIGFS_ATTR(o2hb_region_, start_block);
+CONFIGFS_ATTR(o2hb_region_, blocks);
+CONFIGFS_ATTR(o2hb_region_, dev);
+CONFIGFS_ATTR_RO(o2hb_region_, pid);
 
 static struct configfs_attribute *o2hb_region_attrs[] = {
-	&o2hb_region_attr_block_bytes.attr,
-	&o2hb_region_attr_start_block.attr,
-	&o2hb_region_attr_blocks.attr,
-	&o2hb_region_attr_dev.attr,
-	&o2hb_region_attr_pid.attr,
+	&o2hb_region_attr_block_bytes,
+	&o2hb_region_attr_start_block,
+	&o2hb_region_attr_blocks,
+	&o2hb_region_attr_dev,
+	&o2hb_region_attr_pid,
 	NULL,
 };
 
-static ssize_t o2hb_region_show(struct config_item *item,
-				struct configfs_attribute *attr,
-				char *page)
-{
-	struct o2hb_region *reg = to_o2hb_region(item);
-	struct o2hb_region_attribute *o2hb_region_attr =
-		container_of(attr, struct o2hb_region_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2hb_region_attr->show)
-		ret = o2hb_region_attr->show(reg, page);
-	return ret;
-}
-
-static ssize_t o2hb_region_store(struct config_item *item,
-				 struct configfs_attribute *attr,
-				 const char *page, size_t count)
-{
-	struct o2hb_region *reg = to_o2hb_region(item);
-	struct o2hb_region_attribute *o2hb_region_attr =
-		container_of(attr, struct o2hb_region_attribute, attr);
-	ssize_t ret = -EINVAL;
-
-	if (o2hb_region_attr->store)
-		ret = o2hb_region_attr->store(reg, page, count);
-	return ret;
-}
-
 static struct configfs_item_operations o2hb_region_item_ops = {
 	.release		= o2hb_region_release,
-	.show_attribute		= o2hb_region_show,
-	.store_attribute	= o2hb_region_store,
 };
 
 static struct config_item_type o2hb_region_type = {
@@ -2166,49 +2070,14 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-struct o2hb_heartbeat_group_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2hb_heartbeat_group *, char *);
-	ssize_t (*store)(struct o2hb_heartbeat_group *, const char *, size_t);
-};
-
-static ssize_t o2hb_heartbeat_group_show(struct config_item *item,
-					 struct configfs_attribute *attr,
-					 char *page)
-{
-	struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item));
-	struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr =
-		container_of(attr, struct o2hb_heartbeat_group_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2hb_heartbeat_group_attr->show)
-		ret = o2hb_heartbeat_group_attr->show(reg, page);
-	return ret;
-}
-
-static ssize_t o2hb_heartbeat_group_store(struct config_item *item,
-					  struct configfs_attribute *attr,
-					  const char *page, size_t count)
-{
-	struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item));
-	struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr =
-		container_of(attr, struct o2hb_heartbeat_group_attribute, attr);
-	ssize_t ret = -EINVAL;
-
-	if (o2hb_heartbeat_group_attr->store)
-		ret = o2hb_heartbeat_group_attr->store(reg, page, count);
-	return ret;
-}
-
-static ssize_t o2hb_heartbeat_group_threshold_show(struct o2hb_heartbeat_group *group,
-						     char *page)
+static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group *group,
-						    const char *page,
-						    size_t count)
+static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+		const char *page, size_t count)
 {
 	unsigned long tmp;
 	char *p = (char *)page;
@@ -2223,17 +2092,15 @@ static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group
 	return count;
 }
 
-static
-ssize_t o2hb_heartbeat_group_mode_show(struct o2hb_heartbeat_group *group,
-				       char *page)
+static ssize_t o2hb_heartbeat_group_mode_show(struct config_item *item,
+		char *page)
 {
 	return sprintf(page, "%s\n",
 		       o2hb_heartbeat_mode_desc[o2hb_heartbeat_mode]);
 }
 
-static
-ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
-					const char *page, size_t count)
+static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
+		const char *page, size_t count)
 {
 	unsigned int i;
 	int ret;
@@ -2258,33 +2125,15 @@ ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
 
 }
 
-static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_threshold = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "dead_threshold",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_heartbeat_group_threshold_show,
-	.store	= o2hb_heartbeat_group_threshold_store,
-};
-
-static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_mode = {
-	.attr   = { .ca_owner = THIS_MODULE,
-		.ca_name = "mode",
-		.ca_mode = S_IRUGO | S_IWUSR },
-	.show   = o2hb_heartbeat_group_mode_show,
-	.store  = o2hb_heartbeat_group_mode_store,
-};
+CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold.attr,
-	&o2hb_heartbeat_group_attr_mode.attr,
+	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };
 
-static struct configfs_item_operations o2hb_heartbeat_group_item_ops = {
-	.show_attribute		= o2hb_heartbeat_group_show,
-	.store_attribute	= o2hb_heartbeat_group_store,
-};
-
 static struct configfs_group_operations o2hb_heartbeat_group_group_ops = {
 	.make_item	= o2hb_heartbeat_group_make_item,
 	.drop_item	= o2hb_heartbeat_group_drop_item,
@@ -2292,7 +2141,6 @@ static struct configfs_group_operations o2hb_heartbeat_group_group_ops = {
 
 static struct config_item_type o2hb_heartbeat_group_type = {
 	.ct_group_ops	= &o2hb_heartbeat_group_group_ops,
-	.ct_item_ops	= &o2hb_heartbeat_group_item_ops,
 	.ct_attrs	= o2hb_heartbeat_group_attrs,
 	.ct_owner	= THIS_MODULE,
 };
diff --git a/kernel/fs/ocfs2/cluster/masklog.c b/kernel/fs/ocfs2/cluster/masklog.c
index af7598bff..dfe162f5f 100644
--- a/kernel/fs/ocfs2/cluster/masklog.c
+++ b/kernel/fs/ocfs2/cluster/masklog.c
@@ -64,6 +64,40 @@ static ssize_t mlog_mask_store(u64 mask, const char *buf, size_t count)
 	return count;
 }
 
+void __mlog_printk(const u64 *mask, const char *func, int line,
+		   const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	const char *level;
+	const char *prefix = "";
+
+	if (!__mlog_test_u64(*mask, mlog_and_bits) ||
+	    __mlog_test_u64(*mask, mlog_not_bits))
+		return;
+
+	if (*mask & ML_ERROR) {
+		level = KERN_ERR;
+		prefix = "ERROR: ";
+	} else if (*mask & ML_NOTICE) {
+		level = KERN_NOTICE;
+	} else {
+		level = KERN_INFO;
+	}
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%s(%s,%u,%u):%s:%d %s%pV",
+	       level, current->comm, task_pid_nr(current),
+	       raw_smp_processor_id(), func, line, prefix, &vaf);
+
+	va_end(args);
+}
+EXPORT_SYMBOL_GPL(__mlog_printk);
+
 struct mlog_attribute {
 	struct attribute attr;
 	u64 mask;
diff --git a/kernel/fs/ocfs2/cluster/masklog.h b/kernel/fs/ocfs2/cluster/masklog.h
index 7fdc25a4d..308ea0eb3 100644
--- a/kernel/fs/ocfs2/cluster/masklog.h
+++ b/kernel/fs/ocfs2/cluster/masklog.h
@@ -162,38 +162,20 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 
 #endif
 
-/*
- * smp_processor_id() "helpfully" screams when called outside preemptible
- * regions in current kernels.  sles doesn't have the variants that don't
- * scream.  just do this instead of trying to guess which we're building
- * against.. *sigh*.
- */
-#define __mlog_cpu_guess ({		\
-	unsigned long _cpu = get_cpu();	\
-	put_cpu();			\
-	_cpu;				\
-})
+__printf(4, 5)
+void __mlog_printk(const u64 *m, const char *func, int line,
+		   const char *fmt, ...);
 
-/* In the following two macros, the whitespace after the ',' just
- * before ##args is intentional. Otherwise, gcc 2.95 will eat the
- * previous token if args expands to nothing.
+/*
+ * Testing before the __mlog_printk call lets the compiler eliminate the
+ * call completely when (m & ML_ALLOWED_BITS) is 0.
  */
-#define __mlog_printk(level, fmt, args...)				\
-	printk(level "(%s,%u,%lu):%s:%d " fmt, current->comm,		\
-	       task_pid_nr(current), __mlog_cpu_guess,			\
-	       __PRETTY_FUNCTION__, __LINE__ , ##args)
-
-#define mlog(mask, fmt, args...) do {					\
-	u64 __m = MLOG_MASK_PREFIX | (mask);				\
-	if ((__m & ML_ALLOWED_BITS) &&					\
-	    __mlog_test_u64(__m, mlog_and_bits) &&			\
-	    !__mlog_test_u64(__m, mlog_not_bits)) {			\
-		if (__m & ML_ERROR)					\
-			__mlog_printk(KERN_ERR, "ERROR: "fmt , ##args);	\
-		else if (__m & ML_NOTICE)				\
-			__mlog_printk(KERN_NOTICE, fmt , ##args);	\
-		else __mlog_printk(KERN_INFO, fmt , ##args);		\
-	}								\
+#define mlog(mask, fmt, ...)						\
+do {									\
+	u64 _m = MLOG_MASK_PREFIX | (mask);				\
+	if (_m & ML_ALLOWED_BITS)					\
+		__mlog_printk(&_m, __func__, __LINE__, fmt,		\
+			      ##__VA_ARGS__);				\
 } while (0)
 
 #define mlog_errno(st) ({						\
diff --git a/kernel/fs/ocfs2/cluster/nodemanager.c b/kernel/fs/ocfs2/cluster/nodemanager.c
index 441c84e16..72afdca3c 100644
--- a/kernel/fs/ocfs2/cluster/nodemanager.c
+++ b/kernel/fs/ocfs2/cluster/nodemanager.c
@@ -172,9 +172,9 @@ static void o2nm_node_release(struct config_item *item)
 	kfree(node);
 }
 
-static ssize_t o2nm_node_num_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_num_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", node->nd_num);
+	return sprintf(page, "%d\n", to_o2nm_node(item)->nd_num);
 }
 
 static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node)
@@ -188,15 +188,16 @@ enum {
 	O2NM_NODE_ATTR_NUM = 0,
 	O2NM_NODE_ATTR_PORT,
 	O2NM_NODE_ATTR_ADDRESS,
-	O2NM_NODE_ATTR_LOCAL,
 };
 
-static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page,
+static ssize_t o2nm_node_num_store(struct config_item *item, const char *page,
 				   size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	unsigned long tmp;
 	char *p = (char *)page;
+	int ret = 0;
 
 	tmp = simple_strtoul(p, &p, 0);
 	if (!p || (*p && (*p != '\n')))
@@ -215,26 +216,30 @@ static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page,
 
 	write_lock(&cluster->cl_nodes_lock);
 	if (cluster->cl_nodes[tmp])
-		p = NULL;
+		ret = -EEXIST;
+	else if (test_and_set_bit(O2NM_NODE_ATTR_NUM,
+			&node->nd_set_attributes))
+		ret = -EBUSY;
 	else  {
 		cluster->cl_nodes[tmp] = node;
 		node->nd_num = tmp;
 		set_bit(tmp, cluster->cl_nodes_bitmap);
 	}
 	write_unlock(&cluster->cl_nodes_lock);
-	if (p == NULL)
-		return -EEXIST;
+	if (ret)
+		return ret;
 
 	return count;
 }
-static ssize_t o2nm_node_ipv4_port_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_ipv4_port_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", ntohs(node->nd_ipv4_port));
+	return sprintf(page, "%u\n", ntohs(to_o2nm_node(item)->nd_ipv4_port));
 }
 
-static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node,
+static ssize_t o2nm_node_ipv4_port_store(struct config_item *item,
 					 const char *page, size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	unsigned long tmp;
 	char *p = (char *)page;
 
@@ -247,20 +252,23 @@ static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node,
 	if (tmp >= (u16)-1)
 		return -ERANGE;
 
+	if (test_and_set_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
+		return -EBUSY;
 	node->nd_ipv4_port = htons(tmp);
 
 	return count;
 }
 
-static ssize_t o2nm_node_ipv4_address_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_ipv4_address_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%pI4\n", &node->nd_ipv4_address);
+	return sprintf(page, "%pI4\n", &to_o2nm_node(item)->nd_ipv4_address);
 }
 
-static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
+static ssize_t o2nm_node_ipv4_address_store(struct config_item *item,
 					    const char *page,
 					    size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	int ret, i;
 	struct rb_node **p, *parent;
@@ -282,6 +290,9 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
 	write_lock(&cluster->cl_nodes_lock);
 	if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent))
 		ret = -EEXIST;
+	else if (test_and_set_bit(O2NM_NODE_ATTR_ADDRESS,
+			&node->nd_set_attributes))
+		ret = -EBUSY;
 	else {
 		rb_link_node(&node->nd_ip_node, parent, p);
 		rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree);
@@ -295,14 +306,15 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
 	return count;
 }
 
-static ssize_t o2nm_node_local_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_local_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", node->nd_local);
+	return sprintf(page, "%d\n", to_o2nm_node(item)->nd_local);
 }
 
-static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page,
+static ssize_t o2nm_node_local_store(struct config_item *item, const char *page,
 				     size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	unsigned long tmp;
 	char *p = (char *)page;
@@ -349,108 +361,21 @@ static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page,
 	return count;
 }
 
-struct o2nm_node_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2nm_node *, char *);
-	ssize_t (*store)(struct o2nm_node *, const char *, size_t);
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_num = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "num",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_num_read,
-	.store	= o2nm_node_num_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_ipv4_port = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "ipv4_port",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_ipv4_port_read,
-	.store	= o2nm_node_ipv4_port_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_ipv4_address = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "ipv4_address",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_ipv4_address_read,
-	.store	= o2nm_node_ipv4_address_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_local = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "local",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_local_read,
-	.store	= o2nm_node_local_write,
-};
+CONFIGFS_ATTR(o2nm_node_, num);
+CONFIGFS_ATTR(o2nm_node_, ipv4_port);
+CONFIGFS_ATTR(o2nm_node_, ipv4_address);
+CONFIGFS_ATTR(o2nm_node_, local);
 
 static struct configfs_attribute *o2nm_node_attrs[] = {
-	[O2NM_NODE_ATTR_NUM] = &o2nm_node_attr_num.attr,
-	[O2NM_NODE_ATTR_PORT] = &o2nm_node_attr_ipv4_port.attr,
-	[O2NM_NODE_ATTR_ADDRESS] = &o2nm_node_attr_ipv4_address.attr,
-	[O2NM_NODE_ATTR_LOCAL] = &o2nm_node_attr_local.attr,
+	&o2nm_node_attr_num,
+	&o2nm_node_attr_ipv4_port,
+	&o2nm_node_attr_ipv4_address,
+	&o2nm_node_attr_local,
 	NULL,
 };
 
