Merge tag 'for-7.1-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fixup warning when allocating memory for readahead, __GFP_NOWARN was
   accidentally dropped when setting mapping constraints

 - in tracepoint of file sync, fix sleeping in atomic context when
   handling dentries

 - harden initial loading of block group on crafted/fuzzed images,
   iterate all chunk mapping entries unconditionally

 - fix freeing pages of submitted io after checking for errors

 - fix incorrect inode size after remount when using fallocate KEEP_SIZE
   mode (also requires disabled 'no-holes' feature)

* tag 'for-7.1-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix incorrect i_size after remount caused by KEEP_SIZE prealloc gap
  btrfs: only release the dirty pages io tree after successful writes
  btrfs: tracepoints: fix sleep while in atomic context in btrfs_sync_file()
  btrfs: always pass __GFP_NOWARN from add_ra_bio_pages()
  btrfs: fix check_chunk_block_group_mappings() to iterate all chunk maps

fs/btrfs/block-group.c

@@ -2412,29 +2412,25 @@ static struct btrfs_block_group *btrfs_create_block_group(
  */
 static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 {
-	u64 start = 0;
+	struct rb_node *node;
 	int ret = 0;
 
-	while (1) {
+	/*
+	 * This is called during mount from btrfs_read_block_groups(), before
+	 * any background threads are started, so no concurrent writers can
+	 * modify the mapping_tree. No lock is needed here.
+	 */
+	for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) {
 		struct btrfs_chunk_map *map;
 		struct btrfs_block_group *bg;
 
-		/*
-		 * btrfs_find_chunk_map() will return the first chunk map
-		 * intersecting the range, so setting @length to 1 is enough to
-		 * get the first chunk.
-		 */
-		map = btrfs_find_chunk_map(fs_info, start, 1);
-		if (!map)
-			break;
-
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
 		bg = btrfs_lookup_block_group(fs_info, map->start);
 		if (unlikely(!bg)) {
 			btrfs_err(fs_info,
 	"chunk start=%llu len=%llu doesn't have corresponding block group",
 				     map->start, map->chunk_len);
 			ret = -EUCLEAN;
-			btrfs_free_chunk_map(map);
 			break;
 		}
 		if (unlikely(bg->start != map->start || bg->length != map->chunk_len ||
@@ -2447,12 +2443,9 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 				bg->start, bg->length,
 				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 			ret = -EUCLEAN;
-			btrfs_free_chunk_map(map);
 			btrfs_put_block_group(bg);
 			break;
 		}
-		start = map->start + map->chunk_len;
-		btrfs_free_chunk_map(map);
 		btrfs_put_block_group(bg);
 	}
 	return ret;

fs/btrfs/compression.c

@@ -407,22 +407,18 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 
 	end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
-	/*
-	 * Avoid direct reclaim when the caller does not allow it.  Since
-	 * add_ra_bio_pages() is always speculative, suppress allocation warnings
-	 * in either case.
-	 */
+	/* Avoid direct reclaim when the caller does not allow it. */
+	constraint_gfp = ~__GFP_FS;
+	cache_gfp = GFP_NOFS | __GFP_NOWARN;
 	if (!direct_reclaim) {
-		constraint_gfp = ~(__GFP_FS | __GFP_DIRECT_RECLAIM) | __GFP_NOWARN;
-		cache_gfp = (GFP_NOFS & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN;
-	} else {
-		constraint_gfp = (~__GFP_FS) | __GFP_NOWARN;
-		cache_gfp = GFP_NOFS | __GFP_NOWARN;
+		constraint_gfp &= ~__GFP_DIRECT_RECLAIM;
+		cache_gfp &= ~__GFP_DIRECT_RECLAIM;
 	}
 
 	while (cur < compressed_end) {
 		pgoff_t page_end;
 		pgoff_t pg_index = cur >> PAGE_SHIFT;
+		gfp_t masked_constraint_gfp;
 		u32 add_size;
 
 		if (pg_index > end_index)
@@ -449,8 +445,14 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			continue;
 		}
 
-		folio = filemap_alloc_folio(mapping_gfp_constraint(mapping, constraint_gfp),
-					    0, NULL);
+		/*
+		 * Since add_ra_bio_pages() is always speculative, suppress
+		 * allocation warnings.
+		 */
+		masked_constraint_gfp = mapping_gfp_constraint(mapping, constraint_gfp);
+		masked_constraint_gfp |= __GFP_NOWARN;
+
+		folio = filemap_alloc_folio(masked_constraint_gfp, 0, NULL);
 		if (!folio)
 			break;
 

fs/btrfs/disk-io.c

@@ -4686,6 +4686,7 @@ static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
 			free_extent_buffer_stale(eb);
 		}
 	}
+	btrfs_extent_io_tree_release(dirty_pages);
 }
 
 static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,

fs/btrfs/inode.c

@@ -9299,10 +9299,38 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    (actual_len > inode->i_size) &&
 		    (cur_offset > inode->i_size)) {
+			u64 range_start;
+			u64 range_end;
+
 			if (cur_offset > actual_len)
 				i_size = actual_len;
 			else
 				i_size = cur_offset;
+
+			/*
+			 * Make sure the file_extent_tree covers the entire
+			 * range [old_i_size, new_i_size) before we update
+			 * disk_i_size. Without this, a previous KEEP_SIZE
+			 * prealloc that extended past i_size (and was lost
+			 * across umount/mount because file_extent_tree is
+			 * only populated up to round_up(i_size) on inode
+			 * load) can leave a gap inside this range. That gap
+			 * would cause btrfs_inode_safe_disk_i_size_write()
+			 * (via find_contiguous_extent_bit() starting at 0)
+			 * to truncate disk_i_size to the start of the gap,
+			 * making the persisted size smaller than i_size.
+			 */
+			range_start = round_down(inode->i_size, fs_info->sectorsize);
+			range_end = round_up(i_size, fs_info->sectorsize);
+			ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode),
+					range_start, range_end - range_start);
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
+				if (own_trans)
+					btrfs_end_transaction(trans);
+				break;
+			}
+
 			i_size_write(inode, i_size);
 			btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
 		}

fs/btrfs/transaction.c

@@ -1293,14 +1293,13 @@ static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans)
 	blk_finish_plug(&plug);
 	ret2 = btrfs_wait_extents(fs_info, dirty_pages);
 
-	btrfs_extent_io_tree_release(&trans->transaction->dirty_pages);
-
 	if (ret)
 		return ret;
-	else if (ret2)
+	if (ret2)
 		return ret2;
-	else
-		return 0;
+
+	btrfs_extent_io_tree_release(&trans->transaction->dirty_pages);
+	return 0;
 }
 
 /*

include/trace/events/btrfs.h

@@ -771,10 +771,8 @@ TRACE_EVENT(btrfs_sync_file,
 	TP_fast_assign(
 		struct dentry *dentry = file_dentry(file);
 		struct inode *inode = file_inode(file);
-		struct dentry *parent = dget_parent(dentry);
-		struct inode *parent_inode = d_inode(parent);
+		struct inode *parent_inode = d_inode(dentry->d_parent);
 
-		dput(parent);
 		TP_fast_assign_fsid(btrfs_sb(inode->i_sb));
 		__entry->ino		= btrfs_ino(BTRFS_I(inode));
 		__entry->parent		= btrfs_ino(BTRFS_I(parent_inode));