Merge tag 'for-4.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - when NR_CPUS is large, a SRCU structure can significantly inflate
   size of the main filesystem structure that would not be possible to
   allocate by kmalloc, so the kvalloc fallback is used

 - improved error handling

 - fix endiannes when printing some filesystem attributes via sysfs,
   this is could happen when a filesystem is moved between different
   endianity hosts

 - send fixes: the NO_HOLE mode should not send a write operation for a
   file hole

 - fix log replay for for special files followed by file hardlinks

 - fix log replay failure after unlink and link combination

 - fix max chunk size calculation for DUP allocation

* tag 'for-4.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  Btrfs: fix log replay failure after unlink and link combination
  Btrfs: fix log replay failure after linking special file and fsync
  Btrfs: send, fix issuing write op when processing hole in no data mode
  btrfs: use proper endianness accessors for super_copy
  btrfs: alloc_chunk: fix DUP stripe size handling
  btrfs: Handle btrfs_set_extent_delalloc failure in relocate_file_extent_cluster
  btrfs: handle failure of add_pending_csums
  btrfs: use kvzalloc to allocate btrfs_fs_info

10 files changed, 191 insertions, 47 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1a462ab85c49..da308774b8a4 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2974,7 +2974,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 	kfree(fs_info->super_copy);
 	kfree(fs_info->super_for_commit);
 	security_free_mnt_opts(&fs_info->security_opts);
-	kfree(fs_info);
+	kvfree(fs_info);
 }
 
 /* tree mod log functions from ctree.c */
@@ -3095,7 +3095,10 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
 			  u64 inode_objectid, u64 ref_objectid, int ins_len,
 			  int cow);
 
-int btrfs_find_name_in_ext_backref(struct btrfs_path *path,
+int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot,
+			       const char *name,
+			       int name_len, struct btrfs_inode_ref **ref_ret);
+int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot,
 				   u64 ref_objectid, const char *name,
 				   int name_len,
 				   struct btrfs_inode_extref **extref_ret);
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 39c968f80157..65e1a76bf755 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -22,10 +22,10 @@
 #include "transaction.h"
 #include "print-tree.h"
 
-static int find_name_in_backref(struct btrfs_path *path, const char *name,
-			 int name_len, struct btrfs_inode_ref **ref_ret)
+int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot,
+			       const char *name,
+			       int name_len, struct btrfs_inode_ref **ref_ret)
 {
-	struct extent_buffer *leaf;
 	struct btrfs_inode_ref *ref;
 	unsigned long ptr;
 	unsigned long name_ptr;
@@ -33,9 +33,8 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name,
 	u32 cur_offset = 0;
 	int len;
 
-	leaf = path->nodes[0];
-	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+	item_size = btrfs_item_size_nr(leaf, slot);
+	ptr = btrfs_item_ptr_offset(leaf, slot);
 	while (cur_offset < item_size) {
 		ref = (struct btrfs_inode_ref *)(ptr + cur_offset);
 		len = btrfs_inode_ref_name_len(leaf, ref);
@@ -44,18 +43,19 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name,
 		if (len != name_len)
 			continue;
 		if (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) {
-			*ref_ret = ref;
+			if (ref_ret)
+				*ref_ret = ref;
 			return 1;
 		}
 	}
 	return 0;
 }
 
-int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid,
+int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot,
+				   u64 ref_objectid,
 				   const char *name, int name_len,
 				   struct btrfs_inode_extref **extref_ret)
 {
-	struct extent_buffer *leaf;
 	struct btrfs_inode_extref *extref;
 	unsigned long ptr;
 	unsigned long name_ptr;
@@ -63,9 +63,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid,
 	u32 cur_offset = 0;
 	int ref_name_len;
 
-	leaf = path->nodes[0];
-	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+	item_size = btrfs_item_size_nr(leaf, slot);
+	ptr = btrfs_item_ptr_offset(leaf, slot);
 
 	/*
 	 * Search all extended backrefs in this item. We're only
@@ -113,7 +112,9 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
 		return ERR_PTR(ret);
 	if (ret > 0)
 		return NULL;
-	if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref))
+	if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0],
+					    ref_objectid, name, name_len,
+					    &extref))
 		return NULL;
 	return extref;
 }
@@ -155,7 +156,8 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
 	 * This should always succeed so error here will make the FS
 	 * readonly.
 	 */
-	if (!btrfs_find_name_in_ext_backref(path, ref_objectid,
+	if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0],
+					    ref_objectid,
 					    name, name_len, &extref)) {
 		btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL);
 		ret = -EROFS;
@@ -225,7 +227,8 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	} else if (ret < 0) {
 		goto out;
 	}
-	if (!find_name_in_backref(path, name, name_len, &ref)) {
+	if (!btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+					name, name_len, &ref)) {
 		ret = -ENOENT;
 		search_ext_refs = 1;
 		goto out;
@@ -293,7 +296,9 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans,
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      ins_len);
 	if (ret == -EEXIST) {
-		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+		if (btrfs_find_name_in_ext_backref(path->nodes[0],
+						   path->slots[0],
+						   ref_objectid,
 						   name, name_len, NULL))
 			goto out;
 
