1 files changed, 36 insertions, 29 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 81737eff92f3..3867cb0646e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -485,7 +485,7 @@ struct async_chunk {
 	struct page *locked_page;
 	u64 start;
 	u64 end;
-	unsigned int write_flags;
+	blk_opf_t write_flags;
 	struct list_head extents;
 	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
@@ -1435,7 +1435,7 @@ static int cow_file_range_async(struct btrfs_inode *inode,
 	int i;
 	bool should_compress;
 	unsigned nofs_flag;
-	const unsigned int write_flags = wbc_to_write_flags(wbc);
+	const blk_opf_t write_flags = wbc_to_write_flags(wbc);
 
 	unlock_extent(&inode->io_tree, start, end);
 
@@ -3195,6 +3195,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						logical_len);
+		btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
+						  ordered_extent->disk_num_bytes);
 	} else {
 		BUG_ON(root == fs_info->tree_root);
 		ret = insert_ordered_extent_file_extent(trans, ordered_extent);
@@ -3576,7 +3578,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 	u64 last_objectid = 0;
 	int ret = 0, nr_unlink = 0;
 
-	/* Bail out if the cleanup is already running. */
 	if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state))
 		return 0;
 
@@ -3659,17 +3660,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 			 *
 			 * btrfs_find_orphan_roots() ran before us, which has
 			 * found all deleted roots and loaded them into
-			 * fs_info->fs_roots. So here we can find if an
+			 * fs_info->fs_roots_radix. So here we can find if an
 			 * orphan item corresponds to a deleted root by looking
-			 * up the root from that xarray.
+			 * up the root from that radix tree.
 			 */
 
-			spin_lock(&fs_info->fs_roots_lock);
-			dead_root = xa_load(&fs_info->fs_roots,
-					    (unsigned long)found_key.objectid);
+			spin_lock(&fs_info->fs_roots_radix_lock);
+			dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
+							 (unsigned long)found_key.objectid);
 			if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
 				is_dead_root = 1;
-			spin_unlock(&fs_info->fs_roots_lock);
+			spin_unlock(&fs_info->fs_roots_radix_lock);
 
 			if (is_dead_root) {
 				/* prevent this orphan from being found again */
@@ -3909,7 +3910,7 @@ cache_index:
 	 * cache.
 	 *
 	 * This is required for both inode re-read from disk and delayed inode
-	 * in the delayed_nodes xarray.
+	 * in delayed_nodes_tree.
 	 */
 	if (BTRFS_I(inode)->last_trans == fs_info->generation)
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
@@ -7679,7 +7680,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
 	    em->block_start == EXTENT_MAP_INLINE) {
 		free_extent_map(em);
-		ret = -ENOTBLK;
+		/*
+		 * If we are in a NOWAIT context, return -EAGAIN in order to
+		 * fallback to buffered IO. This is not only because we can
+		 * block with buffered IO (no support for NOWAIT semantics at
+		 * the moment) but also to avoid returning short reads to user
+		 * space - this happens if we were able to read some data from
+		 * previous non-compressed extents and then when we fallback to
+		 * buffered IO, at btrfs_file_read_iter() by calling
+		 * filemap_read(), we fail to fault in pages for the read buffer,
+		 * in which case filemap_read() returns a short read (the number
+		 * of bytes previously read is > 0, so it does not return -EFAULT).
+		 */
+		ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
 		goto unlock_err;
 	}
 
@@ -8152,7 +8165,8 @@ ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_befo
 	struct btrfs_dio_data data;
 
 	return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL, &data, done_before);
+			    IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC,
+			    &data, done_before);
 }
 
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -8255,30 +8269,24 @@ static bool btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
 }
 
 #ifdef CONFIG_MIGRATION
-static int btrfs_migratepage(struct address_space *mapping,
-			     struct page *newpage, struct page *page,
+static int btrfs_migrate_folio(struct address_space *mapping,
+			     struct folio *dst, struct folio *src,
 			     enum migrate_mode mode)
 {
-	int ret;
+	int ret = filemap_migrate_folio(mapping, dst, src, mode);
 
-	ret = migrate_page_move_mapping(mapping, newpage, page, 0);
 	if (ret != MIGRATEPAGE_SUCCESS)
 		return ret;
 
-	if (page_has_private(page))
-		attach_page_private(newpage, detach_page_private(page));
-
-	if (PageOrdered(page)) {
-		ClearPageOrdered(page);
-		SetPageOrdered(newpage);
+	if (folio_test_ordered(src)) {
+		folio_clear_ordered(src);
+		folio_set_ordered(dst);
 	}
 
-	if (mode != MIGRATE_SYNC_NO_COPY)
-		migrate_page_copy(newpage, page);
-	else
-		migrate_page_states(newpage, page);
 	return MIGRATEPAGE_SUCCESS;
 }
+#else
+#define btrfs_migrate_folio NULL
 #endif
 
 static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
@@ -9897,6 +9905,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	extent_info.file_offset = file_offset;
 	extent_info.extent_buf = (char *)&stack_fi;
 	extent_info.is_new_extent = true;
+	extent_info.update_times = true;
 	extent_info.qgroup_reserved = qgroup_released;
 	extent_info.insertions = 0;
 
@@ -11422,9 +11431,7 @@ static const struct address_space_operations btrfs_aops = {
 	.direct_IO	= noop_direct_IO,
 	.invalidate_folio = btrfs_invalidate_folio,
 	.release_folio	= btrfs_release_folio,
-#ifdef CONFIG_MIGRATION
-	.migratepage	= btrfs_migratepage,
-#endif
+	.migrate_folio	= btrfs_migrate_folio,
 	.dirty_folio	= filemap_dirty_folio,
 	.error_remove_page = generic_error_remove_page,
 	.swap_activate	= btrfs_swap_activate,