Merge tag 'v3.11-rc5' into for-3.12 branch

For testing purposes I want some nfs and nfsd bugfixes (specifically,
58cd57bfd9db3bc213bf9d6a10920f82095f0114 and previous nfsd patches, and
Trond's 4f3cc4809a98a165a9708b72b47de71643797bbd).

33 files changed, 302 insertions, 280 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index eaf1333..8bc5e8c 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -36,16 +36,23 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
 				u64 extent_item_pos,
 				struct extent_inode_elem **eie)
 {
-	u64 data_offset;
-	u64 data_len;
+	u64 offset = 0;
 	struct extent_inode_elem *e;
 
-	data_offset = btrfs_file_extent_offset(eb, fi);
-	data_len = btrfs_file_extent_num_bytes(eb, fi);
+	if (!btrfs_file_extent_compression(eb, fi) &&
+	    !btrfs_file_extent_encryption(eb, fi) &&
+	    !btrfs_file_extent_other_encoding(eb, fi)) {
+		u64 data_offset;
+		u64 data_len;
 
-	if (extent_item_pos < data_offset ||
-	    extent_item_pos >= data_offset + data_len)
-		return 1;
+		data_offset = btrfs_file_extent_offset(eb, fi);
+		data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+		if (extent_item_pos < data_offset ||
+		    extent_item_pos >= data_offset + data_len)
+			return 1;
+		offset = extent_item_pos - data_offset;
+	}
 
 	e = kmalloc(sizeof(*e), GFP_NOFS);
 	if (!e)
@@ -53,7 +60,7 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
 
 	e->next = *eie;
 	e->inum = key->objectid;
-	e->offset = key->offset + (extent_item_pos - data_offset);
+	e->offset = key->offset + offset;
 	*eie = e;
 
 	return 0;
@@ -189,7 +196,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 	struct extent_buffer *eb;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
-	struct extent_inode_elem *eie = NULL;
+	struct extent_inode_elem *eie = NULL, *old = NULL;
 	u64 disk_byte;
 
 	if (level != 0) {
@@ -223,6 +230,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 
 		if (disk_byte == wanted_disk_byte) {
 			eie = NULL;
+			old = NULL;
 			if (extent_item_pos) {
 				ret = check_extent_in_eb(&key, eb, fi,
 						*extent_item_pos,
@@ -230,18 +238,20 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 				if (ret < 0)
 					break;
 			}
-			if (!ret) {
-				ret = ulist_add(parents, eb->start,
-						(uintptr_t)eie, GFP_NOFS);
-				if (ret < 0)
-					break;
-				if (!extent_item_pos) {
-					ret = btrfs_next_old_leaf(root, path,
-							time_seq);
-					continue;
-				}
+			if (ret > 0)
+				goto next;
+			ret = ulist_add_merge(parents, eb->start,
+					      (uintptr_t)eie,
+					      (u64 *)&old, GFP_NOFS);
+			if (ret < 0)
+				break;
+			if (!ret && extent_item_pos) {
+				while (old->next)
+					old = old->next;
+				old->next = eie;
 			}
 		}
+next:
 		ret = btrfs_next_old_item(root, path, time_seq);
 	}
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5bf4c39..ed50460 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1271,7 +1271,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		BUG_ON(!eb_rewin);
 	}
 
-	extent_buffer_get(eb_rewin);
 	btrfs_tree_read_unlock(eb);
 	free_extent_buffer(eb);
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 583d98b..fe443fe 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4048,7 +4048,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	}
 
 	while (!end) {
-		u64 offset_in_extent;
+		u64 offset_in_extent = 0;
 
 		/* break if the extent we found is outside the range */
 		if (em->start >= max || extent_map_end(em) < off)
@@ -4064,9 +4064,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 		/*
 		 * record the offset from the start of the extent
-		 * for adjusting the disk offset below
+		 * for adjusting the disk offset below.  Only do this if the
+		 * extent isn't compressed since our in ram offset may be past
+		 * what we have actually allocated on disk.
 		 */
-		offset_in_extent = em_start - em->start;
+		if (!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+			offset_in_extent = em_start - em->start;
 		em_end = extent_map_end(em);
 		em_len = em_end - em_start;
 		emflags = em->flags;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a005fe2..8e686a4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -596,20 +596,29 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 		if (no_splits)
 			goto next;
 
-		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-		    em->start < start) {
+		if (em->start < start) {
 			split->start = em->start;
 			split->len = start - em->start;
-			split->orig_start = em->orig_start;
-			split->block_start = em->block_start;
 
