Update bcachefs sources to bbc3a0b17a89 bcachefs: fsck: Fix check_directory_structure when no check_dirents

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

17 files changed, 318 insertions, 157 deletions

diff --git a/.bcachefs_revision b/.bcachefs_revision
index 4a0284df..ba02a581 100644
--- a/.bcachefs_revision
+++ b/.bcachefs_revision
@@ -1 +1 @@
-54de30ef9de88c274997d8f78d21297d356c7bc0
+bbc3a0b17a890aa19bddd0f9b08e8af488f1ec94
diff --git a/libbcachefs/bcachefs.h b/libbcachefs/bcachefs.h
index 5a1cede2..8043943c 100644
--- a/libbcachefs/bcachefs.h
+++ b/libbcachefs/bcachefs.h
@@ -767,7 +767,8 @@ struct btree_trans_buf {
 	x(sysfs)							\
 	x(btree_write_buffer)						\
 	x(btree_node_scrub)						\
-	x(async_recovery_passes)
+	x(async_recovery_passes)					\
+	x(ioctl_data)
 
 enum bch_write_ref {
 #define x(n) BCH_WRITE_REF_##n,
diff --git a/libbcachefs/btree_io.c b/libbcachefs/btree_io.c
index d8f3c4c6..08b22bdd 100644
--- a/libbcachefs/btree_io.c
+++ b/libbcachefs/btree_io.c
@@ -557,7 +557,9 @@ static int __btree_err(int ret,
 		       const char *fmt, ...)
 {
 	if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
-		return bch_err_throw(c, fsck_fix);
+		return ret == -BCH_ERR_btree_node_read_err_fixable
+			? bch_err_throw(c, fsck_fix)
+			: ret;
 
 	bool have_retry = false;
 	int ret2;
@@ -723,12 +725,11 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b)
 
 static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 			 struct btree *b, struct bset *i,
-			 unsigned offset, unsigned sectors, int write,
+			 unsigned offset, int write,
 			 struct bch_io_failures *failed,
 			 struct printbuf *err_msg)
 {
 	unsigned version = le16_to_cpu(i->version);
-	unsigned ptr_written = btree_ptr_sectors_written(bkey_i_to_s_c(&b->key));
 	struct printbuf buf1 = PRINTBUF;
 	struct printbuf buf2 = PRINTBUF;
 	int ret = 0;
@@ -778,15 +779,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 		     btree_node_unsupported_version,
 		     "BSET_SEPARATE_WHITEOUTS no longer supported");
 
-	if (!write &&
-	    btree_err_on(offset + sectors > (ptr_written ?: btree_sectors(c)),
-			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, ca, b, i, NULL,
-			 bset_past_end_of_btree_node,
-			 "bset past end of btree node (offset %u len %u but written %zu)",
-			 offset, sectors, ptr_written ?: btree_sectors(c)))
-		i->u64s = 0;
-
 	btree_err_on(offset && !i->u64s,
 		     -BCH_ERR_btree_node_read_err_fixable,
 		     c, ca, b, i, NULL,
@@ -1151,6 +1143,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
 		if (first) {
+			sectors = vstruct_sectors(b->data, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data);
 				bool csum_bad = bch2_crc_cmp(b->data->csum, csum);
@@ -1178,9 +1178,15 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     c, NULL, b, NULL, NULL,
 				     btree_node_unsupported_version,
 				     "btree node does not have NEW_EXTENT_OVERWRITE set");
-
-			sectors = vstruct_sectors(b->data, c->block_bits);
 		} else {
+			sectors = vstruct_sectors(bne, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne);
 				bool csum_bad = bch2_crc_cmp(bne->csum, csum);
@@ -1201,14 +1207,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 						"decrypting btree node: %s", bch2_err_str(ret)))
 					goto fsck_err;
 			}
-
-			sectors = vstruct_sectors(bne, c->block_bits);
 		}
 
 		b->version_ondisk = min(b->version_ondisk,
 					le16_to_cpu(i->version));
 
-		ret = validate_bset(c, ca, b, i, b->written, sectors, READ, failed, err_msg);
+		ret = validate_bset(c, ca, b, i, b->written, READ, failed, err_msg);
 		if (ret)
 			goto fsck_err;
 