-static int o2nm_attr_index(struct configfs_attribute *attr)
-{
-	int i;
-	for (i = 0; i < ARRAY_SIZE(o2nm_node_attrs); i++) {
-		if (attr == o2nm_node_attrs[i])
-			return i;
-	}
-	BUG();
-	return 0;
-}
-
-static ssize_t o2nm_node_show(struct config_item *item,
-			      struct configfs_attribute *attr,
-			      char *page)
-{
-	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_node_attribute *o2nm_node_attr =
-		container_of(attr, struct o2nm_node_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2nm_node_attr->show)
-		ret = o2nm_node_attr->show(node, page);
-	return ret;
-}
-
-static ssize_t o2nm_node_store(struct config_item *item,
-			       struct configfs_attribute *attr,
-			       const char *page, size_t count)
-{
-	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_node_attribute *o2nm_node_attr =
-		container_of(attr, struct o2nm_node_attribute, attr);
-	ssize_t ret;
-	int attr_index = o2nm_attr_index(attr);
-
-	if (o2nm_node_attr->store == NULL) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (test_bit(attr_index, &node->nd_set_attributes))
-		return -EBUSY;
-
-	ret = o2nm_node_attr->store(node, page, count);
-	if (ret < count)
-		goto out;
-
-	set_bit(attr_index, &node->nd_set_attributes);
-out:
-	return ret;
-}
-
 static struct configfs_item_operations o2nm_node_item_ops = {
 	.release		= o2nm_node_release,
-	.show_attribute		= o2nm_node_show,
-	.store_attribute	= o2nm_node_store,
 };
 
 static struct config_item_type o2nm_node_type = {
@@ -475,12 +400,6 @@ static struct o2nm_node_group *to_o2nm_node_group(struct config_group *group)
 }
 #endif
 
-struct o2nm_cluster_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2nm_cluster *, char *);
-	ssize_t (*store)(struct o2nm_cluster *, const char *, size_t);
-};
-
 static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count,
                                        unsigned int *val)
 {
@@ -501,15 +420,16 @@ static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count,
 	return count;
 }
 
-static ssize_t o2nm_cluster_attr_idle_timeout_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_idle_timeout_ms_show(struct config_item *item,
+	char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_idle_timeout_ms);
+	return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_idle_timeout_ms);
 }
 
-static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_idle_timeout_ms_store(struct config_item *item,
+	const char *page, size_t count)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret;
 	unsigned int val;
 
@@ -536,15 +456,17 @@ static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_keepalive_delay_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_keepalive_delay_ms_show(
+	struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_keepalive_delay_ms);
+	return sprintf(page, "%u\n",
+			to_o2nm_cluster(item)->cl_keepalive_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_keepalive_delay_ms_store(
+	struct config_item *item, const char *page, size_t count)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret;
 	unsigned int val;
 
@@ -571,22 +493,24 @@ static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_reconnect_delay_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_reconnect_delay_ms_show(
+	struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_reconnect_delay_ms);
+	return sprintf(page, "%u\n",
+			to_o2nm_cluster(item)->cl_reconnect_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_reconnect_delay_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_reconnect_delay_ms_store(
+	struct config_item *item, const char *page, size_t count)
 {
 	return o2nm_cluster_attr_write(page, count,
-	                               &cluster->cl_reconnect_delay_ms);
+                               &to_o2nm_cluster(item)->cl_reconnect_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_fence_method_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_fence_method_show(
+	struct config_item *item, char *page)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret = 0;
 
 	if (cluster)
@@ -595,8 +519,8 @@ static ssize_t o2nm_cluster_attr_fence_method_read(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_fence_method_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_fence_method_store(
+	struct config_item *item, const char *page, size_t count)
 {
 	unsigned int i;
 
@@ -608,10 +532,10 @@ static ssize_t o2nm_cluster_attr_fence_method_write(
 			continue;
 		if (strncasecmp(page, o2nm_fence_method_desc[i], count - 1))
 			continue;
-		if (cluster->cl_fence_method != i) {
+		if (to_o2nm_cluster(item)->cl_fence_method != i) {
 			printk(KERN_INFO "ocfs2: Changing fence method to %s\n",
 			       o2nm_fence_method_desc[i]);
-			cluster->cl_fence_method = i;
+			to_o2nm_cluster(item)->cl_fence_method = i;
 		}
 		return count;
 	}
@@ -620,79 +544,18 @@ bail:
 	return -EINVAL;
 }
 
-static struct o2nm_cluster_attribute o2nm_cluster_attr_idle_timeout_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "idle_timeout_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_idle_timeout_ms_read,
-	.store	= o2nm_cluster_attr_idle_timeout_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_keepalive_delay_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "keepalive_delay_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_keepalive_delay_ms_read,
-	.store	= o2nm_cluster_attr_keepalive_delay_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_reconnect_delay_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "reconnect_delay_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_reconnect_delay_ms_read,
-	.store	= o2nm_cluster_attr_reconnect_delay_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_fence_method = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "fence_method",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_fence_method_read,
-	.store	= o2nm_cluster_attr_fence_method_write,
-};
+CONFIGFS_ATTR(o2nm_cluster_, idle_timeout_ms);
+CONFIGFS_ATTR(o2nm_cluster_, keepalive_delay_ms);
+CONFIGFS_ATTR(o2nm_cluster_, reconnect_delay_ms);
+CONFIGFS_ATTR(o2nm_cluster_, fence_method);
 
 static struct configfs_attribute *o2nm_cluster_attrs[] = {
-	&o2nm_cluster_attr_idle_timeout_ms.attr,
-	&o2nm_cluster_attr_keepalive_delay_ms.attr,
-	&o2nm_cluster_attr_reconnect_delay_ms.attr,
-	&o2nm_cluster_attr_fence_method.attr,
+	&o2nm_cluster_attr_idle_timeout_ms,
+	&o2nm_cluster_attr_keepalive_delay_ms,
+	&o2nm_cluster_attr_reconnect_delay_ms,
+	&o2nm_cluster_attr_fence_method,
 	NULL,
 };
-static ssize_t o2nm_cluster_show(struct config_item *item,
-                                 struct configfs_attribute *attr,
-                                 char *page)
-{
-	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	struct o2nm_cluster_attribute *o2nm_cluster_attr =
-		container_of(attr, struct o2nm_cluster_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2nm_cluster_attr->show)
-		ret = o2nm_cluster_attr->show(cluster, page);
-	return ret;
-}
-
-static ssize_t o2nm_cluster_store(struct config_item *item,
-                                  struct configfs_attribute *attr,
-                                  const char *page, size_t count)
-{
-	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	struct o2nm_cluster_attribute *o2nm_cluster_attr =
-		container_of(attr, struct o2nm_cluster_attribute, attr);
-	ssize_t ret;
-
-	if (o2nm_cluster_attr->store == NULL) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = o2nm_cluster_attr->store(cluster, page, count);
-	if (ret < count)
-		goto out;
-out:
-	return ret;
-}
 
 static struct config_item *o2nm_node_group_make_item(struct config_group *group,
 						     const char *name)
@@ -773,8 +636,6 @@ static void o2nm_cluster_release(struct config_item *item)
 
 static struct configfs_item_operations o2nm_cluster_item_ops = {
 	.release	= o2nm_cluster_release,
-	.show_attribute		= o2nm_cluster_show,
-	.store_attribute	= o2nm_cluster_store,
 };
 
 static struct config_item_type o2nm_cluster_type = {
diff --git a/kernel/fs/ocfs2/cluster/tcp.c b/kernel/fs/ocfs2/cluster/tcp.c
index 56c403a56..2d0acd667 100644
--- a/kernel/fs/ocfs2/cluster/tcp.c
+++ b/kernel/fs/ocfs2/cluster/tcp.c
@@ -2204,7 +2204,7 @@ out:
 	kfree(o2net_hand);
 	kfree(o2net_keep_req);
 	kfree(o2net_keep_resp);
-
+	o2net_debugfs_exit();
 	o2quo_exit();
 	return -ENOMEM;
 }
diff --git a/kernel/fs/ocfs2/dir.c b/kernel/fs/ocfs2/dir.c
index ccd4dcfc3..ffecf89c8 100644
--- a/kernel/fs/ocfs2/dir.c
+++ b/kernel/fs/ocfs2/dir.c
@@ -480,33 +480,26 @@ static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh)
 
 	trailer = ocfs2_trailer_from_bh(bh, dir->i_sb);
 	if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
-		rc = -EINVAL;
-		ocfs2_error(dir->i_sb,
-			    "Invalid dirblock #%llu: "
-			    "signature = %.*s\n",
-			    (unsigned long long)bh->b_blocknr, 7,
-			    trailer->db_signature);
+		rc = ocfs2_error(dir->i_sb,
+				 "Invalid dirblock #%llu: signature = %.*s\n",
+				 (unsigned long long)bh->b_blocknr, 7,
+				 trailer->db_signature);
 		goto out;
 	}
 	if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) {
-		rc = -EINVAL;
-		ocfs2_error(dir->i_sb,
-			    "Directory block #%llu has an invalid "
-			    "db_blkno of %llu",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		rc = ocfs2_error(dir->i_sb,
+				 "Directory block #%llu has an invalid db_blkno of %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 (unsigned long long)le64_to_cpu(trailer->db_blkno));
 		goto out;
 	}
 	if (le64_to_cpu(trailer->db_parent_dinode) !=
 	    OCFS2_I(dir)->ip_blkno) {
-		rc = -EINVAL;
-		ocfs2_error(dir->i_sb,
-			    "Directory block #%llu on dinode "
-			    "#%llu has an invalid parent_dinode "
-			    "of %llu",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)OCFS2_I(dir)->ip_blkno,
-			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		rc = ocfs2_error(dir->i_sb,
+				 "Directory block #%llu on dinode #%llu has an invalid parent_dinode of %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 (unsigned long long)OCFS2_I(dir)->ip_blkno,
+				 (unsigned long long)le64_to_cpu(trailer->db_blkno));
 		goto out;
 	}
 out:
@@ -604,14 +597,13 @@ static int ocfs2_validate_dx_root(struct super_block *sb,
 	}
 
 	if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) {
-		ocfs2_error(sb,
-			    "Dir Index Root # %llu has bad signature %.*s",
-			    (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
-			    7, dx_root->dr_signature);
-		return -EINVAL;
+		ret = ocfs2_error(sb,
+				  "Dir Index Root # %llu has bad signature %.*s\n",
+				  (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
+				  7, dx_root->dr_signature);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di,
@@ -648,12 +640,11 @@ static int ocfs2_validate_dx_leaf(struct super_block *sb,
 	}
 
 	if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) {
-		ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s",
-			    7, dx_leaf->dl_signature);
-		return -EROFS;
+		ret = ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s\n",
+				  7, dx_leaf->dl_signature);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno,
@@ -812,11 +803,10 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
 		el = &eb->h_list;
 
 		if (el->l_tree_depth) {
-			ocfs2_error(inode->i_sb,
-				    "Inode %lu has non zero tree depth in "
-				    "btree tree block %llu\n", inode->i_ino,
-				    (unsigned long long)eb_bh->b_blocknr);
-			ret = -EROFS;
+			ret = ocfs2_error(inode->i_sb,
+					  "Inode %lu has non zero tree depth in btree tree block %llu\n",
+					  inode->i_ino,
+					  (unsigned long long)eb_bh->b_blocknr);
 			goto out;
 		}
 	}
@@ -832,11 +822,11 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
 	}
 
 	if (!found) {
-		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-			    "record (%u, %u, 0) in btree", inode->i_ino,
-			    le32_to_cpu(rec->e_cpos),
-			    ocfs2_rec_clusters(el, rec));
-		ret = -EROFS;
+		ret = ocfs2_error(inode->i_sb,
+				  "Inode %lu has bad extent record (%u, %u, 0) in btree\n",
+				  inode->i_ino,
+				  le32_to_cpu(rec->e_cpos),
+				  ocfs2_rec_clusters(el, rec));
 		goto out;
 	}
 
@@ -1617,7 +1607,7 @@ int __ocfs2_add_entry(handle_t *handle,
 	struct ocfs2_dir_entry *de, *de1;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data;
 	struct super_block *sb = dir->i_sb;
-	int retval, status;
+	int retval;
 	unsigned int size = sb->s_blocksize;
 	struct buffer_head *insert_bh = lookup->dl_leaf_bh;
 	char *data_start = insert_bh->b_data;
@@ -1695,25 +1685,25 @@ int __ocfs2_add_entry(handle_t *handle,
 			}
 
 			if (insert_bh == parent_fe_bh)
-				status = ocfs2_journal_access_di(handle,
+				retval = ocfs2_journal_access_di(handle,
 								 INODE_CACHE(dir),
 								 insert_bh,
 								 OCFS2_JOURNAL_ACCESS_WRITE);
 			else {
-				status = ocfs2_journal_access_db(handle,
+				retval = ocfs2_journal_access_db(handle,
 								 INODE_CACHE(dir),
 								 insert_bh,
 					      OCFS2_JOURNAL_ACCESS_WRITE);
 
-				if (ocfs2_dir_indexed(dir)) {
-					status = ocfs2_dx_dir_insert(dir,
+				if (!retval && ocfs2_dir_indexed(dir))
+					retval = ocfs2_dx_dir_insert(dir,
 								handle,
 								lookup);
-					if (status) {
-						mlog_errno(status);
-						goto bail;
-					}
-				}
+			}
+
+			if (retval) {
+				mlog_errno(retval);
+				goto bail;
 			}
 
 			/* By now the buffer is marked for journaling */
@@ -3543,13 +3533,10 @@ static void dx_leaf_sort_swap(void *a, void *b, int size)
 {
 	struct ocfs2_dx_entry *entry1 = a;
 	struct ocfs2_dx_entry *entry2 = b;
-	struct ocfs2_dx_entry tmp;
 
 	BUG_ON(size != sizeof(*entry1));
 
-	tmp = *entry1;
-	*entry1 = *entry2;
-	*entry2 = tmp;
+	swap(*entry1, *entry2);
 }
 
 static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf)
diff --git a/kernel/fs/ocfs2/dlm/dlmcommon.h b/kernel/fs/ocfs2/dlm/dlmcommon.h
index fae17c640..e88ccf8c8 100644
--- a/kernel/fs/ocfs2/dlm/dlmcommon.h
+++ b/kernel/fs/ocfs2/dlm/dlmcommon.h
@@ -1014,7 +1014,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 
 /* will exit holding res->spinlock, but may drop in function */
 void __dlm_wait_on_lockres_flags(struct dlm_lock_resource *res, int flags);
-void __dlm_wait_on_lockres_flags_set(struct dlm_lock_resource *res, int flags);
 
