Merge tag 'bcachefs-2025-02-20' of git://evilpiepirate.org/bcachefs

Pull bcachefs fixes from Kent Overstreet:
 "Small stuff:

   - The fsck code for Hongbo's directory i_size patch was wrong, caught
     by transaction restart injection: we now have the CI running
     another test variant with restart injection enabled

   - Another fixup for reflink pointers to missing indirect extents:
     previous fix was for fsck code, this fixes the normal runtime paths

   - Another small srcu lock hold time fix, reported by jpsollie"

* tag 'bcachefs-2025-02-20' of git://evilpiepirate.org/bcachefs:
  bcachefs: Fix srcu lock warning in btree_update_nodes_written()
  bcachefs: Fix bch2_indirect_extent_missing_error()
  bcachefs: Fix fsck directory i_size checking

Author: torvalds

fs/bcachefs/btree_update_interior.c

@@ -681,9 +681,11 @@ static void btree_update_nodes_written(struct btree_update *as)
 
 		b = as->old_nodes[i];
 
+		bch2_trans_begin(trans);
 		btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
 		seq = b->data ? b->data->keys.seq : 0;
 		six_unlock_read(&b->c.lock);
+		bch2_trans_unlock_long(trans);
 
 		if (seq == as->old_nodes_seq[i])
 			wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner,

fs/bcachefs/fsck.c

@@ -823,6 +823,7 @@ struct inode_walker_entry {
 	struct bch_inode_unpacked inode;
 	u32			snapshot;
 	u64			count;
+	u64			i_size;
 };
 
 struct inode_walker {
@@ -910,8 +911,9 @@ lookup_inode_for_snapshot(struct bch_fs *c, struct inode_walker *w, struct bkey_
 	if (k.k->p.snapshot != i->snapshot && !is_whiteout) {
 		struct inode_walker_entry new = *i;
 
-		new.snapshot = k.k->p.snapshot;
-		new.count = 0;
+		new.snapshot	= k.k->p.snapshot;
+		new.count	= 0;
+		new.i_size	= 0;
 
 		struct printbuf buf = PRINTBUF;
 		bch2_bkey_val_to_text(&buf, c, k);
@@ -1116,37 +1118,6 @@ static int get_snapshot_root_inode(struct btree_trans *trans,
 	return ret;
 }
 
-static int check_directory_size(struct btree_trans *trans,
-				struct bch_inode_unpacked *inode_u,
-				struct bkey_s_c inode_k, bool *write_inode)
-{
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	u64 new_size = 0;
-	int ret;
-
-	for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents,
-			SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot),
-			POS(inode_k.k->p.offset, U64_MAX),
-			0, k, ret) {
-		if (k.k->type != KEY_TYPE_dirent)
-			continue;
-
-		struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k);
-		struct qstr name = bch2_dirent_get_name(dirent);
-
-		new_size += dirent_occupied_size(&name);
-	}
-	bch2_trans_iter_exit(trans, &iter);
-
-	if (!ret && inode_u->bi_size != new_size) {
-		inode_u->bi_size = new_size;
-		*write_inode = true;
-	}
-
-	return ret;
-}
-
 static int check_inode(struct btree_trans *trans,
 		       struct btree_iter *iter,
 		       struct bkey_s_c k,
@@ -1335,16 +1306,6 @@ static int check_inode(struct btree_trans *trans,
 		u.bi_journal_seq = journal_cur_seq(&c->journal);
 		do_update = true;
 	}
-
-	if (S_ISDIR(u.bi_mode)) {
-		ret = check_directory_size(trans, &u, k, &do_update);
-
-		fsck_err_on(ret,
-			    trans, directory_size_mismatch,
-			    "directory inode %llu:%u with the mismatch directory size",
-			    u.bi_inum, k.k->p.snapshot);
-		ret = 0;
-	}
 do_update:
 	if (do_update) {
 		ret = __bch2_fsck_write_inode(trans, &u);
@@ -2017,10 +1978,31 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
 	return ret;
 }
 
-static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w)
+static int check_dir_i_size_notnested(struct btree_trans *trans, struct inode_walker *w)
+{
+	struct bch_fs *c = trans->c;
+	int ret = 0;
+
+	darray_for_each(w->inodes, i)
+		if (fsck_err_on(i->inode.bi_size != i->i_size,
+				trans, inode_dir_wrong_nlink,
+				"directory %llu:%u with wrong i_size: got %llu, should be %llu",
+				w->last_pos.inode, i->snapshot, i->inode.bi_size, i->i_size)) {
+			i->inode.bi_size = i->i_size;
+			ret = bch2_fsck_write_inode(trans, &i->inode);
+			if (ret)
+				break;
+		}
+fsck_err:
+	bch_err_fn(c, ret);
+	return ret;
+}
+
+static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w)
 {
 	u32 restart_count = trans->restart_count;
 	return check_subdir_count_notnested(trans, w) ?:
+		check_dir_i_size_notnested(trans, w) ?:
 		trans_was_restarted(trans, restart_count);
 }
 
@@ -2367,7 +2349,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 		goto out;
 
 	if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) {
-		ret = check_subdir_count(trans, dir);
+		ret = check_subdir_dirents_count(trans, dir);
 		if (ret)
 			goto err;
 	}
@@ -2457,9 +2439,11 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 	if (ret)
 		goto err;
 
-	if (d.v->d_type == DT_DIR)
-		for_each_visible_inode(c, s, dir, d.k->p.snapshot, i)
+	for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) {
+		if (d.v->d_type == DT_DIR)
 			i->count++;
+		i->i_size += bkey_bytes(d.k);
+	}
 out:
 err:
 fsck_err:

fs/bcachefs/reflink.c

@@ -172,7 +172,7 @@ static int bch2_indirect_extent_missing_error(struct btree_trans *trans,
 					      bool should_commit)
 {
 	if (REFLINK_P_ERROR(p.v))
-		return -BCH_ERR_missing_indirect_extent;
+		return 0;
 
 	struct bch_fs *c = trans->c;
 	u64 live_start	= REFLINK_P_IDX(p.v);
@@ -259,23 +259,23 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans,
 		return k;
 
 	if (unlikely(!bkey_extent_is_reflink_data(k.k))) {
-		bch2_trans_iter_exit(trans, iter);
-
 		unsigned size = min((u64) k.k->size,
 				    REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) -
 				    reflink_offset);
 		bch2_key_resize(&iter->k, size);
 
 		int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset,
 							     k.k->p.offset, should_commit);
-		if (ret)
+		if (ret) {
+			bch2_trans_iter_exit(trans, iter);
 			return bkey_s_c_err(ret);
+		}
 	} else if (unlikely(REFLINK_P_ERROR(p.v))) {
-		bch2_trans_iter_exit(trans, iter);
-
 		int ret = bch2_indirect_extent_not_missing(trans, p, should_commit);
-		if (ret)
+		if (ret) {
+			bch2_trans_iter_exit(trans, iter);
 			return bkey_s_c_err(ret);
+		}
 	}
 
 	*offset_into_extent = reflink_offset - bkey_start_offset(k.k);
@@ -300,7 +300,7 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans,
 	if (ret)
 		return ret;
 
-	if (bkey_deleted(k.k)) {
+	if (!bkey_refcount_c(k)) {
 		if (!(flags & BTREE_TRIGGER_overwrite))
 			ret = -BCH_ERR_missing_indirect_extent;
 		goto next;
@@ -381,8 +381,6 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans,
 not_found:
 	if (flags & BTREE_TRIGGER_check_repair) {
 		ret = bch2_indirect_extent_missing_error(trans, p, *idx, next_idx, false);
-		if (ret == -BCH_ERR_missing_indirect_extent)
-			ret = 0;
 		if (ret)
 			goto err;
 	}

fs/bcachefs/sb-downgrade.c

@@ -92,7 +92,7 @@
 	  BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0,	\
 	  BCH_FSCK_ERR_accounting_key_junk_at_end)		\
 	x(directory_size,					\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_inodes),		\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_dirents),		\
 	  BCH_FSCK_ERR_directory_size_mismatch)			\
 
 #define DOWNGRADE_TABLE()					\