@@ -1982,28 +1986,12 @@ static void btree_node_scrub_work(struct work_struct *work)
 	prt_newline(&err);
 
 	if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) {
-		struct btree_trans *trans = bch2_trans_get(c);
-
-		struct btree_iter iter;
-		bch2_trans_node_iter_init(trans, &iter, scrub->btree,
-					  scrub->key.k->k.p, 0, scrub->level - 1, 0);
-
-		struct btree *b;
-		int ret = lockrestart_do(trans,
-			PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(trans, &iter)));
-		if (ret)
-			goto err;
-
-		if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) {
-			bch_err(c, "error validating btree node during scrub on %s at btree %s",
-				scrub->ca->name, err.buf);
-
-			ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0);
-		}
-err:
-		bch2_trans_iter_exit(trans, &iter);
-		bch2_trans_begin(trans);
-		bch2_trans_put(trans);
+		int ret = bch2_trans_do(c,
+			bch2_btree_node_rewrite_key(trans, scrub->btree, scrub->level - 1,
+						    scrub->key.k, 0));
+		if (!bch2_err_matches(ret, ENOENT) &&
+		    !bch2_err_matches(ret, EROFS))
+			bch_err_fn_ratelimited(c, ret);
 	}
 
 	printbuf_exit(&err);
@@ -2267,7 +2255,7 @@ static void btree_node_write_endio(struct bio *bio)
 }
 
 static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
-				   struct bset *i, unsigned sectors)
+				   struct bset *i)
 {
 	int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key),
 				     (struct bkey_validate_context) {
@@ -2282,7 +2270,7 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
 	}
 
 	ret = validate_bset_keys(c, b, i, WRITE, NULL, NULL) ?:
-		validate_bset(c, NULL, b, i, b->written, sectors, WRITE, NULL, NULL);
+		validate_bset(c, NULL, b, i, b->written, WRITE, NULL, NULL);
 	if (ret) {
 		bch2_inconsistent_error(c);
 		dump_stack();
@@ -2475,7 +2463,7 @@ do_write:
 
 	/* if we're going to be encrypting, check metadata validity first: */
 	if (validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	ret = bset_encrypt(c, i, b->written << 9);
@@ -2492,7 +2480,7 @@ do_write:
 
 	/* if we're not encrypting, check metadata after checksumming: */
 	if (!validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	/*
diff --git a/libbcachefs/btree_journal_iter.c b/libbcachefs/btree_journal_iter.c
index 8f94c3bd..a41fabd0 100644
--- a/libbcachefs/btree_journal_iter.c
+++ b/libbcachefs/btree_journal_iter.c
@@ -713,20 +713,15 @@ int bch2_journal_keys_sort(struct bch_fs *c)
 	struct journal_replay *i, **_i;
 	struct journal_keys *keys = &c->journal_keys;
 	size_t nr_read = 0;
-	u64 nr_entries = 0, nr_non_ignored = 0;
 
 	u64 rewind_seq = c->opts.journal_rewind ?: U64_MAX;
 
 	genradix_for_each(&c->journal_entries, iter, _i) {
 		i = *_i;
 
-		nr_entries += i != NULL;
-
 		if (journal_replay_ignore(i))
 			continue;
 
-		nr_non_ignored++;
-
 		cond_resched();
 
 		vstruct_for_each(&i->j, entry) {
diff --git a/libbcachefs/btree_update_interior.c b/libbcachefs/btree_update_interior.c
index e7758460..7bf1bd6a 100644
--- a/libbcachefs/btree_update_interior.c
+++ b/libbcachefs/btree_update_interior.c
@@ -2293,9 +2293,9 @@ err:
 	goto out;
 }
 
-static int bch2_btree_node_rewrite_key(struct btree_trans *trans,
-				       enum btree_id btree, unsigned level,
-				       struct bkey_i *k, unsigned flags)
+int bch2_btree_node_rewrite_key(struct btree_trans *trans,
+				enum btree_id btree, unsigned level,
+				struct bkey_i *k, unsigned flags)
 {
 	struct btree_iter iter;
 	bch2_trans_node_iter_init(trans, &iter,
@@ -2367,9 +2367,8 @@ static void async_btree_node_rewrite_work(struct work_struct *work)
 
 	int ret = bch2_trans_do(c, bch2_btree_node_rewrite_key(trans,
 						a->btree_id, a->level, a->key.k, 0));
-	if (ret != -ENOENT &&
-	    !bch2_err_matches(ret, EROFS) &&
-	    ret != -BCH_ERR_journal_shutdown)
+	if (!bch2_err_matches(ret, ENOENT) &&
+	    !bch2_err_matches(ret, EROFS))
 		bch_err_fn_ratelimited(c, ret);
 
 	spin_lock(&c->btree_node_rewrites_lock);
diff --git a/libbcachefs/btree_update_interior.h b/libbcachefs/btree_update_interior.h
index b649c36c..ac04e45a 100644
--- a/libbcachefs/btree_update_interior.h
+++ b/libbcachefs/btree_update_interior.h
@@ -176,6 +176,9 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans,
 
 int bch2_btree_node_rewrite(struct btree_trans *, struct btree_iter *,
 			    struct btree *, unsigned, unsigned);
+int bch2_btree_node_rewrite_key(struct btree_trans *,
+				enum btree_id, unsigned,
+				struct bkey_i *, unsigned);
 int bch2_btree_node_rewrite_pos(struct btree_trans *,
 				enum btree_id, unsigned,
 				struct bpos, unsigned, unsigned);
diff --git a/libbcachefs/chardev.c b/libbcachefs/chardev.c
index fde3c238..5ea89aa2 100644
--- a/libbcachefs/chardev.c
+++ b/libbcachefs/chardev.c
@@ -319,6 +319,7 @@ static int bch2_data_thread(void *arg)
 		ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_done;
 		ctx->stats.data_type = (int) DATA_PROGRESS_DATA_TYPE_done;
 	}
+	enumerated_ref_put(&ctx->c->writes, BCH_WRITE_REF_ioctl_data);
 	return 0;
 }
 
@@ -378,15 +379,24 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	struct bch_data_ctx *ctx;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_ioctl_data))
+		return -EROFS;
 
-	if (arg.op >= BCH_DATA_OP_NR || arg.flags)
-		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN)) {
+		ret = -EPERM;
+		goto put_ref;
+	}
+
+	if (arg.op >= BCH_DATA_OP_NR || arg.flags) {
+		ret = -EINVAL;
+		goto put_ref;
+	}
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
+	if (!ctx) {
+		ret = -ENOMEM;
+		goto put_ref;
+	}
 
 	ctx->c = c;
 	ctx->arg = arg;
@@ -395,7 +405,12 @@ static long bch2_ioctl_data(struct bch_fs *c,
 			&bcachefs_data_ops,
 			bch2_data_thread);
 	if (ret < 0)
-		kfree(ctx);
+		goto cleanup;
+	return ret;
+cleanup:
+	kfree(ctx);
+put_ref:
+	enumerated_ref_put(&c->writes, BCH_WRITE_REF_ioctl_data);
 	return ret;
 }
 
diff --git a/libbcachefs/fsck.c b/libbcachefs/fsck.c
index 48810a8e..57ddc20a 100644
--- a/libbcachefs/fsck.c
+++ b/libbcachefs/fsck.c
@@ -327,7 +327,8 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode)
 	    (inode->bi_flags & BCH_INODE_has_child_snapshot))
 		return false;
 
-	return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked);
+	return !bch2_inode_has_backpointer(inode) &&
+		!(inode->bi_flags & BCH_INODE_unlinked);
 }
 
 static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot)
@@ -372,6 +373,18 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (inode->bi_subvol) {
 		inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL;
 
+		struct btree_iter subvol_iter;
+		struct bkey_i_subvolume *subvol =
+			bch2_bkey_get_mut_typed(trans, &subvol_iter,
+						BTREE_ID_subvolumes, POS(0, inode->bi_subvol),
+						0, subvolume);
+		ret = PTR_ERR_OR_ZERO(subvol);
+		if (ret)
+			return ret;
+
+		subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL;
+		bch2_trans_iter_exit(trans, &subvol_iter);
+
 		u64 root_inum;
 		ret = subvol_lookup(trans, inode->bi_parent_subvol,
 				    &dirent_snapshot, &root_inum);
@@ -387,6 +400,8 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (ret)
 		return ret;
 
+	bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum);
+
 	lostfound.bi_nlink += S_ISDIR(inode->bi_mode);
 
 	/* ensure lost+found inode is also present in inode snapshot */
@@ -423,6 +438,16 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (ret)
 		return ret;
 
+	{
+		CLASS(printbuf, buf)();
+		ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum,
+						 inode->bi_snapshot, NULL, &buf);
+		if (ret)
+			return ret;
+
+		bch_info(c, "reattached at %s", buf.buf);
+	}
+
 	/*
 	 * Fix up inodes in child snapshots: if they should also be reattached
 	 * update the backpointer field, if they should not be we need to emit
@@ -490,13 +515,21 @@ static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans,
 static int remove_backpointer(struct btree_trans *trans,
 			      struct bch_inode_unpacked *inode)
 {
-	if (!inode->bi_dir)
+	if (!bch2_inode_has_backpointer(inode))
 		return 0;
 
+	u32 snapshot = inode->bi_snapshot;
+
+	if (inode->bi_parent_subvol) {
+		int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot);
+		if (ret)
+			return ret;
+	}
+
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter,
-				     SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot));
+				     SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot));
 	int ret = bkey_err(d) ?:
 		  dirent_points_to_inode(c, d, inode) ?:
 		  bch2_fsck_remove_dirent(trans, d.k->p);
@@ -1133,13 +1166,14 @@ static int check_inode(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	if (u.bi_dir || u.bi_dir_offset) {
+	if (bch2_inode_has_backpointer(&u)) {
 		ret = check_inode_dirent_inode(trans, &u, &do_update);
 		if (ret)
 			goto err;
 	}
 
-	if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked),
+	if (fsck_err_on(bch2_inode_has_backpointer(&u) &&
+			(u.bi_flags & BCH_INODE_unlinked),
 			trans, inode_unlinked_but_has_dirent,
 			"inode unlinked but has dirent\n%s",
 			(printbuf_reset(&buf),
@@ -1436,6 +1470,7 @@ static int check_key_has_inode(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	struct printbuf buf = PRINTBUF;
+	struct btree_iter iter2 = {};
 	int ret = PTR_ERR_OR_ZERO(i);
 	if (ret)
 		return ret;
@@ -1445,40 +1480,105 @@ static int check_key_has_inode(struct btree_trans *trans,
 
 	bool have_inode = i && !i->whiteout;
 
-	if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) {
-		ret =   reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?:
-			bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
-		if (ret)
-			goto err;
+	if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes)))
+		goto reconstruct;
 
-		inode->last_pos.inode--;
-		ret = bch_err_throw(c, transaction_restart_nested);
-		goto err;
+	if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode))
+		goto out;
+
+	prt_printf(&buf, ", ");
+
+	bool have_old_inode = false;
+	darray_for_each(inode->inodes, i2)
+		if (!i2->whiteout &&
+		    bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) &&
+		    btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) {
+			prt_printf(&buf, "but found good inode in older snapshot\n");
+			bch2_inode_unpacked_to_text(&buf, &i2->inode);
+			prt_newline(&buf);
+			have_old_inode = true;
+			break;
+		}
+
+	struct bkey_s_c k2;
+	unsigned nr_keys = 0;
+
+	prt_printf(&buf, "found keys:\n");
+
+	for_each_btree_key_max_norestart(trans, iter2, iter->btree_id,
+					 SPOS(k.k->p.inode, 0, k.k->p.snapshot),
+					 POS(k.k->p.inode, U64_MAX),
+					 0, k2, ret) {
+		nr_keys++;
+		if (nr_keys <= 10) {
+			bch2_bkey_val_to_text(&buf, c, k2);
+			prt_newline(&buf);
+		}
+		if (nr_keys >= 100)
+			break;
 	}
 
-	if (fsck_err_on(!have_inode,
-			trans, key_in_missing_inode,
-			"key in missing inode:\n%s",
-			(printbuf_reset(&buf),
-			 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		goto delete;
+	if (ret)
+		goto err;
 
-	if (fsck_err_on(have_inode && !btree_matches_i_mode(iter->btree_id, i->inode.bi_mode),
-			trans, key_in_wrong_inode_type,
-			"key for wrong inode mode %o:\n%s",
-			i->inode.bi_mode,
-			(printbuf_reset(&buf),
-			 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		goto delete;
+	if (nr_keys > 100)
+		prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys);
+	else if (nr_keys > 10)
+		prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys);
+
+	if (!have_inode) {
+		if (fsck_err_on(!have_inode,
+				trans, key_in_missing_inode,
+				"key in missing inode%s", buf.buf)) {
+			/*
+			 * Maybe a deletion that raced with data move, or something
+			 * weird like that? But if we know the inode was deleted, or
+			 * it's just a few keys, we can safely delete them.
+			 *
+			 * If it's many keys, we should probably recreate the inode
+			 */
+			if (have_old_inode || nr_keys <= 2)
+				goto delete;
+			else
+				goto reconstruct;
+		}
+	} else {
+		/*
+		 * not autofix, this one would be a giant wtf - bit error in the
+		 * inode corrupting i_mode?
+		 *
+		 * may want to try repairing inode instead of deleting
+		 */
+		if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode),
+				trans, key_in_wrong_inode_type,
+				"key for wrong inode mode %o%s",
+				i->inode.bi_mode, buf.buf))
+			goto delete;
+	}
 out:
 err:
 fsck_err:
+	bch2_trans_iter_exit(trans, &iter2);
 	printbuf_exit(&buf);
 	bch_err_fn(c, ret);
 	return ret;
 delete:
+	/*
+	 * XXX: print out more info
+	 * count up extents for this inode, check if we have different inode in
+	 * an older snapshot version, perhaps decide if we want to reconstitute
+	 */
 	ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node);
 	goto out;
+reconstruct:
+	ret =   reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?:
+		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+	if (ret)
+		goto err;
+
+	inode->last_pos.inode--;
+	ret = bch_err_throw(c, transaction_restart_nested);
+	goto out;
 }
 
 static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w)
@@ -1968,14 +2068,22 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
 				continue;
 		}
 
-		if (fsck_err_on(i->inode.bi_nlink != i->count,
-				trans, inode_dir_wrong_nlink,
-				"directory %llu:%u with wrong i_nlink: got %u, should be %llu",
-				w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_nlink, i->count)) {
-			i->inode.bi_nlink = i->count;
-			ret = bch2_fsck_write_inode(trans, &i->inode);
-			if (ret)
-				break;
+		if (i->inode.bi_nlink != i->count) {
+			CLASS(printbuf, buf)();
+
+			lockrestart_do(trans,
+				       bch2_inum_snapshot_to_path(trans, w->last_pos.inode,
+								  i->inode.bi_snapshot, NULL, &buf));
+
+			if (fsck_err_on(i->inode.bi_nlink != i->count,
+					trans, inode_dir_wrong_nlink,
+					"directory with wrong i_nlink: got %u, should be %llu\n%s",
+					i->inode.bi_nlink, i->count, buf.buf)) {
+				i->inode.bi_nlink = i->count;
+				ret = bch2_fsck_write_inode(trans, &i->inode);
+				if (ret)
+					break;
+			}
 		}
 	}
 fsck_err:
@@ -2512,6 +2620,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 	if (k.k->type != KEY_TYPE_subvolume)
 		return 0;
 
+	subvol_inum start = {
+		.subvol = k.k->p.offset,
+		.inum	= le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode),
+	};
+
 	while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) {
 		ret = darray_push(&subvol_path, k.k->p.offset);
 		if (ret)
@@ -2530,11 +2643,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 
 		if (darray_u32_has(&subvol_path, parent)) {
 			printbuf_reset(&buf);
-			prt_printf(&buf, "subvolume loop:\n");
+			prt_printf(&buf, "subvolume loop: ");
 
-			darray_for_each_reverse(subvol_path, i)
-				prt_printf(&buf, "%u ", *i);
-			prt_printf(&buf, "%u", parent);
+			ret = bch2_inum_to_path(trans, start, &buf);
+			if (ret)
+				goto err;
 
 			if (fsck_err(trans, subvol_loop, "%s", buf.buf))
 				ret = reattach_subvol(trans, s);
@@ -2578,19 +2691,13 @@ int bch2_check_subvolume_structure(struct bch_fs *c)
 	return ret;
 }
 
-struct pathbuf_entry {
-	u64	inum;
-	u32	snapshot;
-};
-
-typedef DARRAY(struct pathbuf_entry) pathbuf;
-
-static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p,
+static int bch2_bi_depth_renumber_one(struct btree_trans *trans,
+				      u64 inum, u32 snapshot,
 				      u32 new_depth)
 {
 	struct btree_iter iter;
 	struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
-					       SPOS(0, p->inum, p->snapshot), 0);
+					       SPOS(0, inum, snapshot), 0);
 
 	struct bch_inode_unpacked inode;
 	int ret = bkey_err(k) ?:
@@ -2609,14 +2716,15 @@ err:
 	return ret;
 }
 
-static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth)
+static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path,
+				  u32 snapshot, u32 new_bi_depth)
 {
 	u32 restart_count = trans->restart_count;
 	int ret = 0;
 
 	darray_for_each_reverse(*path, i) {
 		ret = nested_lockrestart_do(trans,
-				bch2_bi_depth_renumber_one(trans, i, new_bi_depth));
+				bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth));
 		bch_err_fn(trans->c, ret);
 		if (ret)
 			break;
@@ -2627,37 +2735,36 @@ static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32
 	return ret ?: trans_was_restarted(trans, restart_count);
 }
 
-static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot)
-{
-	darray_for_each(*p, i)
-		if (i->inum	== inum &&
-		    i->snapshot	== snapshot)
-			return true;
-	return false;
-}
-
 static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter inode_iter = {};
-	pathbuf path = {};
+	darray_u64 path = {};
 	struct printbuf buf = PRINTBUF;
 	u32 snapshot = inode_k.k->p.snapshot;
 	bool redo_bi_depth = false;
 	u32 min_bi_depth = U32_MAX;
 	int ret = 0;
 