 /* will exit holding res->spinlock, but may drop in function */
 static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
diff --git a/kernel/fs/ocfs2/dlm/dlmdomain.c b/kernel/fs/ocfs2/dlm/dlmdomain.c
index 7df88a6dd..2ee7fe747 100644
--- a/kernel/fs/ocfs2/dlm/dlmdomain.c
+++ b/kernel/fs/ocfs2/dlm/dlmdomain.c
@@ -1465,39 +1465,46 @@ static int dlm_request_join(struct dlm_ctxt *dlm,
 	if (status == -ENOPROTOOPT) {
 		status = 0;
 		*response = JOIN_OK_NO_MAP;
-	} else if (packet.code == JOIN_DISALLOW ||
-		   packet.code == JOIN_OK_NO_MAP) {
-		*response = packet.code;
-	} else if (packet.code == JOIN_PROTOCOL_MISMATCH) {
-		mlog(ML_NOTICE,
-		     "This node requested DLM locking protocol %u.%u and "
-		     "filesystem locking protocol %u.%u.  At least one of "
-		     "the protocol versions on node %d is not compatible, "
-		     "disconnecting\n",
-		     dlm->dlm_locking_proto.pv_major,
-		     dlm->dlm_locking_proto.pv_minor,
-		     dlm->fs_locking_proto.pv_major,
-		     dlm->fs_locking_proto.pv_minor,
-		     node);
-		status = -EPROTO;
-		*response = packet.code;
-	} else if (packet.code == JOIN_OK) {
-		*response = packet.code;
-		/* Use the same locking protocol as the remote node */
-		dlm->dlm_locking_proto.pv_minor = packet.dlm_minor;
-		dlm->fs_locking_proto.pv_minor = packet.fs_minor;
-		mlog(0,
-		     "Node %d responds JOIN_OK with DLM locking protocol "
-		     "%u.%u and fs locking protocol %u.%u\n",
-		     node,
-		     dlm->dlm_locking_proto.pv_major,
-		     dlm->dlm_locking_proto.pv_minor,
-		     dlm->fs_locking_proto.pv_major,
-		     dlm->fs_locking_proto.pv_minor);
 	} else {
-		status = -EINVAL;
-		mlog(ML_ERROR, "invalid response %d from node %u\n",
-		     packet.code, node);
+		*response = packet.code;
+		switch (packet.code) {
+		case JOIN_DISALLOW:
+		case JOIN_OK_NO_MAP:
+			break;
+		case JOIN_PROTOCOL_MISMATCH:
+			mlog(ML_NOTICE,
+			     "This node requested DLM locking protocol %u.%u and "
+			     "filesystem locking protocol %u.%u.  At least one of "
+			     "the protocol versions on node %d is not compatible, "
+			     "disconnecting\n",
+			     dlm->dlm_locking_proto.pv_major,
+			     dlm->dlm_locking_proto.pv_minor,
+			     dlm->fs_locking_proto.pv_major,
+			     dlm->fs_locking_proto.pv_minor,
+			     node);
+			status = -EPROTO;
+			break;
+		case JOIN_OK:
+			/* Use the same locking protocol as the remote node */
+			dlm->dlm_locking_proto.pv_minor = packet.dlm_minor;
+			dlm->fs_locking_proto.pv_minor = packet.fs_minor;
+			mlog(0,
+			     "Node %d responds JOIN_OK with DLM locking protocol "
+			     "%u.%u and fs locking protocol %u.%u\n",
+			     node,
+			     dlm->dlm_locking_proto.pv_major,
+			     dlm->dlm_locking_proto.pv_minor,
+			     dlm->fs_locking_proto.pv_major,
+			     dlm->fs_locking_proto.pv_minor);
+			break;
+		default:
+			status = -EINVAL;
+			mlog(ML_ERROR, "invalid response %d from node %u\n",
+			     packet.code, node);
+			/* Reset response to JOIN_DISALLOW */
+			*response = JOIN_DISALLOW;
+			break;
+		}
 	}
 
 	mlog(0, "status %d, node %d response is %d\n", status, node,
@@ -1725,12 +1732,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 
 	o2hb_setup_callback(&dlm->dlm_hb_down, O2HB_NODE_DOWN_CB,
 			    dlm_hb_node_down_cb, dlm, DLM_HB_NODE_DOWN_PRI);
+	o2hb_setup_callback(&dlm->dlm_hb_up, O2HB_NODE_UP_CB,
+			    dlm_hb_node_up_cb, dlm, DLM_HB_NODE_UP_PRI);
+
 	status = o2hb_register_callback(dlm->name, &dlm->dlm_hb_down);
 	if (status)
 		goto bail;
 
-	o2hb_setup_callback(&dlm->dlm_hb_up, O2HB_NODE_UP_CB,
-			    dlm_hb_node_up_cb, dlm, DLM_HB_NODE_UP_PRI);
 	status = o2hb_register_callback(dlm->name, &dlm->dlm_hb_up);
 	if (status)
 		goto bail;
@@ -1845,8 +1853,6 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 					sizeof(struct dlm_exit_domain),
 					dlm_begin_exit_domain_handler,
 					dlm, NULL, &dlm->dlm_domain_handlers);
-	if (status)
-		goto bail;
 
 bail:
 	if (status)
@@ -1860,6 +1866,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 	int status;
 	unsigned int backoff;
 	unsigned int total_backoff = 0;
+	char wq_name[O2NM_MAX_NAME_LEN];
 
 	BUG_ON(!dlm);
 
@@ -1889,7 +1896,8 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
-	dlm->dlm_worker = create_singlethread_workqueue("dlm_wq");
+	snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name);
+	dlm->dlm_worker = create_singlethread_workqueue(wq_name);
 	if (!dlm->dlm_worker) {
 		status = -ENOMEM;
 		mlog_errno(status);
diff --git a/kernel/fs/ocfs2/dlm/dlmmaster.c b/kernel/fs/ocfs2/dlm/dlmmaster.c
index fdf4b41d0..4e2162b35 100644
--- a/kernel/fs/ocfs2/dlm/dlmmaster.c
+++ b/kernel/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -795,8 +785,18 @@ lookup:
 		dlm_lockres_grab_inflight_ref(dlm, tmpres);
 
 		spin_unlock(&tmpres->spinlock);
-		if (res)
+		if (res) {
+			spin_lock(&dlm->track_lock);
+			if (!list_empty(&res->tracking))
+				list_del_init(&res->tracking);
+			else
+				mlog(ML_ERROR, "Resource %.*s not "
+						"on the Tracking list\n",
+						res->lockname.len,
+						res->lockname.name);
+			spin_unlock(&dlm->track_lock);
 			dlm_lockres_put(res);
+		}
 		res = tmpres;
 		goto leave;
 	}
@@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int found, ret;
 	int set_maybe;
 	int dispatch_assert = 0;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm))
 		return DLM_MASTER_RESP_NO;
@@ -1657,16 +1658,20 @@ send_response:
 		if (ret < 0) {
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
+			spin_unlock(&res->spinlock);
 			dlm_lockres_put(res);
-		} else
+		} else {
+			dispatched = 1;
 			__dlm_lockres_grab_inflight_worker(dlm, res);
-		spin_unlock(&res->spinlock);
+			spin_unlock(&res->spinlock);
+		}
 	} else {
 		if (res)
 			dlm_lockres_put(res);
 	}
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return response;
 }
 
@@ -2090,7 +2095,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 
 
 	/* queue up work for dlm_assert_master_worker */
-	dlm_grab(dlm);  /* get an extra ref for the work item */
 	dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL);
 	item->u.am.lockres = res; /* already have a ref */
 	/* can optionally ignore node numbers higher than this node */
@@ -2515,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	spin_lock(&dlm->master_lock);
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name,
 				    namelen, target, dlm->node_num);
+	/* get an extra reference on the mle.
+	 * otherwise the assert_master from the new
+	 * master will destroy this.
+	 */
+	dlm_get_mle_inuse(mle);
 	spin_unlock(&dlm->master_lock);
 	spin_unlock(&dlm->spinlock);
 
@@ -2550,6 +2559,7 @@ fail:
 		if (mle_added) {
 			dlm_mle_detach_hb_events(dlm, mle);
 			dlm_put_mle(mle);
+			dlm_put_mle_inuse(mle);
 		} else if (mle) {
 			kmem_cache_free(dlm_mle_cache, mle);
 			mle = NULL;
@@ -2567,17 +2577,6 @@ fail:
 	 * ensure that all assert_master work is flushed. */
 	flush_workqueue(dlm->dlm_worker);
 
-	/* get an extra reference on the mle.
-	 * otherwise the assert_master from the new
-	 * master will destroy this.
-	 * also, make sure that all callers of dlm_get_mle
-	 * take both dlm->spinlock and dlm->master_lock */
-	spin_lock(&dlm->spinlock);
-	spin_lock(&dlm->master_lock);
-	dlm_get_mle_inuse(mle);
-	spin_unlock(&dlm->master_lock);
-	spin_unlock(&dlm->spinlock);
-
 	/* notify new node and send all lock state */
 	/* call send_one_lockres with migration flag.
 	 * this serves as notice to the target node that a
@@ -2839,6 +2838,8 @@ again:
 	res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY;
 	if (!ret)
 		BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING));
+	else
+		res->migration_pending = 0;
 	spin_unlock(&res->spinlock);
 
 	/*
@@ -3306,6 +3307,15 @@ top:
 			    mle->new_master != dead_node)
 				continue;
 
+			if (mle->new_master == dead_node && mle->inuse) {
+				mlog(ML_NOTICE, "%s: target %u died during "
+						"migration from %u, the MLE is "
+						"still keep used, ignore it!\n",
+						dlm->name, dead_node,
+						mle->master);
+				continue;
+			}
+
 			/* If we have reached this point, this mle needs to be
 			 * removed from the list and freed. */
 			dlm_clean_migration_mle(dlm, mle);
diff --git a/kernel/fs/ocfs2/dlm/dlmrecovery.c b/kernel/fs/ocfs2/dlm/dlmrecovery.c
index ce12e0b1a..42f0cae93 100644
--- a/kernel/fs/ocfs2/dlm/dlmrecovery.c
+++ b/kernel/fs/ocfs2/dlm/dlmrecovery.c
@@ -205,7 +205,7 @@ int dlm_launch_recovery_thread(struct dlm_ctxt *dlm)
 	mlog(0, "starting dlm recovery thread...\n");
 
 	dlm->dlm_reco_thread_task = kthread_run(dlm_recovery_thread, dlm,
-						"dlm_reco_thread");
+			"dlm_reco-%s", dlm->name);
 	if (IS_ERR(dlm->dlm_reco_thread_task)) {
 		mlog_errno(PTR_ERR(dlm->dlm_reco_thread_task));
 		dlm->dlm_reco_thread_task = NULL;
@@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	unsigned int hash;
 	int master = DLM_LOCK_RES_OWNER_UNKNOWN;
 	u32 flags = DLM_ASSERT_MASTER_REQUERY;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm)) {
 		/* since the domain has gone away on this
@@ -1719,9 +1720,11 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				dlm_put(dlm);
 				/* sender will take care of this and retry */
 				return ret;
-			} else
+			} else {
+				dispatched = 1;
 				__dlm_lockres_grab_inflight_worker(dlm, res);
-			spin_unlock(&res->spinlock);
+				spin_unlock(&res->spinlock);
+			}
 		} else {
 			/* put.. incase we are not the master */
 			spin_unlock(&res->spinlock);
@@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 	spin_unlock(&dlm->spinlock);
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return master;
 }
 
@@ -2356,6 +2360,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						break;
 					}
 				}
+				dlm_lockres_clear_refmap_bit(dlm, res,
+						dead_node);
 				spin_unlock(&res->spinlock);
 				continue;
 			}
diff --git a/kernel/fs/ocfs2/dlm/dlmthread.c b/kernel/fs/ocfs2/dlm/dlmthread.c
index 69aac6f08..c5f6c241e 100644
--- a/kernel/fs/ocfs2/dlm/dlmthread.c
+++ b/kernel/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
@@ -483,7 +493,8 @@ int dlm_launch_thread(struct dlm_ctxt *dlm)
 {
 	mlog(0, "Starting dlm_thread...\n");
 
-	dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm_thread");
+	dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm-%s",
+			dlm->name);
 	if (IS_ERR(dlm->dlm_thread_task)) {
 		mlog_errno(PTR_ERR(dlm->dlm_thread_task));
 		dlm->dlm_thread_task = NULL;
diff --git a/kernel/fs/ocfs2/dlmglue.c b/kernel/fs/ocfs2/dlmglue.c
index 23157e40d..b002acf50 100644
--- a/kernel/fs/ocfs2/dlmglue.c
+++ b/kernel/fs/ocfs2/dlmglue.c
@@ -1390,6 +1390,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
 	unsigned int gen;
 	int noqueue_attempted = 0;
 	int dlm_locked = 0;
+	int kick_dc = 0;
 
 	if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) {
 		mlog_errno(-EINVAL);
@@ -1524,7 +1525,12 @@ update_holders:
 unlock:
 	lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
 
+	/* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */
+	kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED);
+
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
+	if (kick_dc)
+		ocfs2_wake_downconvert_thread(osb);
 out:
 	/*
 	 * This is helping work around a lock inversion between the page lock
@@ -2998,7 +3004,8 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 	}
 
