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, 67 insertions, 20 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c0c778243bf1..26d6ed170a19 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4250,9 +4250,9 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index);
 	if (ret) {
-		btrfs_info(fs_info,
-			"failed to delete reference to %.*s, inode %llu parent %llu",
-			name->len, name->name, ino, dir_ino);
+		btrfs_crit(fs_info,
+	   "failed to delete reference to %.*s, root %llu inode %llu parent %llu",
+			   name->len, name->name, btrfs_root_id(root), ino, dir_ino);
 		btrfs_abort_transaction(trans, ret);
 		goto err;
 	}
@@ -8059,6 +8059,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	int ret;
 	int ret2;
 	bool need_abort = false;
+	bool logs_pinned = false;
 	struct fscrypt_name old_fname, new_fname;
 	struct fscrypt_str *old_name, *new_name;
 
@@ -8182,6 +8183,31 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	inode_inc_iversion(new_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID &&
+	    new_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not for
+		 * root entries) pin the log early to prevent any concurrent
+		 * task from logging the directory after we removed the old
+		 * entries and before we add the new entries, otherwise that
+		 * task can sync a log without any entry for the inodes we are
+		 * renaming and therefore replaying that log, if a power failure
+		 * happens after syncing the log, would result in deleting the
+		 * inodes.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent) {
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8253,30 +8279,23 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		BTRFS_I(new_inode)->dir_index = new_idx;
 
 	/*
-	 * Now pin the logs of the roots. We do it to ensure that no other task
-	 * can sync the logs while we are in progress with the rename, because
-	 * that could result in an inconsistency in case any of the inodes that
-	 * are part of this rename operation were logged before.
+	 * Do the log updates for all inodes.
+	 *
+	 * If either entry is for a root we don't need to update the logs since
+	 * we've called btrfs_set_log_full_commit() before.
 	 */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(dest);
-
-	/* Do the log updates for all inodes. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned) {
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   old_rename_ctx.index, new_dentry->d_parent);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
 		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
 				   new_rename_ctx.index, old_dentry->d_parent);
+	}
 
-	/* Now unpin the logs. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+out_fail:
+	if (logs_pinned) {
 		btrfs_end_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
 		btrfs_end_log_trans(dest);
-out_fail:
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans:
@@ -8326,6 +8345,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	int ret2;
 	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
 	struct fscrypt_name old_fname, new_fname;
+	bool logs_pinned = false;
 
 	if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
@@ -8460,6 +8480,29 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	inode_inc_iversion(old_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not a
+		 * root entry) pin the log to prevent any concurrent task from
+		 * logging the directory after we removed the old entry and
+		 * before we add the new entry, otherwise that task can sync
+		 * a log without any entry for the inode we are renaming and
+		 * therefore replaying that log, if a power failure happens
+		 * after syncing the log, would result in deleting the inode.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8524,7 +8567,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	if (old_inode->i_nlink == 1)
 		BTRFS_I(old_inode)->dir_index = index;
 
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned)
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   rename_ctx.index, new_dentry->d_parent);
 
@@ -8540,6 +8583,10 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 		}
 	}
 out_fail:
+	if (logs_pinned) {
+		btrfs_end_log_trans(root);
+		btrfs_end_log_trans(dest);
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans: