Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 167 insertions, 88 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6c2e794eff..b28bb1c93d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -114,6 +114,15 @@ struct data_reloc_warn {
 	int mirror_num;
 };
 
+/*
+ * For the file_extent_tree, we want to hold the inode lock when we lookup and
+ * update the disk_i_size, but lockdep will complain because our io_tree we hold
+ * the tree lock and get the inode lock when setting delalloc. These two things
+ * are unrelated, so make a class for the file_extent_tree so we don't get the
+ * two locking patterns mixed up.
+ */
+static struct lock_class_key file_extent_tree_class;
+
 static const struct inode_operations btrfs_dir_inode_operations;
 static const struct inode_operations btrfs_symlink_inode_operations;
 static const struct inode_operations btrfs_special_inode_operations;
@@ -447,8 +456,8 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 		 * range, then btrfs_mark_ordered_io_finished() will handle
 		 * the ordered extent accounting for the range.
 		 */
-		btrfs_page_clamp_clear_ordered(inode->root->fs_info, page,
-					       offset, bytes);
+		btrfs_folio_clamp_clear_ordered(inode->root->fs_info,
+						page_folio(page), offset, bytes);
 		put_page(page);
 	}
 
@@ -1037,7 +1046,7 @@ free_pages:
 	if (pages) {
 		for (i = 0; i < nr_pages; i++) {
 			WARN_ON(pages[i]->mapping);
-			put_page(pages[i]);
+			btrfs_free_compr_page(pages[i]);
 		}
 		kfree(pages);
 	}
@@ -1052,7 +1061,7 @@ static void free_async_extent_pages(struct async_extent *async_extent)
 
 	for (i = 0; i < async_extent->nr_pages; i++) {
 		WARN_ON(async_extent->pages[i]->mapping);
-		put_page(async_extent->pages[i]);
+		btrfs_free_compr_page(async_extent->pages[i]);
 	}
 	kfree(async_extent->pages);
 	async_extent->nr_pages = 0;
@@ -1135,13 +1144,13 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 				   0, *alloc_hint, &ins, 1, 1);
 	if (ret) {
 		/*
-		 * Here we used to try again by going back to non-compressed
-		 * path for ENOSPC.  But we can't reserve space even for
-		 * compressed size, how could it work for uncompressed size
-		 * which requires larger size?  So here we directly go error
-		 * path.
+		 * We can't reserve contiguous space for the compressed size.
+		 * Unlikely, but it's possible that we could have enough
+		 * non-contiguous space for the uncompressed size instead.  So
+		 * fall back to uncompressed.
 		 */
-		goto out_free;
+		submit_uncompressed_range(inode, async_extent, locked_page);
+		goto done;
 	}
 
 	/* Here we're doing allocation and writeback of the compressed pages */
@@ -1193,7 +1202,6 @@ done:
 out_free_reserve:
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
-out_free:
 	mapping_set_error(inode->vfs_inode.i_mapping, -EIO);
 	extent_clear_unlock_delalloc(inode, start, end,
 				     NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
@@ -2793,7 +2801,7 @@ out_page:
 					       PAGE_SIZE, !ret);
 		clear_page_dirty_for_io(page);
 	}
-	btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);
+	btrfs_folio_clear_checked(fs_info, page_folio(page), page_start, PAGE_SIZE);
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
@@ -2820,7 +2828,7 @@ out_page:
 int btrfs_writepage_cow_fixup(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_writepage_fixup *fixup;
 
