Merge tag 'for-5.13-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Error handling improvements, caught by error injection:

   - handle errors during checksum deletion

   - set error on mapping when ordered extent io cannot be finished

   - inode link count fixup in tree-log

   - missing return value checks for inode updates in tree-log

   - abort transaction in rename exchange if adding second reference
     fails

  Fixes:

   - fix fsync failure after writes to prealloc extents

   - fix deadlock when cloning inline extents and low on available space

   - fix compressed writes that cross stripe boundary"

* tag 'for-5.13-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  MAINTAINERS: add btrfs IRC link
  btrfs: fix deadlock when cloning inline extents and low on available space
  btrfs: fix fsync failure and transaction abort after writes to prealloc extents
  btrfs: abort in rename_exchange if we fail to insert the second ref
  btrfs: check error value from btrfs_update_inode in tree log
  btrfs: fixup error handling in fixup_inode_link_counts
  btrfs: mark ordered extent and inode with error if we fail to finish
  btrfs: return errors from btrfs_del_csums in cleanup_ref_head
  btrfs: fix error handling in btrfs_del_csums
  btrfs: fix compressed writes that cross stripe boundary

Author: torvalds

MAINTAINERS

@@ -3877,6 +3877,7 @@ L:	[email protected]
 S:	Maintained
 W:	http://btrfs.wiki.kernel.org/
 Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
+C:	irc://irc.libera.chat/btrfs
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git
 F:	Documentation/filesystems/btrfs.rst
 F:	fs/btrfs/

fs/btrfs/compression.c

@@ -457,18 +457,25 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	bytes_left = compressed_len;
 	for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
 		int submit = 0;
-		int len;
+		int len = 0;
 
 		page = compressed_pages[pg_index];
 		page->mapping = inode->vfs_inode.i_mapping;
 		if (bio->bi_iter.bi_size)
 			submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio,
 							  0);
 
-		if (pg_index == 0 && use_append)
-			len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0);
-		else
-			len = bio_add_page(bio, page, PAGE_SIZE, 0);
+		/*
+		 * Page can only be added to bio if the current bio fits in
+		 * stripe.
+		 */
+		if (!submit) {
+			if (pg_index == 0 && use_append)
+				len = bio_add_zone_append_page(bio, page,
+							       PAGE_SIZE, 0);
+			else
+				len = bio_add_page(bio, page, PAGE_SIZE, 0);
+		}
 
 		page->mapping = NULL;
 		if (submit || len < PAGE_SIZE) {

fs/btrfs/extent-tree.c

@@ -1868,7 +1868,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 	trace_run_delayed_ref_head(fs_info, head, 0);
 	btrfs_delayed_ref_unlock(head);
 	btrfs_put_delayed_ref_head(head);
-	return 0;
+	return ret;
 }
 
 static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head(

fs/btrfs/file-item.c

@@ -788,7 +788,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 	u64 end_byte = bytenr + len;
 	u64 csum_end;
 	struct extent_buffer *leaf;
-	int ret;
+	int ret = 0;
 	const u32 csum_size = fs_info->csum_size;
 	u32 blocksize_bits = fs_info->sectorsize_bits;
 
@@ -806,6 +806,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 
 		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 		if (ret > 0) {
+			ret = 0;
 			if (path->slots[0] == 0)
 				break;
 			path->slots[0]--;
@@ -862,7 +863,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			ret = btrfs_del_items(trans, root, path,
 					      path->slots[0], del_nr);
 			if (ret)
-				goto out;
+				break;
 			if (key.offset == bytenr)
 				break;
 		} else if (key.offset < bytenr && csum_end > end_byte) {
@@ -906,8 +907,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			ret = btrfs_split_item(trans, root, path, &key, offset);
 			if (ret && ret != -EAGAIN) {
 				btrfs_abort_transaction(trans, ret);
-				goto out;
+				break;
 			}
+			ret = 0;
 
 			key.offset = end_byte - 1;
 		} else {
@@ -917,12 +919,41 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		}
 		btrfs_release_path(path);
 	}
-	ret = 0;
-out:
 	btrfs_free_path(path);
 	return ret;
 }
 
+static int find_next_csum_offset(struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 u64 *next_offset)
+{
+	const u32 nritems = btrfs_header_nritems(path->nodes[0]);
+	struct btrfs_key found_key;
+	int slot = path->slots[0] + 1;
+	int ret;
+
+	if (nritems == 0 || slot >= nritems) {
+		ret = btrfs_next_leaf(root, path);
+		if (ret < 0) {
+			return ret;
+		} else if (ret > 0) {
+			*next_offset = (u64)-1;
+			return 0;
+		}
+		slot = path->slots[0];
+	}
+
+	btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
+
+	if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
+	    found_key.type != BTRFS_EXTENT_CSUM_KEY)
+		*next_offset = (u64)-1;
+	else
+		*next_offset = found_key.offset;
+
+	return 0;
+}
+
 int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums)
@@ -938,7 +969,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 	u64 total_bytes = 0;
 	u64 csum_offset;
 	u64 bytenr;
-	u32 nritems;
 	u32 ins_size;
 	int index = 0;
 	int found_next;
@@ -981,26 +1011,10 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			goto insert;
 		}
 	} else {
-		int slot = path->slots[0] + 1;
-		/* we didn't find a csum item, insert one */
-		nritems = btrfs_header_nritems(path->nodes[0]);
-		if (!nritems || (path->slots[0] >= nritems - 1)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0) {
-				goto out;
-			} else if (ret > 0) {
-				found_next = 1;
-				goto insert;
-			}
-			slot = path->slots[0];
-		}
-		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
-		if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
-		    found_key.type != BTRFS_EXTENT_CSUM_KEY) {
-			found_next = 1;
-			goto insert;
-		}
-		next_offset = found_key.offset;
+		/* We didn't find a csum item, insert one. */
+		ret = find_next_csum_offset(root, path, &next_offset);
+		if (ret < 0)
+			goto out;
 		found_next = 1;
 		goto insert;
 	}
@@ -1056,8 +1070,48 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 		tmp = sums->len - total_bytes;
 		tmp >>= fs_info->sectorsize_bits;
 		WARN_ON(tmp < 1);
+		extend_nr = max_t(int, 1, tmp);
+
+		/*
+		 * A log tree can already have checksum items with a subset of
+		 * the checksums we are trying to log. This can happen after
+		 * doing a sequence of partial writes into prealloc extents and
+		 * fsyncs in between, with a full fsync logging a larger subrange
+		 * of an extent for which a previous fast fsync logged a smaller
+		 * subrange. And this happens in particular due to merging file
+		 * extent items when we complete an ordered extent for a range
+		 * covered by a prealloc extent - this is done at
+		 * btrfs_mark_extent_written().
+		 *
+		 * So if we try to extend the previous checksum item, which has
+		 * a range that ends at the start of the range we want to insert,
+		 * make sure we don't extend beyond the start offset of the next
+		 * checksum item. If we are at the last item in the leaf, then
+		 * forget the optimization of extending and add a new checksum
+		 * item - it is not worth the complexity of releasing the path,
+		 * getting the first key for the next leaf, repeat the btree
+		 * search, etc, because log trees are temporary anyway and it
+		 * would only save a few bytes of leaf space.
+		 */
+		if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+			if (path->slots[0] + 1 >=
+			    btrfs_header_nritems(path->nodes[0])) {
+				ret = find_next_csum_offset(root, path, &next_offset);
+				if (ret < 0)
+					goto out;
+				found_next = 1;
+				goto insert;
+			}
+
+			ret = find_next_csum_offset(root, path, &next_offset);
+			if (ret < 0)
+				goto out;
+
+			tmp = (next_offset - bytenr) >> fs_info->sectorsize_bits;
+			if (tmp <= INT_MAX)
+				extend_nr = min_t(int, extend_nr, tmp);
+		}
 
-		extend_nr = max_t(int, 1, (int)tmp);
 		diff = (csum_offset + extend_nr) * csum_size;
 		diff = min(diff,
 			   MAX_CSUM_ITEMS(fs_info, csum_size) * csum_size);

fs/btrfs/inode.c

@@ -3000,6 +3000,18 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	if (ret || truncated) {
 		u64 unwritten_start = start;
 