+	struct bpos start = inode_k.k->p;
+
 	struct bch_inode_unpacked inode;
 	ret = bch2_inode_unpack(inode_k, &inode);
 	if (ret)
 		return ret;
 
-	while (!inode.bi_subvol) {
+	/*
+	 * If we're running full fsck, check_dirents() will have already ran,
+	 * and we shouldn't see any missing backpointers here - otherwise that's
+	 * handled separately, by check_unreachable_inodes
+	 */
+	while (!inode.bi_subvol &&
+	       bch2_inode_has_backpointer(&inode)) {
 		struct btree_iter dirent_iter;
 		struct bkey_s_c_dirent d;
-		u32 parent_snapshot = snapshot;
 
-		d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot);
+		d = dirent_get_by_pos(trans, &dirent_iter,
+				      SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot));
 		ret = bkey_err(d.s_c);
 		if (ret && !bch2_err_matches(ret, ENOENT))
 			goto out;
@@ -2675,15 +2782,10 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 
 		bch2_trans_iter_exit(trans, &dirent_iter);
 
-		ret = darray_push(&path, ((struct pathbuf_entry) {
-			.inum		= inode.bi_inum,
-			.snapshot	= snapshot,
-		}));
+		ret = darray_push(&path, inode.bi_inum);
 		if (ret)
 			return ret;
 
-		snapshot = parent_snapshot;
-
 		bch2_trans_iter_exit(trans, &inode_iter);
 		inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes,
 					     SPOS(0, inode.bi_dir, snapshot), 0);
@@ -2705,15 +2807,22 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 			break;
 
 		inode = parent_inode;
-		snapshot = inode_k.k->p.snapshot;
 		redo_bi_depth = true;
 
-		if (path_is_dup(&path, inode.bi_inum, snapshot)) {
+		if (darray_find(path, inode.bi_inum)) {
 			printbuf_reset(&buf);
-			prt_printf(&buf, "directory structure loop:\n");
-			darray_for_each_reverse(path, i)
-				prt_printf(&buf, "%llu:%u ", i->inum, i->snapshot);
-			prt_printf(&buf, "%llu:%u", inode.bi_inum, snapshot);
+			prt_printf(&buf, "directory structure loop in snapshot %u: ",
+				   snapshot);
+
+			ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf);
+			if (ret)
+				goto out;
+
+			if (c->opts.verbose) {
+				prt_newline(&buf);
+				darray_for_each(path, i)
+					prt_printf(&buf, "%llu ", *i);
+			}
 
 			if (fsck_err(trans, dir_loop, "%s", buf.buf)) {
 				ret = remove_backpointer(trans, &inode);
@@ -2733,7 +2842,7 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 		min_bi_depth = 0;
 
 	if (redo_bi_depth)
-		ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth);
+		ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth);
 out:
 fsck_err:
 	bch2_trans_iter_exit(trans, &inode_iter);
@@ -2750,7 +2859,7 @@ fsck_err:
 int bch2_check_directory_structure(struct bch_fs *c)
 {
 	int ret = bch2_trans_run(c,
-		for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN,
+		for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN,
 					  BTREE_ITER_intent|
 					  BTREE_ITER_prefetch|
 					  BTREE_ITER_all_snapshots, k,
diff --git a/libbcachefs/inode.h b/libbcachefs/inode.h
index 82cec283..b8ec3e62 100644
--- a/libbcachefs/inode.h
+++ b/libbcachefs/inode.h
@@ -254,6 +254,11 @@ static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_
 		: c->opts.casefold;
 }
 
+static inline bool bch2_inode_has_backpointer(const struct bch_inode_unpacked *bi)
+{
+	return bi->bi_dir || bi->bi_dir_offset;
+}
+
 /* i_nlink: */
 
 static inline unsigned nlink_bias(umode_t mode)
diff --git a/libbcachefs/io_read.c b/libbcachefs/io_read.c
index 04bbdcf5..cd184b21 100644
--- a/libbcachefs/io_read.c
+++ b/libbcachefs/io_read.c
@@ -1491,7 +1491,12 @@ void bch2_read_bio_to_text(struct printbuf *out, struct bch_read_bio *rbio)
 	prt_printf(out, "have_ioref:\t%u\n",	rbio->have_ioref);
 	prt_printf(out, "narrow_crcs:\t%u\n",	rbio->narrow_crcs);
 	prt_printf(out, "context:\t%u\n",	rbio->context);
-	prt_printf(out, "ret:\t%s\n",		bch2_err_str(rbio->ret));
+
+	int ret = READ_ONCE(rbio->ret);
+	if (ret < 0)
+		prt_printf(out, "ret:\t%s\n",		bch2_err_str(ret));
+	else
+		prt_printf(out, "ret:\t%i\n",		ret);
 
 	prt_printf(out, "flags:\t");
 	bch2_prt_bitflags(out, bch2_read_bio_flags, rbio->flags);
diff --git a/libbcachefs/namei.c b/libbcachefs/namei.c
index 779c22eb..c3f87c59 100644
--- a/libbcachefs/namei.c
+++ b/libbcachefs/namei.c
@@ -625,14 +625,26 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 {
 	unsigned orig_pos = path->pos;
 	int ret = 0;
+	DARRAY(subvol_inum) inums = {};
+
+	if (!snapshot) {
+		ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot);
+		if (ret)
+			goto disconnected;
+	}
 
 	while (true) {
-		if (!snapshot) {
-			ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot);
-			if (ret)
-				goto disconnected;
+		subvol_inum n = (subvol_inum) { subvol ?: snapshot, inum };
+
+		if (darray_find_p(inums, i, i->subvol == n.subvol && i->inum == n.inum)) {
+			prt_str_reversed(path, "(loop)");
+			break;
 		}
 
+		ret = darray_push(&inums, n);
+		if (ret)
+			goto err;
+
 		struct bch_inode_unpacked inode;
 		ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, &inode, 0);
 		if (ret)
@@ -650,7 +662,9 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 		inum = inode.bi_dir;
 		if (inode.bi_parent_subvol) {
 			subvol = inode.bi_parent_subvol;
-			snapshot = 0;
+			ret = bch2_subvolume_get_snapshot(trans, inode.bi_parent_subvol, &snapshot);
+			if (ret)
+				goto disconnected;
 		}
 
 		struct btree_iter d_iter;
@@ -662,6 +676,7 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 			goto disconnected;
 
 		struct qstr dirent_name = bch2_dirent_get_name(d);
+
 		prt_bytes_reversed(path, dirent_name.name, dirent_name.len);
 
 		prt_char(path, '/');
@@ -677,8 +692,10 @@ out:
 		goto err;
 
 	reverse_bytes(path->buf + orig_pos, path->pos - orig_pos);
+	darray_exit(&inums);
 	return 0;
 err:
+	darray_exit(&inums);
 	return ret;
 disconnected:
 	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -717,8 +734,7 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans,
 	if (inode_points_to_dirent(target, d))
 		return 0;
 
-	if (!target->bi_dir &&
-	    !target->bi_dir_offset) {
+	if (!bch2_inode_has_backpointer(target)) {
 		fsck_err_on(S_ISDIR(target->bi_mode),
 			    trans, inode_dir_missing_backpointer,
 			    "directory with missing backpointer\n%s",
diff --git a/libbcachefs/recovery.c b/libbcachefs/recovery.c
index 37f2cc1e..fa5d1ef5 100644
--- a/libbcachefs/recovery.c
+++ b/libbcachefs/recovery.c
@@ -762,6 +762,16 @@ int bch2_fs_recovery(struct bch_fs *c)
 		c->opts.fsck = true;
 	}
 
+	if (go_rw_in_recovery(c)) {
+		/*
+		 * start workqueues/kworkers early - kthread creation checks for
+		 * pending signals, which is _very_ annoying
+		 */
+		ret = bch2_fs_init_rw(c);
+		if (ret)
+			goto err;
+	}
+
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 	bool write_sb = false;
diff --git a/libbcachefs/recovery_passes.c b/libbcachefs/recovery_passes.c
index 35ac0d64..c2c18c0a 100644
--- a/libbcachefs/recovery_passes.c
+++ b/libbcachefs/recovery_passes.c
@@ -217,11 +217,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c)
 
 	set_bit(BCH_FS_may_go_rw, &c->flags);
 
-	if (keys->nr ||
-	    !c->opts.read_only ||
-	    !c->sb.clean ||
-	    c->opts.recovery_passes ||
-	    (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))) {
+	if (go_rw_in_recovery(c)) {
 		if (c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)) {
 			bch_info(c, "mounting a filesystem with no alloc info read-write; will recreate");
 			bch2_reconstruct_alloc(c);
diff --git a/libbcachefs/recovery_passes.h b/libbcachefs/recovery_passes.h
index 260571c7..2117f0ce 100644
--- a/libbcachefs/recovery_passes.h
+++ b/libbcachefs/recovery_passes.h
@@ -17,6 +17,15 @@ enum bch_run_recovery_pass_flags {
 	RUN_RECOVERY_PASS_ratelimit	= BIT(1),
 };
 