 	/* launch downconvert thread */
-	osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc");
+	osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s",
+			osb->uuid_str);
 	if (IS_ERR(osb->dc_task)) {
 		status = PTR_ERR(osb->dc_task);
 		osb->dc_task = NULL;
@@ -3035,8 +3042,6 @@ local:
 	ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb);
 
 	osb->cconn = conn;
-
-	status = 0;
 bail:
 	if (status < 0) {
 		ocfs2_dlm_shutdown_debug(osb);
diff --git a/kernel/fs/ocfs2/extent_map.c b/kernel/fs/ocfs2/extent_map.c
index 767370b65..e4719e0a3 100644
--- a/kernel/fs/ocfs2/extent_map.c
+++ b/kernel/fs/ocfs2/extent_map.c
@@ -305,8 +305,8 @@ static int ocfs2_last_eb_is_empty(struct inode *inode,
 
 	if (el->l_tree_depth) {
 		ocfs2_error(inode->i_sb,
-			    "Inode %lu has non zero tree depth in "
-			    "leaf block %llu\n", inode->i_ino,
+			    "Inode %lu has non zero tree depth in leaf block %llu\n",
+			    inode->i_ino,
 			    (unsigned long long)eb_bh->b_blocknr);
 		ret = -EROFS;
 		goto out;
@@ -441,8 +441,8 @@ static int ocfs2_get_clusters_nocache(struct inode *inode,
 
 		if (el->l_tree_depth) {
 			ocfs2_error(inode->i_sb,
-				    "Inode %lu has non zero tree depth in "
-				    "leaf block %llu\n", inode->i_ino,
+				    "Inode %lu has non zero tree depth in leaf block %llu\n",
+				    inode->i_ino,
 				    (unsigned long long)eb_bh->b_blocknr);
 			ret = -EROFS;
 			goto out;
@@ -475,8 +475,9 @@ static int ocfs2_get_clusters_nocache(struct inode *inode,
 	BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
 
 	if (!rec->e_blkno) {
-		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-			    "record (%u, %u, 0)", inode->i_ino,
+		ocfs2_error(inode->i_sb,
+			    "Inode %lu has bad extent record (%u, %u, 0)\n",
+			    inode->i_ino,
 			    le32_to_cpu(rec->e_cpos),
 			    ocfs2_rec_clusters(el, rec));
 		ret = -EROFS;
@@ -564,8 +565,8 @@ int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
 
 		if (el->l_tree_depth) {
 			ocfs2_error(inode->i_sb,
-				    "Inode %lu has non zero tree depth in "
-				    "xattr leaf block %llu\n", inode->i_ino,
+				    "Inode %lu has non zero tree depth in xattr leaf block %llu\n",
+				    inode->i_ino,
 				    (unsigned long long)eb_bh->b_blocknr);
 			ret = -EROFS;
 			goto out;
@@ -582,8 +583,9 @@ int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
 		BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
 
 		if (!rec->e_blkno) {
-			ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-				    "record (%u, %u, 0) in xattr", inode->i_ino,
+			ocfs2_error(inode->i_sb,
+				    "Inode %lu has bad extent record (%u, %u, 0) in xattr\n",
+				    inode->i_ino,
 				    le32_to_cpu(rec->e_cpos),
 				    ocfs2_rec_clusters(el, rec));
 			ret = -EROFS;
diff --git a/kernel/fs/ocfs2/file.c b/kernel/fs/ocfs2/file.c
index d8b670cbd..0e5b4515f 100644
--- a/kernel/fs/ocfs2/file.c
+++ b/kernel/fs/ocfs2/file.c
@@ -37,6 +37,7 @@
 #include <linux/falloc.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 
 #include <cluster/masklog.h>
 
@@ -104,8 +105,11 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name, mode);
 
-	if (file->f_mode & FMODE_WRITE)
-		dquot_initialize(inode);
+	if (file->f_mode & FMODE_WRITE) {
+		status = dquot_initialize(inode);
+		if (status)
+			goto leave;
+	}
 
 	spin_lock(&oi->ip_lock);
 
@@ -1126,6 +1130,7 @@ out:
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int status = 0, size_change;
+	int inode_locked = 0;
 	struct inode *inode = d_inode(dentry);
 	struct super_block *sb = inode->i_sb;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
@@ -1154,8 +1159,11 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	if (status)
 		return status;
 
-	if (is_quota_modification(inode, attr))
-		dquot_initialize(inode);
+	if (is_quota_modification(inode, attr)) {
+		status = dquot_initialize(inode);
+		if (status)
+			return status;
+	}
 	size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
 	if (size_change) {
 		status = ocfs2_rw_lock(inode, 1);
@@ -1171,6 +1179,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 			mlog_errno(status);
 		goto bail_unlock_rw;
 	}
+	inode_locked = 1;
 
 	if (size_change) {
 		status = inode_newsize_ok(inode, attr->ia_size);
@@ -1208,8 +1217,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		    && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
 		    OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
 			transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
-			if (!transfer_to[USRQUOTA]) {
-				status = -ESRCH;
+			if (IS_ERR(transfer_to[USRQUOTA])) {
+				status = PTR_ERR(transfer_to[USRQUOTA]);
 				goto bail_unlock;
 			}
 		}
@@ -1217,8 +1226,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		    && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
 		    OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) {
 			transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
-			if (!transfer_to[GRPQUOTA]) {
-				status = -ESRCH;
+			if (IS_ERR(transfer_to[GRPQUOTA])) {
+				status = PTR_ERR(transfer_to[GRPQUOTA]);
 				goto bail_unlock;
 			}
 		}
@@ -1251,7 +1260,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
 bail_unlock:
-	ocfs2_inode_unlock(inode, 1);
+	if (status) {
+		ocfs2_inode_unlock(inode, 1);
+		inode_locked = 0;
+	}
 bail_unlock_rw:
 	if (size_change)
 		ocfs2_rw_unlock(inode, 1);
@@ -1267,6 +1279,8 @@ bail:
 		if (status < 0)
 			mlog_errno(status);
 	}
+	if (inode_locked)
+		ocfs2_inode_unlock(inode, 1);
 
 	return status;
 }
@@ -2250,13 +2264,11 @@ out:
 static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
-	int direct_io, appending, rw_level, have_alloc_sem  = 0;
+	int direct_io, appending, rw_level;
 	int can_do_direct, has_refcount = 0;
 	ssize_t written = 0;
 	ssize_t ret;
 	size_t count = iov_iter_count(from), orig_count;
-	loff_t old_size;
-	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2264,6 +2276,8 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
 	int unaligned_dio = 0;
 	int dropped_dio = 0;
+	int append_write = ((iocb->ki_pos + count) >=
+			i_size_read(inode) ? 1 : 0);
 
 	trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2279,26 +2293,18 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	mutex_lock(&inode->i_mutex);
 
-	ocfs2_iocb_clear_sem_locked(iocb);
-
 relock:
-	/* to match setattr's i_mutex -> rw_lock ordering */
-	if (direct_io) {
-		have_alloc_sem = 1;
-		/* communicate with ocfs2_dio_end_io */
-		ocfs2_iocb_set_sem_locked(iocb);
-	}
-
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
+	 * For append write, we must take rw EX.
 	 */
-	rw_level = (!direct_io || full_coherency);
+	rw_level = (!direct_io || full_coherency || append_write);
 
 	ret = ocfs2_rw_lock(inode, rw_level);
 	if (ret < 0) {
 		mlog_errno(ret);
-		goto out_sems;
+		goto out_mutex;
 	}
 
 	/*
@@ -2347,7 +2353,6 @@ relock:
 	if (direct_io && !can_do_direct) {
 		ocfs2_rw_unlock(inode, rw_level);
 
-		have_alloc_sem = 0;
 		rw_level = -1;
 
 		direct_io = 0;
@@ -2367,13 +2372,6 @@ relock:
 		ocfs2_iocb_set_unaligned_aio(iocb);
 	}
 
-	/*
-	 * To later detect whether a journal commit for sync writes is
-	 * necessary, we sample i_size, and cluster count here.
-	 */
-	old_size = i_size_read(inode);
-	old_clusters = OCFS2_I(inode)->ip_clusters;
-
 	/* communicate with ocfs2_dio_end_io */
 	ocfs2_iocb_set_rw_locked(iocb, rw_level);
 
@@ -2381,6 +2379,20 @@ relock:
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
 
+	/*
+	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
+	 * function pointer which is called when o_direct io completes so that
+	 * it can unlock our rw lock.
+	 * Unfortunately there are error cases which call end_io and others
+	 * that don't.  so we don't have to unlock the rw_lock if either an
+	 * async dio is going to do it in the future or an end_io after an
+	 * error has already done it.
+	 */
+	if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
+		rw_level = -1;
+		unaligned_dio = 0;
+	}
+
 	if (unlikely(written <= 0))
 		goto no_sync;
 
@@ -2405,22 +2417,7 @@ relock:
 	}
 
 no_sync:
-	/*
-	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
-	 * function pointer which is called when o_direct io completes so that
-	 * it can unlock our rw lock.
-	 * Unfortunately there are error cases which call end_io and others
-	 * that don't.  so we don't have to unlock the rw_lock if either an
-	 * async dio is going to do it in the future or an end_io after an
-	 * error has already done it.
-	 */
-	if ((ret == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
-		rw_level = -1;
-		have_alloc_sem = 0;
-		unaligned_dio = 0;
-	}
-
-	if (unaligned_dio) {
+	if (unaligned_dio && ocfs2_iocb_is_unaligned_aio(iocb)) {
 		ocfs2_iocb_clear_unaligned_aio(iocb);
 		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
 	}
@@ -2429,10 +2426,7 @@ out:
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
-out_sems:
-	if (have_alloc_sem)
-		ocfs2_iocb_clear_sem_locked(iocb);
-
+out_mutex:
 	mutex_unlock(&inode->i_mutex);
 
 	if (written)
@@ -2473,7 +2467,7 @@ bail:
 static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 				   struct iov_iter *to)
 {
-	int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
+	int ret = 0, rw_level = -1, lock_level = 0;
 	struct file *filp = iocb->ki_filp;
 	struct inode *inode = file_inode(filp);
 
@@ -2490,16 +2484,11 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 		goto bail;
 	}
 
-	ocfs2_iocb_clear_sem_locked(iocb);
-
 	/*
 	 * buffered reads protect themselves in ->readpage().  O_DIRECT reads
 	 * need locks to protect pending reads from racing with truncate.
 	 */
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		have_alloc_sem = 1;
-		ocfs2_iocb_set_sem_locked(iocb);
-
 		ret = ocfs2_rw_lock(inode, 0);
 		if (ret < 0) {
 			mlog_errno(ret);
@@ -2535,13 +2524,9 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
 		rw_level = -1;
-		have_alloc_sem = 0;
 	}
 
 bail:
-	if (have_alloc_sem)
-		ocfs2_iocb_clear_sem_locked(iocb);
-
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
diff --git a/kernel/fs/ocfs2/inode.c b/kernel/fs/ocfs2/inode.c
index b254416dc..8f87e05ee 100644
--- a/kernel/fs/ocfs2/inode.c
+++ b/kernel/fs/ocfs2/inode.c
@@ -971,6 +971,7 @@ static void ocfs2_delete_inode(struct inode *inode)
 	int wipe, status;
 	sigset_t oldset;
 	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
 
 	trace_ocfs2_delete_inode(inode->i_ino,
 				 (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1025,6 +1026,14 @@ static void ocfs2_delete_inode(struct inode *inode)
 		goto bail_unlock_nfs_sync;
 	}
 
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	/* Skip inode deletion and wait for dio orphan entry recovered
+	 * first */
+	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+		ocfs2_cleanup_delete_inode(inode, 0);
+		goto bail_unlock_inode;
+	}
+
 	/* Query the cluster. This will be the final decision made
 	 * before we go ahead and wipe the inode. */
 	status = ocfs2_query_inode_wipe(inode, di_bh, &wipe);
@@ -1191,17 +1200,19 @@ void ocfs2_evict_inode(struct inode *inode)
 int ocfs2_drop_inode(struct inode *inode)
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	int res;
 
 	trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink, oi->ip_flags);
 
-	if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
-		res = 1;
-	else
-		res = generic_drop_inode(inode);
+	assert_spin_locked(&inode->i_lock);
+	inode->i_state |= I_WILL_FREE;
+	spin_unlock(&inode->i_lock);
+	write_inode_now(inode, 1);
+	spin_lock(&inode->i_lock);
+	WARN_ON(inode->i_state & I_NEW);
+	inode->i_state &= ~I_WILL_FREE;
 
-	return res;
+	return 1;
 }
 
 /*
@@ -1350,32 +1361,32 @@ int ocfs2_validate_inode_block(struct super_block *sb,
 	rc = -EINVAL;
 
 	if (!OCFS2_IS_VALID_DINODE(di)) {
-		ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
-			    (unsigned long long)bh->b_blocknr, 7,
-			    di->i_signature);
+		rc = ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
+				 (unsigned long long)bh->b_blocknr, 7,
+				 di->i_signature);
 		goto bail;
 	}
 
 	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
-		ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)le64_to_cpu(di->i_blkno));
+		rc = ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 (unsigned long long)le64_to_cpu(di->i_blkno));
 		goto bail;
 	}
 
 	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
-		ocfs2_error(sb,
-			    "Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
-			    (unsigned long long)bh->b_blocknr);
+		rc = ocfs2_error(sb,
+				 "Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
+				 (unsigned long long)bh->b_blocknr);
 		goto bail;
 	}
 
 	if (le32_to_cpu(di->i_fs_generation) !=
 	    OCFS2_SB(sb)->fs_generation) {
-		ocfs2_error(sb,
-			    "Invalid dinode #%llu: fs_generation is %u\n",
-			    (unsigned long long)bh->b_blocknr,
-			    le32_to_cpu(di->i_fs_generation));
+		rc = ocfs2_error(sb,
+				 "Invalid dinode #%llu: fs_generation is %u\n",
+				 (unsigned long long)bh->b_blocknr,
+				 le32_to_cpu(di->i_fs_generation));
 		goto bail;
 	}
 
diff --git a/kernel/fs/ocfs2/inode.h b/kernel/fs/ocfs2/inode.h
index 5e86b247c..aac8b86f3 100644
--- a/kernel/fs/ocfs2/inode.h
+++ b/kernel/fs/ocfs2/inode.h
@@ -81,8 +81,6 @@ struct ocfs2_inode_info
 	tid_t i_sync_tid;
 	tid_t i_datasync_tid;
 
-	wait_queue_head_t append_dio_wq;
-
 	struct dquot *i_dquot[MAXQUOTAS];
 };
 
@@ -114,6 +112,8 @@ struct ocfs2_inode_info
 #define OCFS2_INODE_OPEN_DIRECT		0x00000020
 /* Tell the inode wipe code it's not in orphan dir */
 #define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000040
+/* Entry in orphan dir with 'dio-' prefix */
+#define OCFS2_INODE_DIO_ORPHAN_ENTRY	0x00000080
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {
diff --git a/kernel/fs/ocfs2/ioctl.c b/kernel/fs/ocfs2/ioctl.c
index 53e6c40ed..3cb097ccc 100644
--- a/kernel/fs/ocfs2/ioctl.c
+++ b/kernel/fs/ocfs2/ioctl.c
@@ -980,7 +980,6 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case OCFS2_IOC_GROUP_EXTEND:
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
-	case FITRIM:
 		break;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, argp, sizeof(args)))
diff --git a/kernel/fs/ocfs2/journal.c b/kernel/fs/ocfs2/journal.c
index ff5319282..13534f4fe 100644
--- a/kernel/fs/ocfs2/journal.c
+++ b/kernel/fs/ocfs2/journal.c
@@ -108,7 +108,7 @@ struct ocfs2_replay_map {
 	unsigned char rm_replay_slots[0];
 };
 
-void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
+static void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
 {
 	if (!osb->replay_map)
 		return;
@@ -153,7 +153,7 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+static void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
 		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
@@ -173,7 +173,7 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
 	replay_map->rm_state = REPLAY_DONE;
 }
 