-			if (compressed)
-				split->block_len = em->block_len;
-			else
-				split->block_len = split->len;
-			split->ram_bytes = em->ram_bytes;
-			split->orig_block_len = max(split->block_len,
-						    em->orig_block_len);
+			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+				split->orig_start = em->orig_start;
+				split->block_start = em->block_start;
+
+				if (compressed)
+					split->block_len = em->block_len;
+				else
+					split->block_len = split->len;
+				split->orig_block_len = max(split->block_len,
+						em->orig_block_len);
+				split->ram_bytes = em->ram_bytes;
+			} else {
+				split->orig_start = split->start;
+				split->block_len = 0;
+				split->block_start = em->block_start;
+				split->orig_block_len = 0;
+				split->ram_bytes = split->len;
+			}
+
 			split->generation = gen;
 			split->bdev = em->bdev;
 			split->flags = flags;
@@ -620,8 +629,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split = split2;
 			split2 = NULL;
 		}
-		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-		    testend && em->start + em->len > start + len) {
+		if (testend && em->start + em->len > start + len) {
 			u64 diff = start + len - em->start;
 
 			split->start = start + len;
@@ -630,18 +638,28 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			split->generation = gen;
-			split->orig_block_len = max(em->block_len,
+
+			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+				split->orig_block_len = max(em->block_len,
 						    em->orig_block_len);
-			split->ram_bytes = em->ram_bytes;
 
-			if (compressed) {
-				split->block_len = em->block_len;
-				split->block_start = em->block_start;
-				split->orig_start = em->orig_start;
+				split->ram_bytes = em->ram_bytes;
+				if (compressed) {
+					split->block_len = em->block_len;
+					split->block_start = em->block_start;
+					split->orig_start = em->orig_start;
+				} else {
+					split->block_len = split->len;
+					split->block_start = em->block_start
+						+ diff;
+					split->orig_start = em->orig_start;
+				}
 			} else {
-				split->block_len = split->len;
-				split->block_start = em->block_start + diff;
-				split->orig_start = em->orig_start;
+				split->ram_bytes = split->len;
+				split->orig_start = split->start;
+				split->block_len = 0;
+				split->block_start = em->block_start;
+				split->orig_block_len = 0;
 			}
 
 			ret = add_extent_mapping(em_tree, split, modified);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6d1b93c..021694c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2166,16 +2166,23 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
 		if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
 			continue;
 
-		extent_offset = btrfs_file_extent_offset(leaf, extent);
-		if (key.offset - extent_offset != offset)
+		/*
+		 * 'offset' refers to the exact key.offset,
+		 * NOT the 'offset' field in btrfs_extent_data_ref, ie.
+		 * (key.offset - extent_offset).
+		 */
+		if (key.offset != offset)
 			continue;
 
+		extent_offset = btrfs_file_extent_offset(leaf, extent);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, extent);
+
 		if (extent_offset >= old->extent_offset + old->offset +
 		    old->len || extent_offset + num_bytes <=
 		    old->extent_offset + old->offset)
 			continue;
 
+		ret = 0;
 		break;
 	}
 
@@ -2187,7 +2194,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
 
 	backref->root_id = root_id;
 	backref->inum = inum;
-	backref->file_pos = offset + extent_offset;
+	backref->file_pos = offset;
 	backref->num_bytes = num_bytes;
 	backref->extent_offset = extent_offset;
 	backref->generation = btrfs_file_extent_generation(leaf, extent);
@@ -2210,7 +2217,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path,
 	new->path = path;
 
 	list_for_each_entry_safe(old, tmp, &new->head, list) {
-		ret = iterate_inodes_from_logical(old->bytenr, fs_info,
+		ret = iterate_inodes_from_logical(old->bytenr +
+						  old->extent_offset, fs_info,
 						  path, record_one_backref,
 						  old);
 		BUG_ON(ret < 0 && ret != -ENOENT);
@@ -4391,9 +4399,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	int mask = attr->ia_valid;
 	int ret;
 
-	if (newsize == oldsize)
-		return 0;
-
 	/*
 	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
 	 * special case where we need to update the times despite not having
@@ -5165,14 +5170,31 @@ next:
 	}
 