+static inline bool go_rw_in_recovery(struct bch_fs *c)
+{
+	return (c->journal_keys.nr ||
+		!c->opts.read_only ||
+		!c->sb.clean ||
+		c->opts.recovery_passes ||
+		(c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info))));
+}
+
 int bch2_run_print_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass);
 
 int __bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *,
diff --git a/libbcachefs/sb-errors_format.h b/libbcachefs/sb-errors_format.h
index 82ecee3d..f1aa4054 100644
--- a/libbcachefs/sb-errors_format.h
+++ b/libbcachefs/sb-errors_format.h
@@ -251,7 +251,7 @@ enum bch_fsck_flags {
 	x(deleted_inode_not_unlinked,				214,	FSCK_AUTOFIX)	\
 	x(deleted_inode_has_child_snapshots,			288,	FSCK_AUTOFIX)	\
 	x(extent_overlapping,					215,	0)		\
-	x(key_in_missing_inode,					216,	0)		\
+	x(key_in_missing_inode,					216,	FSCK_AUTOFIX)	\
 	x(key_in_wrong_inode_type,				217,	0)		\
 	x(extent_past_end_of_inode,				218,	FSCK_AUTOFIX)	\
 	x(dirent_empty_name,					219,	0)		\
@@ -260,11 +260,11 @@ enum bch_fsck_flags {
 	x(dirent_name_embedded_nul,				222,	0)		\
 	x(dirent_name_dot_or_dotdot,				223,	0)		\
 	x(dirent_name_has_slash,				224,	0)		\
-	x(dirent_d_type_wrong,					225,	0)		\
+	x(dirent_d_type_wrong,					225,	FSCK_AUTOFIX)	\
 	x(inode_bi_parent_wrong,				226,	0)		\
 	x(dirent_in_missing_dir_inode,				227,	0)		\
 	x(dirent_in_non_dir_inode,				228,	0)		\
-	x(dirent_to_missing_inode,				229,	0)		\
+	x(dirent_to_missing_inode,				229,	FSCK_AUTOFIX)	\
 	x(dirent_to_overwritten_inode,				302,	0)		\
 	x(dirent_to_missing_subvol,				230,	0)		\
 	x(dirent_to_itself,					231,	0)		\
diff --git a/libbcachefs/super.c b/libbcachefs/super.c
index a5b97c9c..69c097ff 100644
--- a/libbcachefs/super.c
+++ b/libbcachefs/super.c
@@ -210,7 +210,6 @@ static int bch2_dev_alloc(struct bch_fs *, unsigned);
 static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *);
 static void bch2_dev_io_ref_stop(struct bch_dev *, int);
 static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *);
-static int bch2_fs_init_rw(struct bch_fs *);
 
 struct bch_fs *bch2_dev_to_fs(dev_t dev)
 {
@@ -794,7 +793,7 @@ err:
 	return ret;
 }
 
-static int bch2_fs_init_rw(struct bch_fs *c)
+int bch2_fs_init_rw(struct bch_fs *c)
 {
 	if (test_bit(BCH_FS_rw_init_done, &c->flags))
 		return 0;
@@ -1015,6 +1014,16 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 	if (ret)
 		goto err;
 
+	if (go_rw_in_recovery(c)) {
+		/*
+		 * start workqueues/kworkers early - kthread creation checks for
+		 * pending signals, which is _very_ annoying
+		 */
+		ret = bch2_fs_init_rw(c);
+		if (ret)
+			goto err;
+	}
+
 #ifdef CONFIG_UNICODE
 	/* Default encoding until we can potentially have more as an option. */
 	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
diff --git a/libbcachefs/super.h b/libbcachefs/super.h
index dc52f06c..e90bab9a 100644
--- a/libbcachefs/super.h
+++ b/libbcachefs/super.h
@@ -46,6 +46,7 @@ void __bch2_fs_stop(struct bch_fs *);
 void bch2_fs_free(struct bch_fs *);
 void bch2_fs_stop(struct bch_fs *);
 
+int bch2_fs_init_rw(struct bch_fs *);
 int bch2_fs_start(struct bch_fs *);
 struct bch_fs *bch2_fs_open(darray_const_str *, struct bch_opts *);