-void ocfs2_free_replay_slots(struct ocfs2_super *osb)
+static void ocfs2_free_replay_slots(struct ocfs2_super *osb)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 
@@ -374,7 +374,7 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
 		mlog_errno(PTR_ERR(handle));
 
 		if (is_journal_aborted(journal)) {
-			ocfs2_abort(osb->sb, "Detected aborted journal");
+			ocfs2_abort(osb->sb, "Detected aborted journal\n");
 			handle = ERR_PTR(-EROFS);
 		}
 	} else {
@@ -571,9 +571,7 @@ static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
 	     (unsigned long)bh,
 	     (unsigned long long)bh->b_blocknr);
 
-	/* We aren't guaranteed to have the superblock here - but if we
-	 * don't, it'll just crash. */
-	ocfs2_error(bh->b_assoc_map->host->i_sb,
+	ocfs2_error(bh->b_bdev->bd_super,
 		    "JBD2 has aborted our journal, ocfs2 cannot continue\n");
 }
 
@@ -670,7 +668,23 @@ static int __ocfs2_journal_access(handle_t *handle,
 		mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n");
 		mlog(ML_ERROR, "b_blocknr=%llu\n",
 		     (unsigned long long)bh->b_blocknr);
-		BUG();
+
+		lock_buffer(bh);
+		/*
+		 * A previous attempt to write this buffer head failed.
+		 * Nothing we can do but to retry the write and hope for
+		 * the best.
+		 */
+		if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) {
+			clear_buffer_write_io_error(bh);
+			set_buffer_uptodate(bh);
+		}
+
+		if (!buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			return -EIO;
+		}
+		unlock_buffer(bh);
 	}
 
 	/* Set the current transaction information on the ci so
@@ -775,7 +789,20 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh)
 	trace_ocfs2_journal_dirty((unsigned long long)bh->b_blocknr);
 
 	status = jbd2_journal_dirty_metadata(handle, bh);
-	BUG_ON(status);
+	if (status) {
+		mlog_errno(status);
+		if (!is_handle_aborted(handle)) {
+			journal_t *journal = handle->h_transaction->t_journal;
+			struct super_block *sb = bh->b_bdev->bd_super;
+
+			mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. "
+					"Aborting transaction and journal.\n");
+			handle->h_err = status;
+			jbd2_journal_abort_handle(handle);
+			jbd2_journal_abort(journal, status);
+			ocfs2_abort(sb, "Journal already aborted.\n");
+		}
+	}
 }
 
 #define OCFS2_DEFAULT_COMMIT_INTERVAL	(HZ * JBD2_DEFAULT_MAX_COMMIT_AGE)
@@ -1063,7 +1090,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 	/* Launch the commit thread */
 	if (!local) {
 		osb->commit_task = kthread_run(ocfs2_commit_thread, osb,
-					       "ocfs2cmt");
+				"ocfs2cmt-%s", osb->uuid_str);
 		if (IS_ERR(osb->commit_task)) {
 			status = PTR_ERR(osb->commit_task);
 			osb->commit_task = NULL;
@@ -1480,7 +1507,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 		goto out;
 
 	osb->recovery_thread_task =  kthread_run(__ocfs2_recovery_thread, osb,
-						 "ocfs2rec");
+			"ocfs2rec-%s", osb->uuid_str);
 	if (IS_ERR(osb->recovery_thread_task)) {
 		mlog_errno((int)PTR_ERR(osb->recovery_thread_task));
 		osb->recovery_thread_task = NULL;
@@ -1884,7 +1911,7 @@ static inline unsigned long ocfs2_orphan_scan_timeout(void)
  * hasn't happened.  The node queues a scan and increments the
  * sequence number in the LVB.
  */
-void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
+static void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 {
 	struct ocfs2_orphan_scan *os;
 	int status, i;
@@ -1933,7 +1960,7 @@ out:
 }
 
 /* Worker task that gets fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT millsec */
-void ocfs2_orphan_scan_work(struct work_struct *work)
+static void ocfs2_orphan_scan_work(struct work_struct *work)
 {
 	struct ocfs2_orphan_scan *os;
 	struct ocfs2_super *osb;
@@ -1994,6 +2021,7 @@ struct ocfs2_orphan_filldir_priv {
 	struct dir_context	ctx;
 	struct inode		*head;
 	struct ocfs2_super	*osb;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 };
 
 static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
@@ -2009,12 +2037,22 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 	if (name_len == 2 && !strncmp("..", name, 2))
 		return 0;
 
+	/* do not include dio entry in case of orphan scan */
+	if ((p->orphan_reco_type == ORPHAN_NO_NEED_TRUNCATE) &&
+			(!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX,
+			OCFS2_DIO_ORPHAN_PREFIX_LEN)))
+		return 0;
+
 	/* Skip bad inodes so that recovery can continue */
 	iter = ocfs2_iget(p->osb, ino,
 			  OCFS2_FI_FLAG_ORPHAN_RECOVERY, 0);
 	if (IS_ERR(iter))
 		return 0;
 
+	if (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX,
+			OCFS2_DIO_ORPHAN_PREFIX_LEN))
+		OCFS2_I(iter)->ip_flags |= OCFS2_INODE_DIO_ORPHAN_ENTRY;
+
 	/* Skip inodes which are already added to recover list, since dio may
 	 * happen concurrently with unlink/rename */
 	if (OCFS2_I(iter)->ip_next_orphan) {
@@ -2033,14 +2071,16 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 
 static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 			       int slot,
-			       struct inode **head)
+			       struct inode **head,
+			       enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int status;
 	struct inode *orphan_dir_inode = NULL;
 	struct ocfs2_orphan_filldir_priv priv = {
 		.ctx.actor = ocfs2_orphan_filldir,
 		.osb = osb,
-		.head = *head
+		.head = *head,
+		.orphan_reco_type = orphan_reco_type
 	};
 
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
@@ -2137,11 +2177,13 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 	struct inode *inode = NULL;
 	struct inode *iter;
 	struct ocfs2_inode_info *oi;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
 
 	trace_ocfs2_recover_orphans(slot);
 
 	ocfs2_mark_recovering_orphan_dir(osb, slot);
-	ret = ocfs2_queue_orphans(osb, slot, &inode);
+	ret = ocfs2_queue_orphans(osb, slot, &inode, orphan_reco_type);
 	ocfs2_clear_recovering_orphan_dir(osb, slot);
 
 	/* Error here should be noted, but we want to continue with as
@@ -2157,60 +2199,59 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		iter = oi->ip_next_orphan;
 		oi->ip_next_orphan = NULL;
 
-		/*
-		 * We need to take and drop the inode lock to
-		 * force read inode from disk.
-		 */
-		ret = ocfs2_inode_lock(inode, NULL, 0);
-		if (ret) {
-			mlog_errno(ret);
-			goto next;
-		}
-		ocfs2_inode_unlock(inode, 0);
-
-		if (inode->i_nlink == 0) {
-			spin_lock(&oi->ip_lock);
-			/* Set the proper information to get us going into
-			 * ocfs2_delete_inode. */
-			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-			spin_unlock(&oi->ip_lock);
-		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
-			struct buffer_head *di_bh = NULL;
-
+		if (oi->ip_flags & OCFS2_INODE_DIO_ORPHAN_ENTRY) {
+			mutex_lock(&inode->i_mutex);
 			ret = ocfs2_rw_lock(inode, 1);
-			if (ret) {
+			if (ret < 0) {
 				mlog_errno(ret);
-				goto next;
+				goto unlock_mutex;
 			}
-
+			/*
+			 * We need to take and drop the inode lock to
+			 * force read inode from disk.
+			 */
 			ret = ocfs2_inode_lock(inode, &di_bh, 1);
-			if (ret < 0) {
-				ocfs2_rw_unlock(inode, 1);
+			if (ret) {
 				mlog_errno(ret);
-				goto next;
+				goto unlock_rw;
 			}
 
-			ret = ocfs2_truncate_file(inode, di_bh,
-					i_size_read(inode));
-			ocfs2_inode_unlock(inode, 1);
-			ocfs2_rw_unlock(inode, 1);
-			brelse(di_bh);
-			if (ret < 0) {
-				if (ret != -ENOSPC)
+			di = (struct ocfs2_dinode *)di_bh->b_data;
+
+			if (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size_read(inode));
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+					goto unlock_inode;
+				}
+
+				ret = ocfs2_del_inode_from_orphan(osb, inode,
+						di_bh, 0, 0);
+				if (ret)
 					mlog_errno(ret);
-				goto next;
 			}
+unlock_inode:
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			di_bh = NULL;
+unlock_rw:
+			ocfs2_rw_unlock(inode, 1);
+unlock_mutex:
+			mutex_unlock(&inode->i_mutex);
 
-			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
-			if (ret)
-				mlog_errno(ret);
-
-			wake_up(&OCFS2_I(inode)->append_dio_wq);
-		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
+			/* clear dio flag in ocfs2_inode_info */
+			oi->ip_flags &= ~OCFS2_INODE_DIO_ORPHAN_ENTRY;
+		} else {
+			spin_lock(&oi->ip_lock);
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		}
 
-next:
 		iput(inode);
-
 		inode = iter;
 	}
 
diff --git a/kernel/fs/ocfs2/localalloc.c b/kernel/fs/ocfs2/localalloc.c
index 857bbbcd3..0a4457fb0 100644
--- a/kernel/fs/ocfs2/localalloc.c
+++ b/kernel/fs/ocfs2/localalloc.c
@@ -665,8 +665,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 #ifdef CONFIG_OCFS2_DEBUG_FS
 	if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
 	    ocfs2_local_alloc_count_bits(alloc)) {
-		ocfs2_error(osb->sb, "local alloc inode %llu says it has "
-			    "%u used bits, but a count shows %u",
+		ocfs2_error(osb->sb, "local alloc inode %llu says it has %u used bits, but a count shows %u\n",
 			    (unsigned long long)le64_to_cpu(alloc->i_blkno),
 			    le32_to_cpu(alloc->id1.bitmap1.i_used),
 			    ocfs2_local_alloc_count_bits(alloc));
diff --git a/kernel/fs/ocfs2/locks.c b/kernel/fs/ocfs2/locks.c
index 6b6d092b0..d56f0079b 100644
--- a/kernel/fs/ocfs2/locks.c
+++ b/kernel/fs/ocfs2/locks.c
@@ -66,8 +66,11 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 * level.
 		 */
 
-		flock_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+		locks_lock_file_wait(file,
+				&(struct file_lock) {
+					.fl_type = F_UNLCK,
+					.fl_flags = FL_FLOCK
+				});
 
 		ocfs2_file_unlock(file);
 	}
@@ -81,7 +84,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		goto out;
 	}
 
-	ret = flock_lock_file_wait(file, fl);
+	ret = locks_lock_file_wait(file, fl);
 	if (ret)
 		ocfs2_file_unlock(file);
 
@@ -98,7 +101,7 @@ static int ocfs2_do_funlock(struct file *file, int cmd, struct file_lock *fl)
 
 	mutex_lock(&fp->fp_mutex);
 	ocfs2_file_unlock(file);
-	ret = flock_lock_file_wait(file, fl);
+	ret = locks_lock_file_wait(file, fl);
 	mutex_unlock(&fp->fp_mutex);
 
 	return ret;
@@ -119,7 +122,7 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) ||
 	    ocfs2_mount_local(osb))
-		return flock_lock_file_wait(file, fl);
+		return locks_lock_file_wait(file, fl);
 
 	if (fl->fl_type == F_UNLCK)
 		return ocfs2_do_funlock(file, cmd, fl);
diff --git a/kernel/fs/ocfs2/move_extents.c b/kernel/fs/ocfs2/move_extents.c
index 56a768d06..124471d26 100644
--- a/kernel/fs/ocfs2/move_extents.c
+++ b/kernel/fs/ocfs2/move_extents.c
@@ -99,11 +99,9 @@ static int __ocfs2_move_extent(handle_t *handle,
 
 	index = ocfs2_search_extent_list(el, cpos);
 	if (index == -1) {
-		ocfs2_error(inode->i_sb,
-			    "Inode %llu has an extent at cpos %u which can no "
-			    "longer be found.\n",
-			    (unsigned long long)ino, cpos);
-		ret = -EROFS;
+		ret = ocfs2_error(inode->i_sb,
+				  "Inode %llu has an extent at cpos %u which can no longer be found\n",
+				  (unsigned long long)ino, cpos);
 		goto out;
 	}
 
diff --git a/kernel/fs/ocfs2/namei.c b/kernel/fs/ocfs2/namei.c
index 176fe6afd..3123408da 100644
--- a/kernel/fs/ocfs2/namei.c
+++ b/kernel/fs/ocfs2/namei.c
@@ -106,8 +106,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
-#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
-#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
 
 static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
@@ -200,11 +198,12 @@ bail:
 static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
 {
 	struct inode *inode;
+	int status;
 
 	inode = new_inode(dir->i_sb);
 	if (!inode) {
 		mlog(ML_ERROR, "new_inode failed!\n");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	/* populate as many fields early on as possible - many of
@@ -213,7 +212,10 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
 	if (S_ISDIR(mode))
 		set_nlink(inode, 2);
 	inode_init_owner(inode, dir, mode);
-	dquot_initialize(inode);
+	status = dquot_initialize(inode);
+	if (status)
+		return ERR_PTR(status);
+
 	return inode;
 }
 
@@ -264,7 +266,11 @@ static int ocfs2_mknod(struct inode *dir,
 			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
 			  (unsigned long)dev, mode);
 
-	dquot_initialize(dir);
+	status = dquot_initialize(dir);
+	if (status) {
+		mlog_errno(status);
+		return status;
+	}
 
 	/* get our super block */
 	osb = OCFS2_SB(dir->i_sb);
@@ -311,8 +317,9 @@ static int ocfs2_mknod(struct inode *dir,
 	}
 
 	inode = ocfs2_get_init_inode(dir, mode);
-	if (!inode) {
-		status = -ENOMEM;
+	if (IS_ERR(inode)) {
+		status = PTR_ERR(inode);
+		inode = NULL;
 		mlog_errno(status);
 		goto leave;
 	}
@@ -360,7 +367,7 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
-	status = posix_acl_create(dir, &mode, &default_acl, &acl);
+	status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
 	if (status) {
 		mlog_errno(status);
 		goto leave;
@@ -648,9 +655,18 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 		return status;
 	}
 
-	return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
+	status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
 				    parent_fe_bh, handle, inode_ac,
 				    fe_blkno, suballoc_loc, suballoc_bit);
+	if (status < 0) {
+		u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit);
+		int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode,
+				inode_ac->ac_bh, suballoc_bit, bg_blkno, 1);
+		if (tmp)
+			mlog_errno(tmp);
+	}
+
+	return status;
 }
 
 static int ocfs2_mkdir(struct inode *dir,
@@ -708,7 +724,11 @@ static int ocfs2_link(struct dentry *old_dentry,
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
-	dquot_initialize(dir);
+	err = dquot_initialize(dir);
+	if (err) {
+		mlog_errno(err);
+		return err;
+	}
 
 	err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
 			&parent_fe_bh, dir, 0);
@@ -896,7 +916,11 @@ static int ocfs2_unlink(struct inode *dir,
 			   (unsigned long long)OCFS2_I(dir)->ip_blkno,
 			   (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
-	dquot_initialize(dir);
+	status = dquot_initialize(dir);
+	if (status) {
+		mlog_errno(status);
+		return status;
+	}
 