 	/* Reached end of directory/root. Bump pos past the last item. */
-	if (key_type == BTRFS_DIR_INDEX_KEY)
-		/*
-		 * 32-bit glibc will use getdents64, but then strtol -
-		 * so the last number we can serve is this.
-		 */
-		ctx->pos = 0x7fffffff;
-	else
-		ctx->pos++;
+	ctx->pos++;
+
+	/*
+	 * Stop new entries from being returned after we return the last
+	 * entry.
+	 *
+	 * New directory entries are assigned a strictly increasing
+	 * offset.  This means that new entries created during readdir
+	 * are *guaranteed* to be seen in the future by that readdir.
+	 * This has broken buggy programs which operate on names as
+	 * they're returned by readdir.  Until we re-use freed offsets
+	 * we have this hack to stop new entries from being returned
+	 * under the assumption that they'll never reach this huge
+	 * offset.
+	 *
+	 * This is being careful not to overflow 32bit loff_t unless the
+	 * last entry requires it because doing so has broken 32bit apps
+	 * in the past.
+	 */
+	if (key_type == BTRFS_DIR_INDEX_KEY) {
+		if (ctx->pos >= INT_MAX)
+			ctx->pos = LLONG_MAX;
+		else
+			ctx->pos = INT_MAX;
+	}
 nopos:
 	ret = 0;
 err:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index d58cce7..af1931a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -983,12 +983,12 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
  * a dirty root struct and adds it into the list of dead roots that need to
  * be deleted
  */
-int btrfs_add_dead_root(struct btrfs_root *root)
+void btrfs_add_dead_root(struct btrfs_root *root)
 {
 	spin_lock(&root->fs_info->trans_lock);
-	list_add_tail(&root->root_list, &root->fs_info->dead_roots);
+	if (list_empty(&root->root_list))
+		list_add_tail(&root->root_list, &root->fs_info->dead_roots);
 	spin_unlock(&root->fs_info->trans_lock);
-	return 0;
 }
 
 /*
@@ -1925,7 +1925,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
 	}
 	root = list_first_entry(&fs_info->dead_roots,
 			struct btrfs_root, root_list);
-	list_del(&root->root_list);
+	list_del_init(&root->root_list);
 	spin_unlock(&fs_info->trans_lock);
 
 	pr_debug("btrfs: cleaner removing %llu\n",
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 005b037..defbc42 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -143,7 +143,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root);
 
-int btrfs_add_dead_root(struct btrfs_root *root);
+void btrfs_add_dead_root(struct btrfs_root *root);
 int btrfs_defrag_root(struct btrfs_root *root);
 int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2c67914..ff60d89 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3746,8 +3746,9 @@ next_slot:
 	}
 
 log_extents:
+	btrfs_release_path(path);
+	btrfs_release_path(dst_path);
 	if (fast_search) {
-		btrfs_release_path(dst_path);
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
 		if (ret) {
 			err = ret;
@@ -3764,8 +3765,6 @@ log_extents:
 	}
 
 	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
-		btrfs_release_path(path);
-		btrfs_release_path(dst_path);
 		ret = log_directory_changes(trans, root, inode, path, dst_path);
 		if (ret) {
 			err = ret;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 4888cb3..c7c83ff 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -533,8 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  */
 void debugfs_remove_recursive(struct dentry *dentry)
 {
-	struct dentry *child;
-	struct dentry *parent;
+	struct dentry *child, *next, *parent;
 
 	if (IS_ERR_OR_NULL(dentry))
 		return;
@@ -544,61 +543,37 @@ void debugfs_remove_recursive(struct dentry *dentry)
 		return;
 
 	parent = dentry;
+ down:
 	mutex_lock(&parent->d_inode->i_mutex);
+	list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+		if (!debugfs_positive(child))
+			continue;
 
-	while (1) {
-		/*
-		 * When all dentries under "parent" has been removed,
-		 * walk up the tree until we reach our starting point.
-		 */
-		if (list_empty(&parent->d_subdirs)) {
-			mutex_unlock(&parent->d_inode->i_mutex);
-			if (parent == dentry)
-				break;
-			parent = parent->d_parent;
-			mutex_lock(&parent->d_inode->i_mutex);
-		}
-		child = list_entry(parent->d_subdirs.next, struct dentry,
-				d_u.d_child);
- next_sibling:
-
-		/*
-		 * If "child" isn't empty, walk down the tree and
-		 * remove all its descendants first.
-		 */
+		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
 			mutex_unlock(&parent->d_inode->i_mutex);
 			parent = child;
-			mutex_lock(&parent->d_inode->i_mutex);
-			continue;
+			goto down;
 		}
-		__debugfs_remove(child, parent);
-		if (parent->d_subdirs.next == &child->d_u.d_child) {
-			/*
-			 * Try the next sibling.
-			 */
-			if (child->d_u.d_child.next != &parent->d_subdirs) {
-				child = list_entry(child->d_u.d_child.next,
-						   struct dentry,
-						   d_u.d_child);
-				goto next_sibling;
-			}
-
-			/*
-			 * Avoid infinite loop if we fail to remove
-			 * one dentry.
-			 */
-			mutex_unlock(&parent->d_inode->i_mutex);
-			break;
-		}
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ up:
+		if (!__debugfs_remove(child, parent))
+			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	}
 