@@ -351,7 +356,8 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 	if (ret == -EEXIST) {
 		u32 old_size;
 
-		if (find_name_in_backref(path, name, name_len, &ref))
+		if (btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+					       name, name_len, &ref))
 			goto out;
 
 		old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
@@ -365,7 +371,9 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 		ret = 0;
 	} else if (ret < 0) {
 		if (ret == -EOVERFLOW) {
-			if (find_name_in_backref(path, name, name_len, &ref))
+			if (btrfs_find_name_in_backref(path->nodes[0],
+						       path->slots[0],
+						       name, name_len, &ref))
 				ret = -EEXIST;
 			else
 				ret = -EMLINK;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a79299a89b7d..f53470112670 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2043,12 +2043,15 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 			     struct inode *inode, struct list_head *list)
 {
 	struct btrfs_ordered_sum *sum;
+	int ret;
 
 	list_for_each_entry(sum, list, list) {
 		trans->adding_csums = true;
-		btrfs_csum_file_blocks(trans,
+		ret = btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
 		trans->adding_csums = false;
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
@@ -3062,7 +3065,11 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	add_pending_csums(trans, inode, &ordered_extent->list);
+	ret = add_pending_csums(trans, inode, &ordered_extent->list);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto out;
+	}
 
 	btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 	ret = btrfs_update_inode_fallback(trans, root, inode);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f0c3f00e97cb..cd2298d185dd 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3268,8 +3268,22 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			nr++;
 		}
 
-		btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL,
-					  0);
+		ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
+						NULL, 0);
+		if (ret) {
+			unlock_page(page);
+			put_page(page);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+							 PAGE_SIZE);
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+			                               PAGE_SIZE);
+
+			clear_extent_bits(&BTRFS_I(inode)->io_tree,
+					  page_start, page_end,
+					  EXTENT_LOCKED | EXTENT_BOUNDARY);
+			goto out;
+
+		}
 		set_page_dirty(page);
 
 		unlock_extent(&BTRFS_I(inode)->io_tree,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index f306c608dc28..484e2af793de 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5005,6 +5005,9 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
+		return send_update_extent(sctx, offset, end - offset);
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 6e71a2a78363..4b817947e00f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1545,7 +1545,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	 * it for searching for existing supers, so this lets us do that and
 	 * then open_ctree will properly initialize everything later.
 	 */
-	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
+	fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
 	if (!fs_info) {
 		error = -ENOMEM;
 		goto error_sec_opts;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a8bafed931f4..d11c70bff5a9 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
 }
 
 BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,8 +433,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n",
-			fs_info->super_copy->sectorsize);
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
 }
 
 BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -444,8 +443,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n",
-			fs_info->super_copy->sectorsize);
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
 }
 
 BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04f07144b45c..9220f004001c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 
 	super = fs_info->super_copy;
 
+	/* update latest btrfs_super_block::chunk_root refs */
 	root_item = &fs_info->chunk_root->root_item;
-	super->chunk_root = root_item->bytenr;
-	super->chunk_root_generation = root_item->generation;
-	super->chunk_root_level = root_item->level;
+	btrfs_set_super_chunk_root(super, root_item->bytenr);
+	btrfs_set_super_chunk_root_generation(super, root_item->generation);
+	btrfs_set_super_chunk_root_level(super, root_item->level);
 
+	/* update latest btrfs_super_block::root refs */
 	root_item = &fs_info->tree_root->root_item;
-	super->root = root_item->bytenr;
-	super->generation = root_item->generation;
-	super->root_level = root_item->level;
+	btrfs_set_super_root(super, root_item->bytenr);
+	btrfs_set_super_generation(super, root_item->generation);
+	btrfs_set_super_root_level(super, root_item->level);
+
 	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		super->cache_generation = root_item->generation;
+		btrfs_set_super_cache_generation(super, root_item->generation);
 	if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
-		super->uuid_tree_generation = root_item->generation;
+		btrfs_set_super_uuid_tree_generation(super,
+						     root_item->generation);
 }
 
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 4fd19b4d6675..434457794c27 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -967,7 +967,9 @@ static noinline int backref_in_log(struct btrfs_root *log,
 	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
 
 	if (key->type == BTRFS_INODE_EXTREF_KEY) {
-		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+		if (btrfs_find_name_in_ext_backref(path->nodes[0],
+						   path->slots[0],
+						   ref_objectid,
 						   name, namelen, NULL))
 			match = 1;
 