 	/* This page has ordered extent covering it already */
@@ -2848,7 +2856,7 @@ int btrfs_writepage_cow_fixup(struct page *page)
 	 * page->mapping outside of the page lock.
 	 */
 	ihold(inode);
-	btrfs_page_set_checked(fs_info, page, page_offset(page), PAGE_SIZE);
+	btrfs_folio_set_checked(fs_info, page_folio(page), page_offset(page), PAGE_SIZE);
 	get_page(page);
 	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL);
 	fixup->page = page;
@@ -3118,8 +3126,13 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->disk_num_bytes);
 		}
 	}
-	unpin_extent_cache(&inode->extent_tree, ordered_extent->file_offset,
-			   ordered_extent->num_bytes, trans->transid);
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, ret);
+		goto out;
+	}
+
+	ret = unpin_extent_cache(inode, ordered_extent->file_offset,
+				 ordered_extent->num_bytes, trans->transid);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -3245,7 +3258,7 @@ out:
 
 int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered)
 {
-	if (btrfs_is_zoned(btrfs_sb(ordered->inode->i_sb)) &&
+	if (btrfs_is_zoned(inode_to_fs_info(ordered->inode)) &&
 	    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
 	    list_empty(&ordered->bioc_list))
 		btrfs_finish_ordered_zoned(ordered);
@@ -3730,7 +3743,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 static int btrfs_read_locked_inode(struct inode *inode,
 				   struct btrfs_path *in_path)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_path *path = in_path;
 	struct extent_buffer *leaf;
 	struct btrfs_inode_item *inode_item;
@@ -3811,7 +3824,7 @@ cache_index:
 	 * cache.
 	 *
 	 * This is required for both inode re-read from disk and delayed inode
-	 * in delayed_nodes_tree.
+	 * in the delayed_nodes xarray.
 	 */
 	if (BTRFS_I(inode)->last_trans == btrfs_get_fs_generation(fs_info))
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
@@ -4455,13 +4468,14 @@ again:
 
 int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
 	struct btrfs_root *root = dir->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *dest = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_block_rsv block_rsv;
 	u64 root_flags;
+	u64 qgroup_reserved = 0;
 	int ret;
 
 	down_write(&fs_info->subvol_sem);
@@ -4506,12 +4520,20 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
 		goto out_undead;
+	qgroup_reserved = block_rsv.qgroup_rsv_reserved;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out_release;
 	}
+	ret = btrfs_record_root_in_trans(trans, root);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto out_end_trans;
+	}
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
@@ -4570,7 +4592,9 @@ out_end_trans:
 	ret = btrfs_end_transaction(trans);
 	inode->i_flags |= S_DEAD;
 out_release:
-	btrfs_subvolume_release_metadata(root, &block_rsv);
+	btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
@@ -4744,7 +4768,7 @@ again:
 	/*
 	 * We unlock the page after the io is completed and then re-lock it
 	 * above.  release_folio() could have come in between that and cleared
-	 * PagePrivate(), but left the page in the mapping.  Set the page mapped
+	 * folio private, but left the page in the mapping.  Set the page mapped
 	 * here to make sure it's properly set for the subpage stuff.
 	 */
 	ret = set_page_extent_mapped(page);
@@ -4786,9 +4810,10 @@ again:
 			memzero_page(page, (block_start - page_offset(page)) + offset,
 				     len);
 	}
-	btrfs_page_clear_checked(fs_info, page, block_start,
-				 block_end + 1 - block_start);
-	btrfs_page_set_dirty(fs_info, page, block_start, block_end + 1 - block_start);
+	btrfs_folio_clear_checked(fs_info, page_folio(page), block_start,
+				  block_end + 1 - block_start);
+	btrfs_folio_set_dirty(fs_info, page_folio(page), block_start,
+			      block_end + 1 - block_start);
 	unlock_extent(io_tree, block_start, block_end, &cached_state);
 
 	if (only_release_metadata)
@@ -4908,7 +4933,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 		last_byte = ALIGN(last_byte, fs_info->sectorsize);
 		hole_size = last_byte - cur_offset;
 
-		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		if (!(em->flags & EXTENT_FLAG_PREALLOC)) {
 			struct extent_map *hole_em;
 
 			err = maybe_insert_hole(inode, cur_offset, hole_size);
@@ -4936,7 +4961,6 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = btrfs_get_fs_generation(fs_info);
 
 			err = btrfs_replace_extent_map_range(inode, hole_em, true);
@@ -5010,7 +5034,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		btrfs_drew_write_unlock(&root->snapshot_lock);
 		btrfs_end_transaction(trans);
 	} else {
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+		struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 
 		if (btrfs_is_zoned(fs_info)) {
 			ret = btrfs_wait_ordered_range(inode,
@@ -5213,7 +5237,7 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
 
 void btrfs_evict_inode(struct inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_block_rsv *rsv = NULL;
@@ -5227,6 +5251,7 @@ void btrfs_evict_inode(struct inode *inode)
 		return;
 	}
 