-	parent = dentry->d_parent;
+	mutex_unlock(&parent->d_inode->i_mutex);
+	child = parent;
+	parent = parent->d_parent;
 	mutex_lock(&parent->d_inode->i_mutex);
-	__debugfs_remove(dentry, parent);
+
+	if (child != dentry) {
+		next = list_entry(child->d_u.d_child.next, struct dentry,
+					d_u.d_child);
+		goto up;
+	}
+
+	if (!__debugfs_remove(child, parent))
+		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	mutex_unlock(&parent->d_inode->i_mutex);
-	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
 EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 911649a..8121491 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -686,7 +686,6 @@ static int device_close(struct inode *inode, struct file *file)
 	   device_remove_lockspace() */
 
 	sigprocmask(SIG_SETMASK, &tmpsig, NULL);
-	recalc_sigpending();
 
 	return 0;
 }
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a618738..72ba470 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4412,7 +4412,7 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
 retry:
 	err = ext4_es_remove_extent(inode, last_block,
 				    EXT_MAX_BLOCKS - last_block);
-	if (err == ENOMEM) {
+	if (err == -ENOMEM) {
 		cond_resched();
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		goto retry;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f03598c..8bf5999 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -734,11 +734,8 @@ repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
 					      inode_bitmap_bh->b_data,
 					      EXT4_INODES_PER_GROUP(sb), ino);
-		if (ino >= EXT4_INODES_PER_GROUP(sb)) {
-			if (++group == ngroups)
-				group = 0;
-			continue;
-		}
+		if (ino >= EXT4_INODES_PER_GROUP(sb))
+			goto next_group;
 		if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
 			ext4_error(sb, "reserved inode found cleared - "
 				   "inode=%lu", ino + 1);
@@ -769,6 +766,9 @@ repeat_in_this_group:
 			goto got; /* we grabbed the inode! */
 		if (ino < EXT4_INODES_PER_GROUP(sb))
 			goto repeat_in_this_group;
+next_group:
+		if (++group == ngroups)
+			group = 0;
 	}
 	err = -ENOSPC;
 	goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ba33c67..dd32a2e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -555,14 +555,13 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		int ret;
 		unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-		if (retval != map->m_len) {
-			printk("ES len assertion failed for inode: %lu "
-			       "retval %d != map->m_len %d "
-			       "in %s (lookup)\n", inode->i_ino, retval,
-			       map->m_len, __func__);
+		if (unlikely(retval != map->m_len)) {
+			ext4_warning(inode->i_sb,
+				     "ES len assertion failed for inode "
+				     "%lu: retval %d != map->m_len %d",
+				     inode->i_ino, retval, map->m_len);
+			WARN_ON(1);
 		}
-#endif
 
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -656,14 +655,13 @@ found:
 		int ret;
 		unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-		if (retval != map->m_len) {
-			printk("ES len assertion failed for inode: %lu "
-			       "retval %d != map->m_len %d "
-			       "in %s (allocation)\n", inode->i_ino, retval,
-			       map->m_len, __func__);
+		if (unlikely(retval != map->m_len)) {
+			ext4_warning(inode->i_sb,
+				     "ES len assertion failed for inode "
+				     "%lu: retval %d != map->m_len %d",
+				     inode->i_ino, retval, map->m_len);
+			WARN_ON(1);
 		}
-#endif
 
 		/*
 		 * If the extent has been zeroed out, we don't need to update
@@ -1637,14 +1635,13 @@ add_delayed:
 		int ret;
 		unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-		if (retval != map->m_len) {
-			printk("ES len assertion failed for inode: %lu "
-			       "retval %d != map->m_len %d "
-			       "in %s (lookup)\n", inode->i_ino, retval,
-			       map->m_len, __func__);
+		if (unlikely(retval != map->m_len)) {
+			ext4_warning(inode->i_sb,
+				     "ES len assertion failed for inode "
+				     "%lu: retval %d != map->m_len %d",
+				     inode->i_ino, retval, map->m_len);
+			WARN_ON(1);
 		}
-#endif
 