 	BUG_ON(d_inode(dentry->d_parent) != dir);
 
@@ -1018,11 +1042,6 @@ leave:
 	if (handle)
 		ocfs2_commit_trans(osb, handle);
 
-	if (child_locked)
-		ocfs2_inode_unlock(inode, 1);
-
-	ocfs2_inode_unlock(dir, 1);
-
 	if (orphan_dir) {
 		/* This was locked for us in ocfs2_prepare_orphan_dir() */
 		ocfs2_inode_unlock(orphan_dir, 1);
@@ -1030,6 +1049,11 @@ leave:
 		iput(orphan_dir);
 	}
 
+	if (child_locked)
+		ocfs2_inode_unlock(inode, 1);
+
+	ocfs2_inode_unlock(dir, 1);
+
 	brelse(fe_bh);
 	brelse(parent_node_bh);
 
@@ -1116,8 +1140,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	int inode1_is_ancestor, inode2_is_ancestor;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
 	struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
-	struct buffer_head **tmpbh;
-	struct inode *tmpinode;
 
 	trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno,
 				(unsigned long long)oi2->ip_blkno);
@@ -1148,13 +1170,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 				(oi1->ip_blkno < oi2->ip_blkno &&
 				inode2_is_ancestor == 0)) {
 			/* switch id1 and id2 around */
-			tmpbh = bh2;
-			bh2 = bh1;
-			bh1 = tmpbh;
-
-			tmpinode = inode2;
-			inode2 = inode1;
-			inode1 = tmpinode;
+			swap(bh2, bh1);
+			swap(inode2, inode1);
 		}
 		/* lock id2 */
 		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
@@ -1237,8 +1254,16 @@ static int ocfs2_rename(struct inode *old_dir,
 			   old_dentry->d_name.len, old_dentry->d_name.name,
 			   new_dentry->d_name.len, new_dentry->d_name.name);
 
-	dquot_initialize(old_dir);
-	dquot_initialize(new_dir);
+	status = dquot_initialize(old_dir);
+	if (status) {
+		mlog_errno(status);
+		goto bail;
+	}
+	status = dquot_initialize(new_dir);
+	if (status) {
+		mlog_errno(status);
+		goto bail;
+	}
 
 	osb = OCFS2_SB(old_dir->i_sb);
 
@@ -1291,6 +1316,11 @@ static int ocfs2_rename(struct inode *old_dir,
 	}
 	parents_locked = 1;
 
+	if (!new_dir->i_nlink) {
+		status = -EACCES;
+		goto bail;
+	}
+
 	/* make sure both dirs have bhs
 	 * get an extra ref on old_dir_bh if old==new */
 	if (!new_dir_bh) {
@@ -1551,12 +1581,25 @@ static int ocfs2_rename(struct inode *old_dir,
 	status = ocfs2_find_entry(old_dentry->d_name.name,
 				  old_dentry->d_name.len, old_dir,
 				  &old_entry_lookup);
-	if (status)
+	if (status) {
+		if (!is_journal_aborted(osb->journal->j_journal)) {
+			ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s "
+					"is not deleted.",
+					new_dentry->d_name.len, new_dentry->d_name.name,
+					old_dentry->d_name.len, old_dentry->d_name.name);
+		}
 		goto bail;
+	}
 
 	status = ocfs2_delete_entry(handle, old_dir, &old_entry_lookup);
 	if (status < 0) {
 		mlog_errno(status);
+		if (!is_journal_aborted(osb->journal->j_journal)) {
+			ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s "
+					"is not deleted.",
+					new_dentry->d_name.len, new_dentry->d_name.name,
+					old_dentry->d_name.len, old_dentry->d_name.name);
+		}
 		goto bail;
 	}
 
@@ -1615,21 +1658,9 @@ static int ocfs2_rename(struct inode *old_dir,
 	ocfs2_dentry_move(old_dentry, new_dentry, old_dir, new_dir);
 	status = 0;
 bail:
-	if (rename_lock)
-		ocfs2_rename_unlock(osb);
-
 	if (handle)
 		ocfs2_commit_trans(osb, handle);
 
-	if (parents_locked)
-		ocfs2_double_unlock(old_dir, new_dir);
-
-	if (old_child_locked)
-		ocfs2_inode_unlock(old_inode, 1);
-
-	if (new_child_locked)
-		ocfs2_inode_unlock(new_inode, 1);
-
 	if (orphan_dir) {
 		/* This was locked for us in ocfs2_prepare_orphan_dir() */
 		ocfs2_inode_unlock(orphan_dir, 1);
@@ -1637,6 +1668,18 @@ bail:
 		iput(orphan_dir);
 	}
 
+	if (new_child_locked)
+		ocfs2_inode_unlock(new_inode, 1);
+
+	if (old_child_locked)
+		ocfs2_inode_unlock(old_inode, 1);
+
+	if (parents_locked)
+		ocfs2_double_unlock(old_dir, new_dir);
+
+	if (rename_lock)
+		ocfs2_rename_unlock(osb);
+
 	if (new_inode)
 		sync_mapping_buffers(old_inode->i_mapping);
 
@@ -1793,7 +1836,11 @@ static int ocfs2_symlink(struct inode *dir,
 	trace_ocfs2_symlink_begin(dir, dentry, symname,
 				  dentry->d_name.len, dentry->d_name.name);
 
-	dquot_initialize(dir);
+	status = dquot_initialize(dir);
+	if (status) {
+		mlog_errno(status);
+		goto bail;
+	}
 
 	sb = dir->i_sb;
 	osb = OCFS2_SB(sb);
@@ -1838,8 +1885,9 @@ static int ocfs2_symlink(struct inode *dir,
 	}
 
 	inode = ocfs2_get_init_inode(dir, S_IFLNK | S_IRWXUGO);
-	if (!inode) {
-		status = -ENOMEM;
+	if (IS_ERR(inode)) {
+		status = PTR_ERR(inode);
+		inode = NULL;
 		mlog_errno(status);
 		goto bail;
 	}
@@ -2492,8 +2540,9 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 	}
 
 	inode = ocfs2_get_init_inode(dir, mode);
-	if (!inode) {
-		status = -ENOMEM;
+	if (IS_ERR(inode)) {
+		status = PTR_ERR(inode);
+		inode = NULL;
 		mlog_errno(status);
 		goto leave;
 	}
@@ -2577,27 +2626,6 @@ leave:
 	return status;
 }
 
-static int ocfs2_dio_orphan_recovered(struct inode *inode)
-{
-	int ret;
-	struct buffer_head *di_bh = NULL;
-	struct ocfs2_dinode *di = NULL;
-
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return 0;
-	}
-
-	di = (struct ocfs2_dinode *) di_bh->b_data;
-	ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
-	ocfs2_inode_unlock(inode, 1);
-	brelse(di_bh);
-
-	return ret;
-}
-
-#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
 int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 	struct inode *inode)
 {
@@ -2609,7 +2637,6 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 	handle_t *handle = NULL;
 	struct ocfs2_dinode *di = NULL;
 
-restart:
 	status = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
@@ -2619,15 +2646,21 @@ restart:
 	di = (struct ocfs2_dinode *) di_bh->b_data;
 	/*
 	 * Another append dio crashed?
-	 * If so, wait for recovery first.
+	 * If so, manually recover it first.
 	 */
 	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
-		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-		wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
-				ocfs2_dio_orphan_recovered(inode),
-				msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
-		goto restart;
+		status = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
+		if (status < 0) {
+			if (status != -ENOSPC)
+				mlog_errno(status);
+			goto bail_unlock_inode;
+		}
+
+		status = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail_unlock_inode;
+		}
 	}
 
 	status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
@@ -2670,30 +2703,22 @@ bail:
 }
 
 int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
-		struct inode *inode, int update_isize,
-		loff_t end)
+		struct inode *inode, struct buffer_head *di_bh,
+		int update_isize, loff_t end)
 {
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
-	struct buffer_head *di_bh = NULL;
-	struct ocfs2_dinode *di = NULL;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	handle_t *handle = NULL;
 	int status = 0;
 
-	status = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-	di = (struct ocfs2_dinode *) di_bh->b_data;
-
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
 			ORPHAN_DIR_SYSTEM_INODE,
 			le16_to_cpu(di->i_dio_orphaned_slot));
 	if (!orphan_dir_inode) {
 		status = -ENOENT;
 		mlog_errno(status);
-		goto bail_unlock_inode;
+		goto bail;
 	}
 
 	mutex_lock(&orphan_dir_inode->i_mutex);
@@ -2702,7 +2727,7 @@ int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
 		mutex_unlock(&orphan_dir_inode->i_mutex);
 		iput(orphan_dir_inode);
 		mlog_errno(status);
-		goto bail_unlock_inode;
+		goto bail;
 	}
 
 	handle = ocfs2_start_trans(osb,
@@ -2749,10 +2774,6 @@ bail_unlock_orphan:
 	brelse(orphan_dir_bh);
 	iput(orphan_dir_inode);
 
-bail_unlock_inode:
-	ocfs2_inode_unlock(inode, 1);
-	brelse(di_bh);
-
 bail:
 	return status;
 }
diff --git a/kernel/fs/ocfs2/namei.h b/kernel/fs/ocfs2/namei.h
index 5ddecce17..1155918d6 100644
--- a/kernel/fs/ocfs2/namei.h
+++ b/kernel/fs/ocfs2/namei.h
@@ -26,6 +26,9 @@
 #ifndef OCFS2_NAMEI_H
 #define OCFS2_NAMEI_H
 
+#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
+#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
+
 extern const struct inode_operations ocfs2_dir_iops;
 
 struct dentry *ocfs2_get_parent(struct dentry *child);
@@ -42,8 +45,8 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 		struct inode *inode);
 int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
-		struct inode *inode, int update_isize,
-		loff_t end);
+		struct inode *inode, struct buffer_head *di_bh,
+		int update_isize, loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/kernel/fs/ocfs2/ocfs2.h b/kernel/fs/ocfs2/ocfs2.h
index 460c6c37e..7a0126267 100644
--- a/kernel/fs/ocfs2/ocfs2.h
+++ b/kernel/fs/ocfs2/ocfs2.h
@@ -286,6 +286,8 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
 
 	OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15,  /* Journal Async Commit */
+	OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
+	OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001
@@ -717,6 +719,16 @@ static inline u64 ocfs2_clusters_to_blocks(struct super_block *sb,
 	return (u64)clusters << c_to_b_bits;
 }
 
+static inline u32 ocfs2_clusters_for_blocks(struct super_block *sb,
+		u64 blocks)
+{
+	int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits -
+			sb->s_blocksize_bits;
+
+	blocks += (1 << b_to_c_bits) - 1;
+	return (u32)(blocks >> b_to_c_bits);
+}
+
 static inline u32 ocfs2_blocks_to_clusters(struct super_block *sb,
 					   u64 blocks)
 {
diff --git a/kernel/fs/ocfs2/ocfs2_fs.h b/kernel/fs/ocfs2/ocfs2_fs.h
index db64ce2d4..540ab5b75 100644
--- a/kernel/fs/ocfs2/ocfs2_fs.h
+++ b/kernel/fs/ocfs2/ocfs2_fs.h
@@ -168,7 +168,7 @@
 /* Refcount tree support */
 #define OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE	0x1000
 
-/* Discontigous block groups */
+/* Discontiguous block groups */
 #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	0x2000
 
 /*
@@ -939,7 +939,7 @@ struct ocfs2_group_desc
 			/*
 			 * Block groups may be discontiguous when
 			 * OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG is set.
-			 * The extents of a discontigous block group are
+			 * The extents of a discontiguous block group are
 			 * stored in bg_list.  It is a flat list.
 			 * l_tree_depth must always be zero.  A
 			 * discontiguous group is signified by a non-zero
diff --git a/kernel/fs/ocfs2/quota_local.c b/kernel/fs/ocfs2/quota_local.c
index 3d0b63d34..8a54fd8a4 100644
--- a/kernel/fs/ocfs2/quota_local.c
+++ b/kernel/fs/ocfs2/quota_local.c
@@ -138,8 +138,7 @@ static int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
 
 	if (i_size_read(inode) >> inode->i_sb->s_blocksize_bits <= v_block) {
 		ocfs2_error(inode->i_sb,
-			    "Quota file %llu is probably corrupted! Requested "
-			    "to read block %Lu but file has size only %Lu\n",
+			    "Quota file %llu is probably corrupted! Requested to read block %Lu but file has size only %Lu\n",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
 			    (unsigned long long)v_block,
 			    (unsigned long long)i_size_read(inode));
@@ -499,8 +498,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 			dquot = dqget(sb,
 				      make_kqid(&init_user_ns, type,
 						le64_to_cpu(dqblk->dqb_id)));
-			if (!dquot) {
-				status = -EIO;
+			if (IS_ERR(dquot)) {
+				status = PTR_ERR(dquot);
 				mlog(ML_ERROR, "Failed to get quota structure "
 				     "for id %u, type %d. Cannot finish quota "
 				     "file recovery.\n",
diff --git a/kernel/fs/ocfs2/refcounttree.c b/kernel/fs/ocfs2/refcounttree.c
index d8c6af101..252119860 100644
--- a/kernel/fs/ocfs2/refcounttree.c
+++ b/kernel/fs/ocfs2/refcounttree.c
@@ -102,32 +102,30 @@ static int ocfs2_validate_refcount_block(struct super_block *sb,
 
 
 	if (!OCFS2_IS_VALID_REFCOUNT_BLOCK(rb)) {
-		ocfs2_error(sb,
-			    "Refcount block #%llu has bad signature %.*s",
-			    (unsigned long long)bh->b_blocknr, 7,
-			    rb->rf_signature);
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Refcount block #%llu has bad signature %.*s\n",
+				 (unsigned long long)bh->b_blocknr, 7,
+				 rb->rf_signature);
+		goto out;
 	}
 
 	if (le64_to_cpu(rb->rf_blkno) != bh->b_blocknr) {
-		ocfs2_error(sb,
-			    "Refcount block #%llu has an invalid rf_blkno "
-			    "of %llu",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)le64_to_cpu(rb->rf_blkno));
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Refcount block #%llu has an invalid rf_blkno of %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 (unsigned long long)le64_to_cpu(rb->rf_blkno));
+		goto out;
 	}
 
 	if (le32_to_cpu(rb->rf_fs_generation) != OCFS2_SB(sb)->fs_generation) {
-		ocfs2_error(sb,
-			    "Refcount block #%llu has an invalid "
-			    "rf_fs_generation of #%u",
-			    (unsigned long long)bh->b_blocknr,
-			    le32_to_cpu(rb->rf_fs_generation));
-		return -EINVAL;
+		rc = ocfs2_error(sb,
+				 "Refcount block #%llu has an invalid rf_fs_generation of #%u\n",
+				 (unsigned long long)bh->b_blocknr,
+				 le32_to_cpu(rb->rf_fs_generation));
+		goto out;
 	}
-
-	return 0;
+out:
+	return rc;
 }
 
 static int ocfs2_read_refcount_block(struct ocfs2_caching_info *ci,
@@ -1102,12 +1100,10 @@ static int ocfs2_get_refcount_rec(struct ocfs2_caching_info *ci,
 		el = &eb->h_list;
 
 		if (el->l_tree_depth) {
-			ocfs2_error(sb,
-			"refcount tree %llu has non zero tree "
-			"depth in leaf btree tree block %llu\n",
-			(unsigned long long)ocfs2_metadata_cache_owner(ci),
-			(unsigned long long)eb_bh->b_blocknr);
-			ret = -EROFS;
+			ret = ocfs2_error(sb,
+					  "refcount tree %llu has non zero tree depth in leaf btree tree block %llu\n",
+					  (unsigned long long)ocfs2_metadata_cache_owner(ci),
+					  (unsigned long long)eb_bh->b_blocknr);
 			goto out;
 		}
 	}
@@ -1406,11 +1402,9 @@ static int cmp_refcount_rec_by_cpos(const void *a, const void *b)
 
 static void swap_refcount_rec(void *a, void *b, int size)
 {
-	struct ocfs2_refcount_rec *l = a, *r = b, tmp;
+	struct ocfs2_refcount_rec *l = a, *r = b;
 