+	fs_info = inode_to_fs_info(inode);
 	evict_inode_truncate_pages(inode);
 
 	if (inode->i_nlink &&
@@ -5652,7 +5677,7 @@ static inline u8 btrfs_inode_type(struct inode *inode)
 
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct inode *inode;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *sub_root = root;
@@ -6191,7 +6216,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	struct inode *dir = args->dir;
 	struct inode *inode = args->inode;
 	const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name;
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_root *root;
 	struct btrfs_inode_item *inode_item;
 	struct btrfs_key *location;
@@ -6236,6 +6261,13 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_generation = BTRFS_I(inode)->generation;
 
 	/*
+	 * We don't have any capability xattrs set here yet, shortcut any
+	 * queries for the xattrs here.  If we add them later via the inode
+	 * security init path or any other path this flag will be cleared.
+	 */
+	set_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
+
+	/*
 	 * Subvolumes don't inherit flags from their parent directory.
 	 * Originally this was probably by accident, but we probably can't
 	 * change it now without compatibility issues.
@@ -6506,7 +6538,7 @@ fail_dir_item:
 static int btrfs_create_common(struct inode *dir, struct dentry *dentry,
 			       struct inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_new_inode_args new_inode_args = {
 		.dir = dir,
@@ -6576,7 +6608,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	struct btrfs_trans_handle *trans = NULL;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = d_inode(old_dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct fscrypt_name fname;
 	u64 index;
 	int err;
@@ -7062,7 +7094,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes, bool nowait, bool strict)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct can_nocow_file_extent_args nocow_args = { 0 };
 	struct btrfs_path *path;
 	int ret;
@@ -7277,13 +7309,11 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
-	if (type == BTRFS_ORDERED_PREALLOC) {
-		set_bit(EXTENT_FLAG_FILLING, &em->flags);
-	} else if (type == BTRFS_ORDERED_COMPRESSED) {
-		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-		em->compress_type = compress_type;
-	}
+	em->flags |= EXTENT_FLAG_PINNED;
+	if (type == BTRFS_ORDERED_PREALLOC)
+		em->flags |= EXTENT_FLAG_FILLING;
+	else if (type == BTRFS_ORDERED_COMPRESSED)
+		extent_map_set_compression(em, compress_type);
 
 	ret = btrfs_replace_extent_map_range(inode, em, true);
 	if (ret) {
@@ -7303,7 +7333,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					 unsigned int iomap_flags)
 {
 	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em = *map;
 	int type;
 	u64 block_start, orig_start, orig_block_len, ram_bytes;
@@ -7323,10 +7353,10 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * just use the extent.
 	 *
 	 */
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if ((em->flags & EXTENT_FLAG_PREALLOC) ||
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		if (em->flags & EXTENT_FLAG_PREALLOC)
 			type = BTRFS_ORDERED_PREALLOC;
 		else
 			type = BTRFS_ORDERED_NOCOW;
@@ -7443,7 +7473,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 		struct iomap *srcmap)
 {
 	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_dio_data *dio_data = iter->private;
@@ -7561,7 +7591,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * to buffered IO.  Don't blame me, this is the price we pay for using
 	 * the generic code.
 	 */
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
+	if (extent_map_is_compressed(em) ||
 	    em->block_start == EXTENT_MAP_INLINE) {
 		free_extent_map(em);
 		/*
@@ -7657,7 +7687,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * that, since we have locked only the parts we are performing I/O in.
 	 */
 	if ((em->block_start == EXTENT_MAP_HOLE) ||
-	    (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && !write)) {
+	    ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) {
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_HOLE;
 	} else {
@@ -7821,6 +7851,7 @@ struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			u64 start, u64 len)
 {
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
 	int	ret;
 