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bca26f3..36b141e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5481,6 +5481,7 @@ static void __exit ext4_exit_fs(void)
 	kset_unregister(ext4_kset);
 	ext4_exit_system_zone();
 	ext4_exit_pageio();
+	ext4_exit_es();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 6599222..65343c3 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -730,14 +730,14 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0eda527..72a5d5b 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1223,30 +1223,46 @@ static int fuse_direntplus_link(struct file *file,
 		if (name.name[1] == '.' && name.len == 2)
 			return 0;
 	}
+
+	if (invalid_nodeid(o->nodeid))
+		return -EIO;
+	if (!fuse_valid_type(o->attr.mode))
+		return -EIO;
+
 	fc = get_fuse_conn(dir);
 
 	name.hash = full_name_hash(name.name, name.len);
 	dentry = d_lookup(parent, &name);
-	if (dentry && dentry->d_inode) {
+	if (dentry) {
 		inode = dentry->d_inode;
-		if (get_node_id(inode) == o->nodeid) {
+		if (!inode) {
+			d_drop(dentry);
+		} else if (get_node_id(inode) != o->nodeid ||
+			   ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
+			err = d_invalidate(dentry);
+			if (err)
+				goto out;
+		} else if (is_bad_inode(inode)) {
+			err = -EIO;
+			goto out;
+		} else {
 			struct fuse_inode *fi;
 			fi = get_fuse_inode(inode);
 			spin_lock(&fc->lock);
 			fi->nlookup++;
 			spin_unlock(&fc->lock);
 
+			fuse_change_attributes(inode, &o->attr,
+					       entry_attr_timeout(o),
+					       attr_version);
+
 			/*
 			 * The other branch to 'found' comes via fuse_iget()
 			 * which bumps nlookup inside
 			 */
 			goto found;
 		}
-		err = d_invalidate(dentry);
-		if (err)
-			goto out;
 		dput(dentry);
-		dentry = NULL;
 	}
 
 	dentry = d_alloc(parent, &name);
@@ -1259,25 +1275,30 @@ static int fuse_direntplus_link(struct file *file,
 	if (!inode)
 		goto out;
 
-	alias = d_materialise_unique(dentry, inode);
-	err = PTR_ERR(alias);
-	if (IS_ERR(alias))
-		goto out;
+	if (S_ISDIR(inode->i_mode)) {
+		mutex_lock(&fc->inst_mutex);
+		alias = fuse_d_add_directory(dentry, inode);
+		mutex_unlock(&fc->inst_mutex);
+		err = PTR_ERR(alias);
+		if (IS_ERR(alias)) {
+			iput(inode);
+			goto out;
+		}
+	} else {
+		alias = d_splice_alias(inode, dentry);
+	}
+
 	if (alias) {
 		dput(dentry);
 		dentry = alias;
 	}
 
 found:
-	fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o),
-			       attr_version);
-
 	fuse_change_entry_timeout(dentry, o);
 
 	err = 0;
 out:
-	if (dentry)
-		dput(dentry);
+	dput(dentry);
 	return err;
 }
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 01bfe76..41e491b 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -64,12 +64,17 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
 				   nlm_init->protocol, nlm_version,
 				   nlm_init->hostname, nlm_init->noresvport,
 				   nlm_init->net);
-	if (host == NULL) {
-		lockd_down(nlm_init->net);
-		return ERR_PTR(-ENOLCK);
-	}
+	if (host == NULL)
+		goto out_nohost;
+	if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
+		goto out_nobind;
 
 	return host;
+out_nobind:
+	nlmclnt_release_host(host);
+out_nohost:
+	lockd_down(nlm_init->net);
+	return ERR_PTR(-ENOLCK);
 }
 EXPORT_SYMBOL_GPL(nlmclnt_init);
 
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 9760ecb..acd3947 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -125,14 +125,15 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 {
 	struct nlm_args	*argp = &req->a_args;
 	struct nlm_lock	*lock = &argp->lock;
+	char *nodename = req->a_host->h_rpcclnt->cl_nodename;
 
 	nlmclnt_next_cookie(&argp->cookie);
 	memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
-	lock->caller  = utsname()->nodename;
+	lock->caller  = nodename;
 	lock->oh.data = req->a_owner;
 	lock->oh.len  = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
 				(unsigned int)fl->fl_u.nfs_fl.owner->pid,
-				utsname()->nodename);
+				nodename);
 	lock->svid = fl->fl_u.nfs_fl.owner->pid;
 	lock->fl.fl_start = fl->fl_start;
 	lock->fl.fl_end = fl->fl_end;
diff --git a/fs/namei.c b/fs/namei.c
index 8b61d10..89a612e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3671,15 +3671,11 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
 		return -EINVAL;
 	/*
-	 * To use null names we require CAP_DAC_READ_SEARCH
-	 * This ensures that not everyone will be able to create
-	 * handlink using the passed filedescriptor.
+	 * Using empty names is equivalent to using AT_SYMLINK_FOLLOW
+	 * on /proc/self/fd/<fd>.
 	 */
-	if (flags & AT_EMPTY_PATH) {
-		if (!capable(CAP_DAC_READ_SEARCH))
-			return -ENOENT;
+	if (flags & AT_EMPTY_PATH)
 		how = LOOKUP_EMPTY;
-	}
 
