Merge tag 'for-6.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Fixes:

   - fix invalid inode pointer dereferences during log replay

   - fix a race between renames and directory logging

   - fix shutting down delayed iput worker

   - fix device byte accounting when dropping chunk

   - in zoned mode, fix offset calculations for DUP profile when
     conventional and sequential zones are used together

  Regression fixes:

   - fix possible double unlock of extent buffer tree (xarray
     conversion)

   - in zoned mode, fix extent buffer refcount when writing out extents
     (xarray conversion)

  Error handling fixes and updates:

   - handle unexpected extent type when replaying log

   - check and warn if there are remaining delayed inodes when putting a
     root

   - fix assertion when building free space tree

   - handle csum tree error with mount option 'rescue=ibadroot'

  Other:

   - error message updates: add prefix to all scrub related messages,
     include other information in messages"

* tag 'for-6.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: zoned: fix alloc_offset calculation for partly conventional block groups
  btrfs: handle csum tree error with rescue=ibadroots correctly
  btrfs: fix race between async reclaim worker and close_ctree()
  btrfs: fix assertion when building free space tree
  btrfs: don't silently ignore unexpected extent type when replaying log
  btrfs: fix invalid inode pointer dereferences during log replay
  btrfs: fix double unlock of buffer_tree xarray when releasing subpage eb
  btrfs: update superblock's device bytes_used when dropping chunk
  btrfs: fix a race between renames and directory logging
  btrfs: scrub: add prefix for the error messages
  btrfs: warn if leaking delayed_nodes in btrfs_put_root()
  btrfs: fix delayed ref refcount leak in debug assertion
  btrfs: include root in error message when unlinking inode
  btrfs: don't drop a reference if btrfs_check_write_meta_pointer() fails

1 files changed, 21 insertions, 6 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1beb9458f622..0d6ad7512f21 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1835,6 +1835,8 @@ void btrfs_put_root(struct btrfs_root *root)
 	if (refcount_dec_and_test(&root->refs)) {
 		if (WARN_ON(!xa_empty(&root->inodes)))
 			xa_destroy(&root->inodes);
+		if (WARN_ON(!xa_empty(&root->delayed_nodes)))
+			xa_destroy(&root->delayed_nodes);
 		WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
 		if (root->anon_dev)
 			free_anon_bdev(root->anon_dev);
@@ -2156,8 +2158,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 		found = true;
 		root = read_tree_root_path(tree_root, path, &key);
 		if (IS_ERR(root)) {
-			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
-				ret = PTR_ERR(root);
+			ret = PTR_ERR(root);
 			break;
 		}
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
@@ -4310,8 +4311,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	 *
 	 * So wait for all ongoing ordered extents to complete and then run
 	 * delayed iputs. This works because once we reach this point no one
-	 * can either create new ordered extents nor create delayed iputs
-	 * through some other means.
+	 * can create new ordered extents, but delayed iputs can still be added
+	 * by a reclaim worker (see comments further below).
 	 *
 	 * Also note that btrfs_wait_ordered_roots() is not safe here, because
 	 * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent,
@@ -4322,15 +4323,29 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_flush_workqueue(fs_info->endio_write_workers);
 	/* Ordered extents for free space inodes. */
 	btrfs_flush_workqueue(fs_info->endio_freespace_worker);
+	/*
+	 * Run delayed iputs in case an async reclaim worker is waiting for them
+	 * to be run as mentioned above.
+	 */
 	btrfs_run_delayed_iputs(fs_info);
-	/* There should be no more workload to generate new delayed iputs. */
-	set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
 	cancel_work_sync(&fs_info->preempt_reclaim_work);
 	cancel_work_sync(&fs_info->em_shrinker_work);
 
+	/*
+	 * Run delayed iputs again because an async reclaim worker may have
+	 * added new ones if it was flushing delalloc:
+	 *
+	 * shrink_delalloc() -> btrfs_start_delalloc_roots() ->
+	 *    start_delalloc_inodes() -> btrfs_add_delayed_iput()
+	 */
+	btrfs_run_delayed_iputs(fs_info);
+
+	/* There should be no more workload to generate new delayed iputs. */
+	set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
+
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);