 	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
@@ -7846,7 +7877,26 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return ret;
 	}
 
-	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
+	btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	/*
+	 * We did an initial flush to avoid holding the inode's lock while
+	 * triggering writeback and waiting for the completion of IO and ordered
+	 * extents. Now after we locked the inode we do it again, because it's
+	 * possible a new write may have happened in between those two steps.
+	 */
+	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
+		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
+		if (ret) {
+			btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+			return ret;
+		}
+	}
+
+	ret = extent_fiemap(btrfs_inode, fieinfo, start, len);
+	btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -7869,14 +7919,15 @@ static void btrfs_readahead(struct readahead_control *rac)
  */
 static void wait_subpage_spinlock(struct page *page)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(page);
+	struct folio *folio = page_folio(page);
 	struct btrfs_subpage *subpage;
 
-	if (!btrfs_is_subpage(fs_info, page))
+	if (!btrfs_is_subpage(fs_info, page->mapping))
 		return;
 
-	ASSERT(PagePrivate(page) && page->private);
-	subpage = (struct btrfs_subpage *)page->private;
+	ASSERT(folio_test_private(folio) && folio_get_private(folio));
+	subpage = folio_get_private(folio);
 
 	/*
 	 * This may look insane as we just acquire the spinlock and release it,
@@ -7935,7 +7986,7 @@ static int btrfs_migrate_folio(struct address_space *mapping,
 static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 				 size_t length)
 {
-	struct btrfs_inode *inode = BTRFS_I(folio->mapping->host);
+	struct btrfs_inode *inode = folio_to_inode(folio);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_io_tree *tree = &inode->io_tree;
 	struct extent_state *cached_state = NULL;
@@ -8014,7 +8065,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 				page_end);
 		ASSERT(range_end + 1 - cur < U32_MAX);
 		range_len = range_end + 1 - cur;
-		if (!btrfs_page_test_ordered(fs_info, &folio->page, cur, range_len)) {
+		if (!btrfs_folio_test_ordered(fs_info, folio, cur, range_len)) {
 			/*
 			 * If Ordered (Private2) is cleared, it means endio has
 			 * already been executed for the range.
@@ -8023,7 +8074,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 			 */
 			goto next;
 		}
-		btrfs_page_clear_ordered(fs_info, &folio->page, cur, range_len);
+		btrfs_folio_clear_ordered(fs_info, folio, cur, range_len);
 
 		/*
 		 * IO on this page will never be started, so we need to account
@@ -8093,7 +8144,7 @@ next:
 	 * did something wrong.
 	 */
 	ASSERT(!folio_test_ordered(folio));
-	btrfs_page_clear_checked(fs_info, &folio->page, folio_pos(folio), folio_size(folio));
+	btrfs_folio_clear_checked(fs_info, folio, folio_pos(folio), folio_size(folio));
 	if (!inode_evicting)
 		__btrfs_release_folio(folio, GFP_NOFS);
 	clear_page_extent_mapped(&folio->page);
@@ -8117,8 +8168,9 @@ next:
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
+	struct folio *folio = page_folio(page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
@@ -8133,6 +8185,8 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	u64 page_end;
 	u64 end;
 
+	ASSERT(folio_order(folio) == 0);
+
 	reserved_space = PAGE_SIZE;
 
 	sb_start_pagefault(inode->i_sb);
@@ -8236,9 +8290,9 @@ again:
 	if (zero_start != PAGE_SIZE)
 		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
 