 	if (flags & AT_SYMLINK_FOLLOW)
 		how |= LOOKUP_FOLLOW;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index af6e806..941246f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -463,7 +463,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
-		nfs_setsecurity(inode, fattr, label);
 	dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
 		inode->i_sb->s_id,
 		(long long)NFS_FILEID(inode),
@@ -963,9 +962,15 @@ EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	
+	int ret;
+
 	if (mapping->nrpages != 0) {
-		int ret = invalidate_inode_pages2(mapping);
+		if (S_ISREG(inode->i_mode)) {
+			ret = nfs_sync_mapping(mapping);
+			if (ret < 0)
+				return ret;
+		}
+		ret = invalidate_inode_pages2(mapping);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cf11799..108a774 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3071,15 +3071,13 @@ struct rpc_clnt *
 nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name,
 			    struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
+	struct rpc_clnt *client = NFS_CLIENT(dir);
 	int status;
-	struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir));
 
 	status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, NULL);
-	if (status < 0) {
-		rpc_shutdown_client(client);
+	if (status < 0)
 		return ERR_PTR(status);
-	}
-	return client;
+	return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
 }
 
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c74d616..3850b01 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1118,11 +1118,11 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 				len, ((char *)p - (char *)q) + 4);
 		BUG();
 	}
-	len = (char *)p - (char *)q - (bmval_len << 2);
 	*q++ = htonl(bmval0);
 	*q++ = htonl(bmval1);
 	if (bmval_len == 3)
 		*q++ = htonl(bmval2);
+	len = (char *)p - (char *)(q + 1);
 	*q = htonl(len);
 
 /* out: */
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 71fdc0d..f6db66d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2478,6 +2478,10 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 	if (server->flags & NFS_MOUNT_NOAC)
 		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
 
+	if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL)
+		if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS)
+			sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
 	if (IS_ERR(s)) {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0d4c410..419572f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1524,7 +1524,7 @@ static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\
-		1 + 1 + 0 + /* eir_flags, spr_how, SP4_NONE (for now) */\
+		1 + 1 + 2 + /* eir_flags, spr_how, spo_must_enforce & _allow */\
 		2 + /*eir_server_owner.so_minor_id */\
 		/* eir_server_owner.so_major_id<> */\
 		XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1852f53..5e609b1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1259,6 +1259,8 @@ static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
 	struct svc_cred *cr = &rqstp->rq_cred;
 	u32 service;
 
+	if (!cr->cr_gss_mech)
+		return false;
 	service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor);
 	return service == RPC_GSS_SVC_INTEGRITY ||
 	       service == RPC_GSS_SVC_PRIVACY;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0c0f3ea9..c2a4701 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3360,7 +3360,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 		8 /* eir_clientid */ +
 		4 /* eir_sequenceid */ +
 		4 /* eir_flags */ +
-		4 /* spr_how (SP4_NONE) */ +
+		4 /* spr_how */ +
+		8 /* spo_must_enforce, spo_must_allow */ +
 		8 /* so_minor_id */ +
 		4 /* so_major_id.len */ +
 		(XDR_QUADLEN(major_id_sz) * 4) +
@@ -3372,8 +3373,6 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	WRITE32(exid->seqid);
 	WRITE32(exid->flags);
 
-	/* state_protect4_r. Currently only support SP4_NONE */
-	BUG_ON(exid->spa_how != SP4_NONE);
 	WRITE32(exid->spa_how);
 	switch (exid->spa_how) {
 	case SP4_NONE:
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 998b17e..9f6b96a 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2965,6 +2965,11 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			to = map_end & (PAGE_CACHE_SIZE - 1);
 
 		page = find_or_create_page(mapping, page_index, GFP_NOFS);
+		if (!page) {
+			ret = -ENOMEM;
+			mlog_errno(ret);
+			break;
+		}
 
 		/*
 		 * In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page
diff --git a/fs/open.c b/fs/open.c
index d53e298..7931f76 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -823,7 +823,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 	int lookup_flags = 0;
 	int acc_mode;
 