@@ -1191,7 +1193,8 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 	read_extent_buffer(eb, *name, (unsigned long)&extref->name,
 			   *namelen);
 
-	*index = btrfs_inode_extref_index(eb, extref);
+	if (index)
+		*index = btrfs_inode_extref_index(eb, extref);
 	if (parent_objectid)
 		*parent_objectid = btrfs_inode_extref_parent(eb, extref);
 
@@ -1212,12 +1215,102 @@ static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 
 	read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);
 
-	*index = btrfs_inode_ref_index(eb, ref);
+	if (index)
+		*index = btrfs_inode_ref_index(eb, ref);
 
 	return 0;
 }
 
 /*
+ * Take an inode reference item from the log tree and iterate all names from the
+ * inode reference item in the subvolume tree with the same key (if it exists).
+ * For any name that is not in the inode reference item from the log tree, do a
+ * proper unlink of that name (that is, remove its entry from the inode
+ * reference item and both dir index keys).
+ */
+static int unlink_old_inode_refs(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_inode *inode,
+				 struct extent_buffer *log_eb,
+				 int log_slot,
+				 struct btrfs_key *key)
+{
+	int ret;
+	unsigned long ref_ptr;
+	unsigned long ref_end;
+	struct extent_buffer *eb;
+
+again:
+	btrfs_release_path(path);
+	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (ret < 0)
+		goto out;
+
+	eb = path->nodes[0];
+	ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
+	ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]);
+	while (ref_ptr < ref_end) {
+		char *name = NULL;
+		int namelen;
+		u64 parent_id;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY) {
+			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+						NULL, &parent_id);
+		} else {
+			parent_id = key->offset;
+			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+					     NULL);
+		}
+		if (ret)
+			goto out;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
+							     parent_id, name,
+							     namelen, NULL);
+		else
+			ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
+							 namelen, NULL);
+
+		if (!ret) {
+			struct inode *dir;
+
+			btrfs_release_path(path);
+			dir = read_one_inode(root, parent_id);
+			if (!dir) {
+				ret = -ENOENT;
+				kfree(name);
+				goto out;
+			}
+			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+						 inode, name, namelen);
+			kfree(name);
+			iput(dir);
+			if (ret)
+				goto out;
+			goto again;
+		}
+
+		kfree(name);
+		ref_ptr += namelen;
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ref_ptr += sizeof(struct btrfs_inode_extref);
+		else
+			ref_ptr += sizeof(struct btrfs_inode_ref);
+	}
+	ret = 0;
+ out:
+	btrfs_release_path(path);
+	return ret;
+}
+
+/*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
  * root is the destination we are replaying into, and path is for temp
@@ -1345,6 +1438,19 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 		}
 	}
 
+	/*
+	 * Before we overwrite the inode reference item in the subvolume tree
+	 * with the item from the log tree, we must unlink all names from the
+	 * parent directory that are in the subvolume's tree inode reference
+	 * item, otherwise we end up with an inconsistent subvolume tree where
+	 * dir index entries exist for a name but there is no inode reference
+	 * item with the same name.
+	 */
+	ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot,
+				    key);
+	if (ret)
+		goto out;
+
 	/* finally write the back reference in the inode */
 	ret = overwrite_item(trans, root, path, eb, slot, key);
 out:
@@ -5853,7 +5959,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * this will force the logging code to walk the dentry chain
 	 * up for the file
 	 */
-	if (S_ISREG(inode->vfs_inode.i_mode))
+	if (!S_ISDIR(inode->vfs_inode.i_mode))
 		inode->last_unlink_trans = trans->transid;
 
 	/*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2ceb924ca0d6..b2d05c6b1c56 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4829,10 +4829,13 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	ndevs = min(ndevs, devs_max);
 
 	/*
-	 * the primary goal is to maximize the number of stripes, so use as many
-	 * devices as possible, even if the stripes are not maximum sized.
+	 * The primary goal is to maximize the number of stripes, so use as
+	 * many devices as possible, even if the stripes are not maximum sized.
+	 *
+	 * The DUP profile stores more than one stripe per device, the
+	 * max_avail is the total size so we have to adjust.
 	 */
-	stripe_size = devices_info[ndevs-1].max_avail;
+	stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes);
 	num_stripes = ndevs * dev_stripes;
 
 	/*
@@ -4867,8 +4870,6 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			stripe_size = devices_info[ndevs-1].max_avail;
 	}
 
-	stripe_size = div_u64(stripe_size, dev_stripes);
-
 	/* align to BTRFS_STRIPE_LEN */
 	stripe_size = round_down(stripe_size, BTRFS_STRIPE_LEN);