-	btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE);
-	btrfs_page_set_dirty(fs_info, page, page_start, end + 1 - page_start);
-	btrfs_page_set_uptodate(fs_info, page, page_start, end + 1 - page_start);
+	btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE);
+	btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start);
+	btrfs_folio_set_uptodate(fs_info, folio, page_start, end + 1 - page_start);
 
 	btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
 
@@ -8481,10 +8535,20 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_inode *ei;
 	struct inode *inode;
+	struct extent_io_tree *file_extent_tree = NULL;
+
+	/* Self tests may pass a NULL fs_info. */
+	if (fs_info && !btrfs_fs_incompat(fs_info, NO_HOLES)) {
+		file_extent_tree = kmalloc(sizeof(struct extent_io_tree), GFP_KERNEL);
+		if (!file_extent_tree)
+			return NULL;
+	}
 
 	ei = alloc_inode_sb(sb, btrfs_inode_cachep, GFP_KERNEL);
-	if (!ei)
+	if (!ei) {
+		kfree(file_extent_tree);
 		return NULL;
+	}
 
 	ei->root = NULL;
 	ei->generation = 0;
@@ -8520,10 +8584,18 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
+
+	/* This io tree sets the valid inode. */
 	extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO);
 	ei->io_tree.inode = ei;
-	extent_io_tree_init(fs_info, &ei->file_extent_tree,
-			    IO_TREE_INODE_FILE_EXTENT);
+
+	ei->file_extent_tree = file_extent_tree;
+	if (file_extent_tree) {
+		extent_io_tree_init(fs_info, ei->file_extent_tree,
+				    IO_TREE_INODE_FILE_EXTENT);
+		/* Lockdep class is set only for the file extent tree. */
+		lockdep_set_class(&ei->file_extent_tree->lock, &file_extent_tree_class);
+	}
 	mutex_init(&ei->log_mutex);
 	spin_lock_init(&ei->ordered_tree_lock);
 	ei->ordered_tree = RB_ROOT;
@@ -8540,12 +8612,14 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 void btrfs_test_destroy_inode(struct inode *inode)
 {
 	btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (u64)-1, false);
+	kfree(BTRFS_I(inode)->file_extent_tree);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 #endif
 
 void btrfs_free_inode(struct inode *inode)
 {
+	kfree(BTRFS_I(inode)->file_extent_tree);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 
@@ -8665,7 +8739,7 @@ static int btrfs_getattr(struct mnt_idmap *idmap,
 	u64 delalloc_bytes;
 	u64 inode_bytes;
 	struct inode *inode = d_inode(path->dentry);
-	u32 blocksize = inode->i_sb->s_blocksize;
+	u32 blocksize = btrfs_sb(inode->i_sb)->sectorsize;
 	u32 bi_flags = BTRFS_I(inode)->flags;
 	u32 bi_ro_flags = BTRFS_I(inode)->ro_flags;
 
@@ -8705,7 +8779,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 			      struct inode *new_dir,
 			      struct dentry *new_dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir);
 	struct btrfs_trans_handle *trans;
 	unsigned int trans_num_items;
 	struct btrfs_root *root = BTRFS_I(old_dir)->root;
@@ -8957,7 +9031,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir);
 	struct btrfs_new_inode_args whiteout_args = {
 		.dir = old_dir,
 		.dentry = old_dentry,
@@ -9399,7 +9473,7 @@ out:
 static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 			 struct dentry *dentry, const char *symname)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
@@ -9580,7 +9654,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 				       loff_t actual_len, u64 *alloc_hint,
 				       struct btrfs_trans_handle *trans)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key ins;
@@ -9651,7 +9725,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+		em->flags |= EXTENT_FLAG_PREALLOC;
 		em->generation = trans->transid;
 
 		ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, true);
@@ -9732,7 +9806,7 @@ static int btrfs_permission(struct mnt_idmap *idmap,
 static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 			 struct file *file, umode_t mode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode;
@@ -9804,7 +9878,9 @@ void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
 		page = find_get_page(inode->vfs_inode.i_mapping, index);
 		ASSERT(page); /* Pages should be in the extent_io_tree */
 