-	if (flags & O_CREAT)
+	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
 	else
 		op->mode = 0;
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 33532f7..a958444 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -19,12 +19,13 @@
 /*
  * LOCKING:
  *
- * We rely on new Alexander Viro's super-block locking.
+ * These guys are evicted from procfs as the very first step in ->kill_sb().
  *
  */
 
-static int show_version(struct seq_file *m, struct super_block *sb)
+static int show_version(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	char *format;
 
 	if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
@@ -66,8 +67,9 @@ static int show_version(struct seq_file *m, struct super_block *sb)
 #define DJP( x ) le32_to_cpu( jp -> x )
 #define JF( x ) ( r -> s_journal -> x )
 
-static int show_super(struct seq_file *m, struct super_block *sb)
+static int show_super(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 
 	seq_printf(m, "state: \t%s\n"
@@ -128,8 +130,9 @@ static int show_super(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-static int show_per_level(struct seq_file *m, struct super_block *sb)
+static int show_per_level(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 	int level;
 
@@ -186,8 +189,9 @@ static int show_per_level(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-static int show_bitmap(struct seq_file *m, struct super_block *sb)
+static int show_bitmap(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 
 	seq_printf(m, "free_block: %lu\n"
@@ -218,8 +222,9 @@ static int show_bitmap(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+static int show_on_disk_super(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
 	struct reiserfs_super_block *rs = sb_info->s_rs;
 	int hash_code = DFL(s_hash_function_code);
@@ -261,8 +266,9 @@ static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-static int show_oidmap(struct seq_file *m, struct super_block *sb)
+static int show_oidmap(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
 	struct reiserfs_super_block *rs = sb_info->s_rs;
 	unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
@@ -291,8 +297,9 @@ static int show_oidmap(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-static int show_journal(struct seq_file *m, struct super_block *sb)
+static int show_journal(struct seq_file *m, void *unused)
 {
+	struct super_block *sb = m->private;
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 	struct reiserfs_super_block *rs = r->s_rs;
 	struct journal_params *jp = &rs->s_v1.s_journal;
@@ -383,92 +390,24 @@ static int show_journal(struct seq_file *m, struct super_block *sb)
 	return 0;
 }
 
-/* iterator */
-static int test_sb(struct super_block *sb, void *data)
-{
-	return data == sb;
-}
-
-static int set_sb(struct super_block *sb, void *data)
-{
-	return -ENOENT;
-}
-
-struct reiserfs_seq_private {
-	struct super_block *sb;
-	int (*show) (struct seq_file *, struct super_block *);
-};
-
-static void *r_start(struct seq_file *m, loff_t * pos)
-{
-	struct reiserfs_seq_private *priv = m->private;
-	loff_t l = *pos;
-
-	if (l)
-		return NULL;
-
-	if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb)))
-		return NULL;
-
-	up_write(&priv->sb->s_umount);
-	return priv->sb;
-}
-
-static void *r_next(struct seq_file *m, void *v, loff_t * pos)
-{
-	++*pos;
-	if (v)
-		deactivate_super(v);
-	return NULL;
-}
-
-static void r_stop(struct seq_file *m, void *v)
-{
-	if (v)
-		deactivate_super(v);
-}
-
-static int r_show(struct seq_file *m, void *v)
-{
-	struct reiserfs_seq_private *priv = m->private;
-	return priv->show(m, v);
-}
-
-static const struct seq_operations r_ops = {
-	.start = r_start,
-	.next = r_next,
-	.stop = r_stop,
-	.show = r_show,
-};
-
 static int r_open(struct inode *inode, struct file *file)
 {
-	struct reiserfs_seq_private *priv;
-	int ret = seq_open_private(file, &r_ops,
-				   sizeof(struct reiserfs_seq_private));
-
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		priv = m->private;
-		priv->sb = proc_get_parent_data(inode);
-		priv->show = PDE_DATA(inode);
-	}
-	return ret;
+	return single_open(file, PDE_DATA(inode), 
+				proc_get_parent_data(inode));
 }
 
 static const struct file_operations r_file_operations = {
 	.open = r_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = seq_release_private,
-	.owner = THIS_MODULE,
+	.release = single_release,
 };
 
 static struct proc_dir_entry *proc_info_root = NULL;
 static const char proc_info_root_name[] = "fs/reiserfs";
 
 static void add_file(struct super_block *sb, char *name,
-		     int (*func) (struct seq_file *, struct super_block *))
+		     int (*func) (struct seq_file *, void *))
 {
 	proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
 			 &r_file_operations, func);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index f8a23c3..e2e202a 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -499,6 +499,7 @@ int remove_save_link(struct inode *inode, int truncate)
 static void reiserfs_kill_sb(struct super_block *s)
 {
 	if (REISERFS_SB(s)) {
+		reiserfs_proc_info_done(s);
 		/*
 		 * Force any pending inode evictions to occur now. Any
 		 * inodes to be removed that have extended attributes
@@ -554,8 +555,6 @@ static void reiserfs_put_super(struct super_block *s)
 				 REISERFS_SB(s)->reserved_blocks);
 	}
 