-	tmp = *l;
-	*l = *r;
-	*r = tmp;
+	swap(*l, *r);
 }
 
 /*
@@ -2361,10 +2355,8 @@ static int ocfs2_mark_extent_refcounted(struct inode *inode,
 					   cpos, len, phys);
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
-		ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
-			    "tree, but the feature bit is not set in the "
-			    "super block.", inode->i_ino);
-		ret = -EROFS;
+		ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+				  inode->i_ino);
 		goto out;
 	}
 
@@ -2547,10 +2539,8 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode,
 	u64 start_cpos = ocfs2_blocks_to_clusters(inode->i_sb, phys_blkno);
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
-		ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
-			    "tree, but the feature bit is not set in the "
-			    "super block.", inode->i_ino);
-		ret = -EROFS;
+		ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+				  inode->i_ino);
 		goto out;
 	}
 
@@ -2674,11 +2664,10 @@ static int ocfs2_refcount_cal_cow_clusters(struct inode *inode,
 		el = &eb->h_list;
 
 		if (el->l_tree_depth) {
-			ocfs2_error(inode->i_sb,
-				    "Inode %lu has non zero tree depth in "
-				    "leaf block %llu\n", inode->i_ino,
-				    (unsigned long long)eb_bh->b_blocknr);
-			ret = -EROFS;
+			ret = ocfs2_error(inode->i_sb,
+					  "Inode %lu has non zero tree depth in leaf block %llu\n",
+					  inode->i_ino,
+					  (unsigned long long)eb_bh->b_blocknr);
 			goto out;
 		}
 	}
@@ -2931,16 +2920,13 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
-	unsigned int from, to, readahead_pages;
+	unsigned int from, to;
 	loff_t offset, end, map_end;
 	struct address_space *mapping = inode->i_mapping;
 
 	trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster,
 					       new_cluster, new_len);
 
-	readahead_pages =
-		(ocfs2_cow_contig_clusters(sb) <<
-		 OCFS2_SB(sb)->s_clustersize_bits) >> PAGE_CACHE_SHIFT;
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits);
 	/*
@@ -3108,11 +3094,9 @@ static int ocfs2_clear_ext_refcount(handle_t *handle,
 
 	index = ocfs2_search_extent_list(el, cpos);
 	if (index == -1) {
-		ocfs2_error(sb,
-			    "Inode %llu has an extent at cpos %u which can no "
-			    "longer be found.\n",
-			    (unsigned long long)ino, cpos);
-		ret = -EROFS;
+		ret = ocfs2_error(sb,
+				  "Inode %llu has an extent at cpos %u which can no longer be found\n",
+				  (unsigned long long)ino, cpos);
 		goto out;
 	}
 
@@ -3378,10 +3362,8 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
-		ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
-			    "tree, but the feature bit is not set in the "
-			    "super block.", inode->i_ino);
-		return -EROFS;
+		return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+				   inode->i_ino);
 	}
 
 	ocfs2_init_dealloc_ctxt(&context->dealloc);
@@ -4421,8 +4403,9 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir,
 	}
 
 	mutex_lock(&inode->i_mutex);
-	dquot_initialize(dir);
-	error = ocfs2_reflink(old_dentry, dir, new_dentry, preserve);
+	error = dquot_initialize(dir);
+	if (!error)
+		error = ocfs2_reflink(old_dentry, dir, new_dentry, preserve);
 	mutex_unlock(&inode->i_mutex);
 	if (!error)
 		fsnotify_create(dir, new_dentry);
diff --git a/kernel/fs/ocfs2/resize.c b/kernel/fs/ocfs2/resize.c
index d5da6f624..79b802130 100644
--- a/kernel/fs/ocfs2/resize.c
+++ b/kernel/fs/ocfs2/resize.c
@@ -54,11 +54,12 @@
 static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 				       struct ocfs2_group_desc *gd,
 				       u16 cl_cpg,
+				       u16 old_bg_clusters,
 				       int set)
 {
 	int i;
 	u16 backups = 0;
-	u32 cluster;
+	u32 cluster, lgd_cluster;
 	u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno);
 
 	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
@@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 		else if (gd_blkno > lgd_blkno)
 			break;
 
+		/* check if already done backup super */
+		lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno);
+		lgd_cluster += old_bg_clusters;
+		if (lgd_cluster >= cluster)
+			continue;
+
 		if (set)
 			ocfs2_set_bit(cluster % cl_cpg,
 				      (unsigned long *)gd->bg_bitmap);
@@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 	u16 chain, num_bits, backups = 0;
 	u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
 	u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
+	u16 old_bg_clusters;
 
 	trace_ocfs2_update_last_group_and_inode(new_clusters,
 						first_new_cluster);
@@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 
 	group = (struct ocfs2_group_desc *)group_bh->b_data;
 
+	old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc;
 	/* update the group first. */
 	num_bits = new_clusters * cl_bpc;
 	le16_add_cpu(&group->bg_bits, num_bits);
@@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 				     OCFS2_FEATURE_COMPAT_BACKUP_SB)) {
 		backups = ocfs2_calc_new_backup_super(bm_inode,
 						     group,
-						     cl_cpg, 1);
+						     cl_cpg, old_bg_clusters, 1);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
 	}
 
@@ -163,7 +172,7 @@ out_rollback:
 	if (ret < 0) {
 		ocfs2_calc_new_backup_super(bm_inode,
 					    group,
-					    cl_cpg, 0);
+					    cl_cpg, old_bg_clusters, 0);
 		le16_add_cpu(&group->bg_free_bits_count, backups);
 		le16_add_cpu(&group->bg_bits, -1 * num_bits);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
diff --git a/kernel/fs/ocfs2/stack_user.c b/kernel/fs/ocfs2/stack_user.c
index 2768eb1da..ced70c813 100644
--- a/kernel/fs/ocfs2/stack_user.c
+++ b/kernel/fs/ocfs2/stack_user.c
@@ -655,14 +655,7 @@ static int ocfs2_control_init(void)
 
 static void ocfs2_control_exit(void)
 {
-	int rc;
-
-	rc = misc_deregister(&ocfs2_control_device);
-	if (rc)
-		printk(KERN_ERR
-		       "ocfs2: Unable to deregister ocfs2_control device "
-		       "(errno %d)\n",
-		       -rc);
+	misc_deregister(&ocfs2_control_device);
 }
 
 static void fsdlm_lock_ast_wrapper(void *astarg)
diff --git a/kernel/fs/ocfs2/suballoc.c b/kernel/fs/ocfs2/suballoc.c
index 447902963..fc6d25f6d 100644
--- a/kernel/fs/ocfs2/suballoc.c
+++ b/kernel/fs/ocfs2/suballoc.c
@@ -149,10 +149,8 @@ void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
 	brelse(ac->ac_bh);
 	ac->ac_bh = NULL;
 	ac->ac_resv = NULL;
-	if (ac->ac_find_loc_priv) {
-		kfree(ac->ac_find_loc_priv);
-		ac->ac_find_loc_priv = NULL;
-	}
+	kfree(ac->ac_find_loc_priv);
+	ac->ac_find_loc_priv = NULL;
 }
 
 void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
@@ -167,12 +165,12 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
 }
 
 #define do_error(fmt, ...)						\
-	do{								\
-		if (resize)					\
-			mlog(ML_ERROR, fmt "\n", ##__VA_ARGS__);	\
-		else							\
-			ocfs2_error(sb, fmt, ##__VA_ARGS__);		\
-	} while (0)
+do {									\
+	if (resize)							\
+		mlog(ML_ERROR, fmt, ##__VA_ARGS__);			\
+	else								\
+		return ocfs2_error(sb, fmt, ##__VA_ARGS__);		\
+} while (0)
 
 static int ocfs2_validate_gd_self(struct super_block *sb,
 				  struct buffer_head *bh,
@@ -181,44 +179,35 @@ static int ocfs2_validate_gd_self(struct super_block *sb,
 	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
 
 	if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
-		do_error("Group descriptor #%llu has bad signature %.*s",
+		do_error("Group descriptor #%llu has bad signature %.*s\n",
 			 (unsigned long long)bh->b_blocknr, 7,
 			 gd->bg_signature);
-		return -EINVAL;
 	}
 
 	if (le64_to_cpu(gd->bg_blkno) != bh->b_blocknr) {
-		do_error("Group descriptor #%llu has an invalid bg_blkno "
-			 "of %llu",
+		do_error("Group descriptor #%llu has an invalid bg_blkno of %llu\n",
 			 (unsigned long long)bh->b_blocknr,
 			 (unsigned long long)le64_to_cpu(gd->bg_blkno));
-		return -EINVAL;
 	}
 
 	if (le32_to_cpu(gd->bg_generation) != OCFS2_SB(sb)->fs_generation) {
-		do_error("Group descriptor #%llu has an invalid "
-			 "fs_generation of #%u",
+		do_error("Group descriptor #%llu has an invalid fs_generation of #%u\n",
 			 (unsigned long long)bh->b_blocknr,
 			 le32_to_cpu(gd->bg_generation));
-		return -EINVAL;
 	}
 
 	if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
-		do_error("Group descriptor #%llu has bit count %u but "
-			 "claims that %u are free",
+		do_error("Group descriptor #%llu has bit count %u but claims that %u are free\n",
 			 (unsigned long long)bh->b_blocknr,
 			 le16_to_cpu(gd->bg_bits),
 			 le16_to_cpu(gd->bg_free_bits_count));
-		return -EINVAL;
 	}
 
 	if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
-		do_error("Group descriptor #%llu has bit count %u but "
-			 "max bitmap bits of %u",
+		do_error("Group descriptor #%llu has bit count %u but max bitmap bits of %u\n",
 			 (unsigned long long)bh->b_blocknr,
 			 le16_to_cpu(gd->bg_bits),
 			 8 * le16_to_cpu(gd->bg_size));
-		return -EINVAL;
 	}
 
 	return 0;
@@ -233,20 +222,17 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
 	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
 
 	if (di->i_blkno != gd->bg_parent_dinode) {
-		do_error("Group descriptor #%llu has bad parent "
-			 "pointer (%llu, expected %llu)",
+		do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n",
 			 (unsigned long long)bh->b_blocknr,
 			 (unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
 			 (unsigned long long)le64_to_cpu(di->i_blkno));
-		return -EINVAL;
 	}
 
 	max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
 	if (le16_to_cpu(gd->bg_bits) > max_bits) {
-		do_error("Group descriptor #%llu has bit count of %u",
+		do_error("Group descriptor #%llu has bit count of %u\n",
 			 (unsigned long long)bh->b_blocknr,
 			 le16_to_cpu(gd->bg_bits));
-		return -EINVAL;
 	}
 
 	/* In resize, we may meet the case bg_chain == cl_next_free_rec. */
@@ -254,10 +240,9 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
 	     le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) ||
 	    ((le16_to_cpu(gd->bg_chain) ==
 	     le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) && !resize)) {
-		do_error("Group descriptor #%llu has bad chain %u",
+		do_error("Group descriptor #%llu has bad chain %u\n",
 			 (unsigned long long)bh->b_blocknr,
 			 le16_to_cpu(gd->bg_chain));
-		return -EINVAL;
 	}
 
 	return 0;
@@ -384,11 +369,10 @@ static int ocfs2_block_group_fill(handle_t *handle,
 	struct super_block * sb = alloc_inode->i_sb;
 
 	if (((unsigned long long) bg_bh->b_blocknr) != group_blkno) {
-		ocfs2_error(alloc_inode->i_sb, "group block (%llu) != "
-			    "b_blocknr (%llu)",
-			    (unsigned long long)group_blkno,
-			    (unsigned long long) bg_bh->b_blocknr);
-		status = -EIO;
+		status = ocfs2_error(alloc_inode->i_sb,
+				     "group block (%llu) != b_blocknr (%llu)\n",
+				     (unsigned long long)group_blkno,
+				     (unsigned long long) bg_bh->b_blocknr);
 		goto bail;
 	}
 
@@ -834,9 +818,9 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
 	BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
 
 	if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) {
-		ocfs2_error(alloc_inode->i_sb, "Invalid chain allocator %llu",
-			    (unsigned long long)le64_to_cpu(fe->i_blkno));
-		status = -EIO;
+		status = ocfs2_error(alloc_inode->i_sb,
+				     "Invalid chain allocator %llu\n",
+				     (unsigned long long)le64_to_cpu(fe->i_blkno));
 		goto bail;
 	}
 