-		btrfs_page_set_writeback(fs_info, page, start, len);
+		/* This is for data, which doesn't yet support larger folio. */
+		ASSERT(folio_order(page_folio(page)) == 0);
+		btrfs_folio_set_writeback(fs_info, page_folio(page), start, len);
 		put_page(page);
 		index++;
 	}
@@ -10013,7 +10089,7 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb,
 	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	ret = btrfs_alloc_page_array(nr_pages, pages);
+	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
 	if (ret) {
 		ret = -ENOMEM;
 		goto out;
@@ -10132,12 +10208,12 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 	encoded->len = min_t(u64, extent_map_end(em),
 			     inode->vfs_inode.i_size) - iocb->ki_pos;
 	if (em->block_start == EXTENT_MAP_HOLE ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+	    (em->flags & EXTENT_FLAG_PREALLOC)) {
 		disk_bytenr = EXTENT_MAP_HOLE;
 		count = min_t(u64, count, encoded->len);
 		encoded->len = count;
 		encoded->unencoded_len = count;
-	} else if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+	} else if (extent_map_is_compressed(em)) {
 		disk_bytenr = em->block_start;
 		/*
 		 * Bail if the buffer isn't large enough to return the whole
@@ -10152,7 +10228,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		encoded->unencoded_len = em->ram_bytes;
 		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
 		ret = btrfs_encoded_io_compression_from_extent(fs_info,
-							     em->compress_type);
+							       extent_map_compression(em));
 		if (ret < 0)
 			goto out_em;
 		encoded->compression = ret;
@@ -10590,6 +10666,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em = NULL;
+	struct btrfs_chunk_map *map = NULL;
 	struct btrfs_device *device = NULL;
 	struct btrfs_swap_info bsi = {
 		.lowest_ppage = (sector_t)-1ULL,
@@ -10706,7 +10783,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			ret = -EINVAL;
 			goto out;
 		}
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+		if (extent_map_is_compressed(em)) {
 			btrfs_warn(fs_info, "swapfile must not be compressed");
 			ret = -EINVAL;
 			goto out;
@@ -10729,13 +10806,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
-		em = btrfs_get_chunk_map(fs_info, logical_block_start, len);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
+		map = btrfs_get_chunk_map(fs_info, logical_block_start, len);
+		if (IS_ERR(map)) {
+			ret = PTR_ERR(map);
 			goto out;
 		}
 
-		if (em->map_lookup->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+		if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 			btrfs_warn(fs_info,
 				   "swapfile must have single data profile");
 			ret = -EINVAL;
@@ -10743,23 +10820,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		}
 
 		if (device == NULL) {
-			device = em->map_lookup->stripes[0].dev;
+			device = map->stripes[0].dev;
 			ret = btrfs_add_swapfile_pin(inode, device, false);
 			if (ret == 1)
 				ret = 0;
 			else if (ret)
 				goto out;
-		} else if (device != em->map_lookup->stripes[0].dev) {
+		} else if (device != map->stripes[0].dev) {
 			btrfs_warn(fs_info, "swapfile must be on one device");
 			ret = -EINVAL;
 			goto out;
 		}
 
-		physical_block_start = (em->map_lookup->stripes[0].physical +
-					(logical_block_start - em->start));
-		len = min(len, em->len - (logical_block_start - em->start));
-		free_extent_map(em);
-		em = NULL;
+		physical_block_start = (map->stripes[0].physical +
+					(logical_block_start - map->start));
+		len = min(len, map->chunk_len - (logical_block_start - map->start));
+		btrfs_free_chunk_map(map);
+		map = NULL;
 
 		bg = btrfs_lookup_block_group(fs_info, logical_block_start);
 		if (!bg) {
@@ -10812,6 +10889,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 out:
 	if (!IS_ERR_OR_NULL(em))
 		free_extent_map(em);
+	if (!IS_ERR_OR_NULL(map))
+		btrfs_free_chunk_map(map);
 
 	unlock_extent(io_tree, 0, isize - 1, &cached_state);
 
@@ -10956,7 +11035,7 @@ static const struct address_space_operations btrfs_aops = {
 	.release_folio	= btrfs_release_folio,
 	.migrate_folio	= btrfs_migrate_folio,
 	.dirty_folio	= filemap_dirty_folio,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 	.swap_activate	= btrfs_swap_activate,
 	.swap_deactivate = btrfs_swap_deactivate,
 };