-	reiserfs_proc_info_done(s);
-
 	reiserfs_write_unlock(s);
 	mutex_destroy(&REISERFS_SB(s)->lock);
 	kfree(s->s_fs_info);
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index 07d735a..e5869b5 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -39,6 +39,9 @@ typedef struct xfs_timestamp {
  * There is a very similar struct icdinode in xfs_inode which matches the
  * layout of the first 96 bytes of this structure, but is kept in native
  * format instead of big endian.
+ *
+ * Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
+ * padding field for v3 inodes.
  */
 typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b78481f..bb262c2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -896,7 +896,6 @@ xfs_dinode_to_disk(
 	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
 	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
 	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
-	to->di_flushiter = cpu_to_be16(from->di_flushiter);
 	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
 	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
 	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
@@ -924,6 +923,9 @@ xfs_dinode_to_disk(
 		to->di_lsn = cpu_to_be64(from->di_lsn);
 		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &from->di_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = cpu_to_be16(from->di_flushiter);
 	}
 }
 
@@ -1029,10 +1031,14 @@ xfs_dinode_calc_crc(
 /*
  * Read the disk inode attributes into the in-core inode structure.
  *
- * If we are initialising a new inode and we are not utilising the
- * XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new inode core
- * with a random generation number. If we are keeping inodes around, we need to
- * read the inode cluster to get the existing generation number off disk.
+ * For version 5 superblocks, if we are initialising a new inode and we are not
+ * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
+ * inode core with a random generation number. If we are keeping inodes around,
+ * we need to read the inode cluster to get the existing generation number off
+ * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
+ * format) then log recovery is dependent on the di_flushiter field being
+ * initialised from the current on-disk value and hence we must also read the
+ * inode off disk.
  */
 int
 xfs_iread(
@@ -1054,6 +1060,7 @@ xfs_iread(
 
 	/* shortcut IO on inode allocation if possible */
 	if ((iget_flags & XFS_IGET_CREATE) &&
+	    xfs_sb_version_hascrc(&mp->m_sb) &&
 	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
 		/* initialise the on-disk inode core */
 		memset(&ip->i_d, 0, sizeof(ip->i_d));
@@ -2882,12 +2889,18 @@ xfs_iflush_int(
 			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
 		goto corrupt_out;
 	}
+
 	/*
-	 * bump the flush iteration count, used to detect flushes which
-	 * postdate a log record during recovery. This is redundant as we now
-	 * log every change and hence this can't happen. Still, it doesn't hurt.
+	 * Inode item log recovery for v1/v2 inodes are dependent on the
+	 * di_flushiter count for correct sequencing. We bump the flush
+	 * iteration count so we can detect flushes which postdate a log record
+	 * during recovery. This is redundant as we now log every change and
+	 * hence this can't happen but we need to still do it to ensure
+	 * backwards compatibility with old kernels that predate logging all
+	 * inode changes.
 	 */
-	ip->i_d.di_flushiter++;
+	if (ip->i_d.di_version < 3)
+		ip->i_d.di_flushiter++;
 
 	/*
 	 * Copy the dirty parts of the inode into the on-disk
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 6fcc910a..7681b19 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2592,8 +2592,16 @@ xlog_recover_inode_pass2(
 		goto error;
 	}
 
-	/* Skip replay when the on disk inode is newer than the log one */
-	if (dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+	/*
+	 * di_flushiter is only valid for v1/2 inodes. All changes for v3 inodes
+	 * are transactional and if ordering is necessary we can determine that
+	 * more accurately by the LSN field in the V3 inode core. Don't trust
+	 * the inode versions we might be changing them here - use the
+	 * superblock flag to determine whether we need to look at di_flushiter
+	 * to skip replay when the on disk inode is newer than the log one
+	 */
+	if (!xfs_sb_version_hascrc(&mp->m_sb) &&
+	    dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
 		/*
 		 * Deal with the wrap case, DI_MAX_FLUSH is less
 		 * than smaller numbers
@@ -2608,6 +2616,7 @@ xlog_recover_inode_pass2(
 			goto error;
 		}
 	}
+
 	/* Take the opportunity to reset the flush iteration count */
 	dicp->di_flushiter = 0;