@@ -1370,12 +1354,11 @@ int ocfs2_block_group_set_bits(handle_t *handle,
 
 	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
 	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
-		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
-			    " count %u but claims %u are freed. num_bits %d",
-			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
-			    le16_to_cpu(bg->bg_bits),
-			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
-		return -EROFS;
+		return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
+				   (unsigned long long)le64_to_cpu(bg->bg_blkno),
+				   le16_to_cpu(bg->bg_bits),
+				   le16_to_cpu(bg->bg_free_bits_count),
+				   num_bits);
 	}
 	while(num_bits--)
 		ocfs2_set_bit(bit_off++, bitmap);
@@ -1905,13 +1888,11 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 
 	if (le32_to_cpu(fe->id1.bitmap1.i_used) >=
 	    le32_to_cpu(fe->id1.bitmap1.i_total)) {
-		ocfs2_error(ac->ac_inode->i_sb,
-			    "Chain allocator dinode %llu has %u used "
-			    "bits but only %u total.",
-			    (unsigned long long)le64_to_cpu(fe->i_blkno),
-			    le32_to_cpu(fe->id1.bitmap1.i_used),
-			    le32_to_cpu(fe->id1.bitmap1.i_total));
-		status = -EIO;
+		status = ocfs2_error(ac->ac_inode->i_sb,
+				     "Chain allocator dinode %llu has %u used bits but only %u total\n",
+				     (unsigned long long)le64_to_cpu(fe->i_blkno),
+				     le32_to_cpu(fe->id1.bitmap1.i_used),
+				     le32_to_cpu(fe->id1.bitmap1.i_total));
 		goto bail;
 	}
 
@@ -1939,7 +1920,10 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
-		hint = ocfs2_group_from_res(res);
+		if (ocfs2_is_cluster_bitmap(ac->ac_inode))
+			hint = res->sr_bg_blkno;
+		else
+			hint = ocfs2_group_from_res(res);
 		goto set_hint;
 	}
 	if (status < 0 && status != -ENOSPC) {
@@ -2429,12 +2413,11 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 	}
 	le16_add_cpu(&bg->bg_free_bits_count, num_bits);
 	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
-		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
-			    " count %u but claims %u are freed. num_bits %d",
-			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
-			    le16_to_cpu(bg->bg_bits),
-			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
-		return -EROFS;
+		return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
+				   (unsigned long long)le64_to_cpu(bg->bg_blkno),
+				   le16_to_cpu(bg->bg_bits),
+				   le16_to_cpu(bg->bg_free_bits_count),
+				   num_bits);
 	}
 
 	if (undo_fn)
diff --git a/kernel/fs/ocfs2/super.c b/kernel/fs/ocfs2/super.c
index a482e312c..2de4c8a93 100644
--- a/kernel/fs/ocfs2/super.c
+++ b/kernel/fs/ocfs2/super.c
@@ -192,6 +192,7 @@ enum {
 	Opt_resv_level,
 	Opt_dir_resv_level,
 	Opt_journal_async_commit,
+	Opt_err_cont,
 	Opt_err,
 };
 
@@ -224,6 +225,7 @@ static const match_table_t tokens = {
 	{Opt_resv_level, "resv_level=%u"},
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_journal_async_commit, "journal_async_commit"},
+	{Opt_err_cont, "errors=continue"},
 	{Opt_err, NULL}
 };
 
@@ -1330,10 +1332,19 @@ static int ocfs2_parse_options(struct super_block *sb,
 			mopt->mount_opt |= OCFS2_MOUNT_NOINTR;
 			break;
 		case Opt_err_panic:
+			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
+			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
 			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC;
 			break;
 		case Opt_err_ro:
+			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
 			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
+			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_ROFS;
+			break;
+		case Opt_err_cont:
+			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
+			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
+			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_CONT;
 			break;
 		case Opt_data_ordered:
 			mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK;
@@ -1530,6 +1541,8 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
 
 	if (opts & OCFS2_MOUNT_ERRORS_PANIC)
 		seq_printf(s, ",errors=panic");
+	else if (opts & OCFS2_MOUNT_ERRORS_CONT)
+		seq_printf(s, ",errors=continue");
 	else
 		seq_printf(s, ",errors=remount-ro");
 
@@ -1746,8 +1759,6 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
 	ocfs2_lock_res_init_once(&oi->ip_open_lockres);
 
-	init_waitqueue_head(&oi->append_dio_wq);
-
 	ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
 				  &ocfs2_inode_caching_ops);
 
@@ -2541,31 +2552,43 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 	memset(osb, 0, sizeof(struct ocfs2_super));
 }
 
-/* Put OCFS2 into a readonly state, or (if the user specifies it),
- * panic(). We do not support continue-on-error operation. */
-static void ocfs2_handle_error(struct super_block *sb)
+/* Depending on the mount option passed, perform one of the following:
+ * Put OCFS2 into a readonly state (default)
+ * Return EIO so that only the process errs
+ * Fix the error as if fsck.ocfs2 -y
+ * panic
+ */
+static int ocfs2_handle_error(struct super_block *sb)
 {
 	struct ocfs2_super *osb = OCFS2_SB(sb);
-
-	if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC)
-		panic("OCFS2: (device %s): panic forced after error\n",
-		      sb->s_id);
+	int rv = 0;
 
 	ocfs2_set_osb_flag(osb, OCFS2_OSB_ERROR_FS);
+	pr_crit("On-disk corruption discovered. "
+		"Please run fsck.ocfs2 once the filesystem is unmounted.\n");
 
-	if (sb->s_flags & MS_RDONLY &&
-	    (ocfs2_is_soft_readonly(osb) ||
-	     ocfs2_is_hard_readonly(osb)))
-		return;
-
-	printk(KERN_CRIT "File system is now read-only due to the potential "
-	       "of on-disk corruption. Please run fsck.ocfs2 once the file "
-	       "system is unmounted.\n");
-	sb->s_flags |= MS_RDONLY;
-	ocfs2_set_ro_flag(osb, 0);
+	if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC) {
+		panic("OCFS2: (device %s): panic forced after error\n",
+		      sb->s_id);
+	} else if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_CONT) {
+		pr_crit("OCFS2: Returning error to the calling process.\n");
+		rv = -EIO;
+	} else { /* default option */
+		rv = -EROFS;
+		if (sb->s_flags & MS_RDONLY &&
+				(ocfs2_is_soft_readonly(osb) ||
+				 ocfs2_is_hard_readonly(osb)))
+			return rv;
+
+		pr_crit("OCFS2: File system is now read-only.\n");
+		sb->s_flags |= MS_RDONLY;
+		ocfs2_set_ro_flag(osb, 0);
+	}
+
+	return rv;
 }
 
-void __ocfs2_error(struct super_block *sb, const char *function,
+int __ocfs2_error(struct super_block *sb, const char *function,
 		  const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -2577,12 +2600,12 @@ void __ocfs2_error(struct super_block *sb, const char *function,
 
 	/* Not using mlog here because we want to show the actual
 	 * function the error came from. */
-	printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV\n",
+	printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV",
 	       sb->s_id, function, &vaf);
 
 	va_end(args);
 
-	ocfs2_handle_error(sb);
+	return ocfs2_handle_error(sb);
 }
 
 /* Handle critical errors. This is intentionally more drastic than
@@ -2599,7 +2622,7 @@ void __ocfs2_abort(struct super_block *sb, const char *function,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV\n",
+	printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV",
 	       sb->s_id, function, &vaf);
 
 	va_end(args);
diff --git a/kernel/fs/ocfs2/super.h b/kernel/fs/ocfs2/super.h
index 74ff74cf7..b477d0b1c 100644
--- a/kernel/fs/ocfs2/super.h
+++ b/kernel/fs/ocfs2/super.h
@@ -32,16 +32,18 @@ int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
 				  int node_num);
 
 __printf(3, 4)
-void __ocfs2_error(struct super_block *sb, const char *function,
+int __ocfs2_error(struct super_block *sb, const char *function,
 		   const char *fmt, ...);
 
-#define ocfs2_error(sb, fmt, args...) __ocfs2_error(sb, __PRETTY_FUNCTION__, fmt, ##args)
+#define ocfs2_error(sb, fmt, ...)					\
+	__ocfs2_error(sb, __PRETTY_FUNCTION__, fmt, ##__VA_ARGS__)
 
 __printf(3, 4)
 void __ocfs2_abort(struct super_block *sb, const char *function,
 		   const char *fmt, ...);
 
-#define ocfs2_abort(sb, fmt, args...) __ocfs2_abort(sb, __PRETTY_FUNCTION__, fmt, ##args)
+#define ocfs2_abort(sb, fmt, ...)					\
+	__ocfs2_abort(sb, __PRETTY_FUNCTION__, fmt, ##__VA_ARGS__)
 
 /*
  * Void signal blockers, because in-kernel sigprocmask() only fails
diff --git a/kernel/fs/ocfs2/xattr.c b/kernel/fs/ocfs2/xattr.c
index d03bfbf3d..e9164f098 100644
--- a/kernel/fs/ocfs2/xattr.c
+++ b/kernel/fs/ocfs2/xattr.c
@@ -499,30 +499,24 @@ static int ocfs2_validate_xattr_block(struct super_block *sb,
 	 */
 
 	if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
-		ocfs2_error(sb,
-			    "Extended attribute block #%llu has bad "
-			    "signature %.*s",
-			    (unsigned long long)bh->b_blocknr, 7,
-			    xb->xb_signature);
-		return -EINVAL;
+		return ocfs2_error(sb,
+				   "Extended attribute block #%llu has bad signature %.*s\n",
+				   (unsigned long long)bh->b_blocknr, 7,
+				   xb->xb_signature);
 	}
 
 	if (le64_to_cpu(xb->xb_blkno) != bh->b_blocknr) {
-		ocfs2_error(sb,
-			    "Extended attribute block #%llu has an "
-			    "invalid xb_blkno of %llu",
-			    (unsigned long long)bh->b_blocknr,
-			    (unsigned long long)le64_to_cpu(xb->xb_blkno));
-		return -EINVAL;
+		return ocfs2_error(sb,
+				   "Extended attribute block #%llu has an invalid xb_blkno of %llu\n",
+				   (unsigned long long)bh->b_blocknr,
+				   (unsigned long long)le64_to_cpu(xb->xb_blkno));
 	}
 
 	if (le32_to_cpu(xb->xb_fs_generation) != OCFS2_SB(sb)->fs_generation) {
-		ocfs2_error(sb,
-			    "Extended attribute block #%llu has an invalid "
-			    "xb_fs_generation of #%u",
-			    (unsigned long long)bh->b_blocknr,
-			    le32_to_cpu(xb->xb_fs_generation));
-		return -EINVAL;
+		return ocfs2_error(sb,
+				   "Extended attribute block #%llu has an invalid xb_fs_generation of #%u\n",
+				   (unsigned long long)bh->b_blocknr,
+				   le32_to_cpu(xb->xb_fs_generation));
 	}
 
 	return 0;
@@ -3694,11 +3688,10 @@ static int ocfs2_xattr_get_rec(struct inode *inode,
 		el = &eb->h_list;
 
 		if (el->l_tree_depth) {
-			ocfs2_error(inode->i_sb,
-				    "Inode %lu has non zero tree depth in "
-				    "xattr tree block %llu\n", inode->i_ino,
-				    (unsigned long long)eb_bh->b_blocknr);
-			ret = -EROFS;
+			ret = ocfs2_error(inode->i_sb,
+					  "Inode %lu has non zero tree depth in xattr tree block %llu\n",
+					  inode->i_ino,
+					  (unsigned long long)eb_bh->b_blocknr);
 			goto out;
 		}
 	}
@@ -3713,11 +3706,10 @@ static int ocfs2_xattr_get_rec(struct inode *inode,
 	}
 
 	if (!e_blkno) {
-		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-			    "record (%u, %u, 0) in xattr", inode->i_ino,
-			    le32_to_cpu(rec->e_cpos),
-			    ocfs2_rec_clusters(el, rec));
-		ret = -EROFS;
+		ret = ocfs2_error(inode->i_sb, "Inode %lu has bad extent record (%u, %u, 0) in xattr\n",
+				  inode->i_ino,
+				  le32_to_cpu(rec->e_cpos),
+				  ocfs2_rec_clusters(el, rec));
 		goto out;
 	}
 
@@ -7237,9 +7229,10 @@ leave:
 /*
  * 'security' attributes support
  */
-static size_t ocfs2_xattr_security_list(struct dentry *dentry, char *list,
+static size_t ocfs2_xattr_security_list(const struct xattr_handler *handler,
+					struct dentry *dentry, char *list,
 					size_t list_size, const char *name,
-					size_t name_len, int type)
+					size_t name_len)
 {
 	const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
@@ -7252,8 +7245,9 @@ static size_t ocfs2_xattr_security_list(struct dentry *dentry, char *list,
 	return total_len;
 }
 
-static int ocfs2_xattr_security_get(struct dentry *dentry, const char *name,
-				    void *buffer, size_t size, int type)
+static int ocfs2_xattr_security_get(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    void *buffer, size_t size)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
@@ -7261,8 +7255,9 @@ static int ocfs2_xattr_security_get(struct dentry *dentry, const char *name,
 			       name, buffer, size);
 }
 
-static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_security_set(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    const void *value, size_t size, int flags)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
@@ -7271,7 +7266,7 @@ static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
 			       name, value, size, flags);
 }
 
-int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 		     void *fs_info)
 {
 	const struct xattr *xattr;
@@ -7327,13 +7322,17 @@ const struct xattr_handler ocfs2_xattr_security_handler = {
 /*
  * 'trusted' attributes support
  */
-static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list,
+static size_t ocfs2_xattr_trusted_list(const struct xattr_handler *handler,
+				       struct dentry *dentry, char *list,
 				       size_t list_size, const char *name,
-				       size_t name_len, int type)
+				       size_t name_len)
 {
 	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
 	if (list && total_len <= list_size) {
 		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
 		memcpy(list + prefix_len, name, name_len);
@@ -7342,8 +7341,9 @@ static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list,
 	return total_len;
 }
 
-static int ocfs2_xattr_trusted_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
@@ -7351,8 +7351,9 @@ static int ocfs2_xattr_trusted_get(struct dentry *dentry, const char *name,
 			       name, buffer, size);
 }
 
-static int ocfs2_xattr_trusted_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *value, size_t size, int flags)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
@@ -7371,9 +7372,10 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = {
 /*
  * 'user' attributes support
  */
-static size_t ocfs2_xattr_user_list(struct dentry *dentry, char *list,
+static size_t ocfs2_xattr_user_list(const struct xattr_handler *handler,
+				    struct dentry *dentry, char *list,
 				    size_t list_size, const char *name,
-				    size_t name_len, int type)
+				    size_t name_len)
 {
 	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
@@ -7390,8 +7392,9 @@ static size_t ocfs2_xattr_user_list(struct dentry *dentry, char *list,
 	return total_len;
 }
 
-static int ocfs2_xattr_user_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int ocfs2_xattr_user_get(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				void *buffer, size_t size)
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
@@ -7403,8 +7406,9 @@ static int ocfs2_xattr_user_get(struct dentry *dentry, const char *name,
 			       buffer, size);
 }
 
-static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_user_set(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				const void *value, size_t size, int flags)
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);