+		/*
+		 * If we failed to finish this ordered extent for any reason we
+		 * need to make sure BTRFS_ORDERED_IOERR is set on the ordered
+		 * extent, and mark the inode with the error if it wasn't
+		 * already set.  Any error during writeback would have already
+		 * set the mapping error, so we need to set it if we're the ones
+		 * marking this ordered extent as failed.
+		 */
+		if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR,
+					     &ordered_extent->flags))
+			mapping_set_error(ordered_extent->inode->i_mapping, -EIO);
+
 		if (truncated)
 			unwritten_start += logical_len;
 		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
@@ -9076,6 +9088,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	int ret2;
 	bool root_log_pinned = false;
 	bool dest_log_pinned = false;
+	bool need_abort = false;
 
 	/* we only allow rename subvolume link between subvolumes */
 	if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
@@ -9135,6 +9148,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					     old_idx);
 		if (ret)
 			goto out_fail;
+		need_abort = true;
 	}
 
 	/* And now for the dest. */
@@ -9150,8 +9164,11 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					     new_ino,
 					     btrfs_ino(BTRFS_I(old_dir)),
 					     new_idx);
-		if (ret)
+		if (ret) {
+			if (need_abort)
+				btrfs_abort_transaction(trans, ret);
 			goto out_fail;
+		}
 	}
 
 	/* Update inode version and ctime/mtime. */

fs/btrfs/reflink.c

@@ -203,10 +203,7 @@ static int clone_copy_inline_extent(struct inode *dst,
 			 * inline extent's data to the page.
 			 */
 			ASSERT(key.offset > 0);
-			ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
-						  inline_data, size, datal,
-						  comp_type);
-			goto out;
+			goto copy_to_page;
 		}
 	} else if (i_size_read(dst) <= datal) {
 		struct btrfs_file_extent_item *ei;
@@ -222,13 +219,10 @@ static int clone_copy_inline_extent(struct inode *dst,
 		    BTRFS_FILE_EXTENT_INLINE)
 			goto copy_inline_extent;
 
-		ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
-					  inline_data, size, datal, comp_type);
-		goto out;
+		goto copy_to_page;
 	}
 
 copy_inline_extent:
-	ret = 0;
 	/*
 	 * We have no extent items, or we have an extent at offset 0 which may
 	 * or may not be inlined. All these cases are dealt the same way.
@@ -240,11 +234,13 @@ static int clone_copy_inline_extent(struct inode *dst,
 		 * clone. Deal with all these cases by copying the inline extent
 		 * data into the respective page at the destination inode.
 		 */
-		ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
-					  inline_data, size, datal, comp_type);
-		goto out;
+		goto copy_to_page;
 	}
 
+	/*
+	 * Release path before starting a new transaction so we don't hold locks
+	 * that would confuse lockdep.
+	 */
 	btrfs_release_path(path);
 	/*
 	 * If we end up here it means were copy the inline extent into a leaf
@@ -281,11 +277,6 @@ static int clone_copy_inline_extent(struct inode *dst,
 	ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end);
 out:
 	if (!ret && !trans) {
-		/*
-		 * Release path before starting a new transaction so we don't
-		 * hold locks that would confuse lockdep.
-		 */
-		btrfs_release_path(path);
 		/*
 		 * No transaction here means we copied the inline extent into a
 		 * page of the destination inode.
@@ -306,6 +297,21 @@ static int clone_copy_inline_extent(struct inode *dst,
 		*trans_out = trans;
 
 	return ret;
+
+copy_to_page:
+	/*
+	 * Release our path because we don't need it anymore and also because
+	 * copy_inline_to_page() needs to reserve data and metadata, which may
+	 * need to flush delalloc when we are low on available space and
+	 * therefore cause a deadlock if writeback of an inline extent needs to
+	 * write to the same leaf or an ordered extent completion needs to write
+	 * to the same leaf.
+	 */
+	btrfs_release_path(path);
+
+	ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
+				  inline_data, size, datal, comp_type);
+	goto out;
 }
 
 /**