Reducing connection overhead in pg_upgrade compat check phase

From 18f406c16e5ebeaaf4a24c5b5a57a8358a91afb4 Mon Sep 17 00:00:00 2001
From: Justin Pryzby <pryzbyj@telsasoft.com>
Date: Fri, 17 Feb 2023 19:51:42 -0600
Subject: [PATCH] wip: pg_upgrade data structure

---
 src/bin/pg_upgrade/check.c      | 929 ++++++++++++++------------------
 src/bin/pg_upgrade/pg_upgrade.h |  10 +-
 src/bin/pg_upgrade/version.c    | 256 ++++-----
 3 files changed, 517 insertions(+), 678 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 189aa51c4f8..5a5f69e789b 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -23,17 +23,17 @@ static bool equivalent_locale(int category, const char *loca, const char *locb);
 static void check_is_install_user(ClusterInfo *cluster);
 static void check_proper_datallowconn(ClusterInfo *cluster);
 static void check_for_prepared_transactions(ClusterInfo *cluster);
-static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
-static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
-static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
-static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
+static bool check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_user_defined_postfix_ops(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_incompatible_polymorphics(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_tables_with_oids(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_composite_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_reg_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_aclitem_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+static bool check_for_jsonb_9_4_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
-static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
+static bool check_for_user_defined_encoding_conversions(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
 static char *get_canonical_locale_name(int category, const char *locale);
 
 
@@ -88,6 +88,127 @@ check_and_dump_old_cluster(bool live_check)
 {
 	/* -- OLD -- */
 
+	struct checks {
+		int maxmajor; /* Last major version that needs this test */
+		bool (*fn)(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+		char *scriptname;
+		char *fataltext;
+		/* filled in later: */
+		FILE *scriptfp;
+		bool failedtests;
+	} checks[] = {
+		{0, check_for_composite_data_type_usage,
+			 "tables_using_composite.txt",
+			 .fataltext = "Your installation contains system-defined composite type(s) in user tables.\n"
+				 "These type OIDs are not stable across PostgreSQL versions,\n"
+				 "so this cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{0, check_for_reg_data_type_usage,
+			 "tables_using_reg.txt",
+			 .fataltext = "Your installation contains one of the reg* data types in user tables.\n"
+				 "These data types reference system OIDs that are not preserved by\n"
+				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{1500, check_for_aclitem_data_type_usage,
+			"tables_using_aclitem.txt",
+			.fataltext = "Your installation contains the \"aclitem\" data type in user tables.\n"
+				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+				 "so this cluster cannot currently be upgraded.  You can drop the\n"
+				 "problem columns and restart the upgrade.  A list of the problem\n"
+				 "columns is in the file:\n",
+		},
+
+		{1300, check_for_user_defined_encoding_conversions,
+			 "encoding_conversions.txt",
+			 .fataltext = "Your installation contains user-defined encoding conversions.\n"
+				 "The conversion function parameters changed in PostgreSQL version 14\n"
+				 "so this cluster cannot currently be upgraded.  You can remove the\n"
+				 "encoding conversions in the old cluster and restart the upgrade.\n"
+				 "A list of user-defined encoding conversions is in the file:\n"
+		},
+
+		{1300, check_for_user_defined_postfix_ops,
+			"postfix_ops.txt",
+			.fataltext = "Your installation contains user-defined postfix operators, which are not\n"
+				"supported anymore.  Consider dropping the postfix operators and replacing\n"
+				"them with prefix operators or function calls.\n"
+				"A list of user-defined postfix operators is in the file:\n",
+		},
+
+		{1300, check_for_incompatible_polymorphics,
+			 "incompatible_polymorphics.txt",
+			 .fataltext = "Your installation contains user-defined objects that refer to internal\n"
+				 "polymorphic functions with arguments of type \"anyarray\" or \"anyelement\".\n"
+				 "These user-defined objects must be dropped before upgrading and restored\n"
+				 "afterwards, changing them to refer to the new corresponding functions with\n"
+				 "arguments of type \"anycompatiblearray\" and \"anycompatible\".\n"
+				 "A list of the problematic objects is in the file:\n",
+		},
+
+		{1100, check_for_tables_with_oids,
+			 "tables_with_oids.txt",
+			 .fataltext = "Your installation contains tables declared WITH OIDS, which is not\n"
+				 "supported anymore.  Consider removing the oid column using\n"
+				 "    ALTER TABLE ... SET WITHOUT OIDS;\n"
+				 "A list of tables with the problem is in the file:\n",
+		},
+
+		{1100, old_11_check_for_sql_identifier_data_type_usage,
+			 "tables_using_sql_identifier.txt",
+			 .fataltext = "Your installation contains the \"sql_identifier\" data type in user tables.\n"
+				 "The on-disk format for this data type has changed, so this\n"
+				 "cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{906, old_9_6_check_for_unknown_data_type_usage,
+			 "tables_using_unknown.txt",
+			 .fataltext = "Your installation contains the \"unknown\" data type in user tables.\n"
+				 "This data type is no longer allowed in tables, so this\n"
+				 "cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{904, check_for_jsonb_9_4_usage,
+			 "tables_using_jsonb.txt",
+			 .fataltext = "Your installation contains the \"jsonb\" data type in user tables.\n"
+				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+				 "cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{903, old_9_3_check_for_line_data_type_usage,
+			 "tables_using_line.txt",
+			 .fataltext = "Your installation contains the \"line\" data type in user tables.\n"
+				 "This data type changed its internal and input/output format\n"
+				 "between your old and new versions so this\n"
+				 "cluster cannot currently be upgraded.  You can\n"
+				 "drop the problem columns and restart the upgrade.\n"
+				 "A list of the problem columns is in the file:\n",
+		},
+
+		{0000, check_for_isn_and_int8_passing_mismatch,
+			"contrib_isn_and_int8_pass_by_value.txt",
+			.fataltext = "Your installation contains \"contrib/isn\" functions which rely on the\n"
+				"bigint data type.  Your old and new clusters pass bigint values\n"
+				"differently so this cluster cannot currently be upgraded.  You can\n"
+				"manually dump databases in the old cluster that use \"contrib/isn\"\n"
+				"facilities, drop them, perform the upgrade, and then restore them.  A\n"
+				"list of the problem functions is in the file:\n"
+		},
+
+		{ .fn = NULL, } /* sentinel */
+	};
+
 	if (!live_check)
 		start_postmaster(&old_cluster, true);
 
@@ -98,61 +219,76 @@ check_and_dump_old_cluster(bool live_check)
 
 	get_loadable_libraries();
 
-
 	/*
 	 * Check for various failure cases
 	 */
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
-	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
-	 * format for existing data.
+	 * For each DB, run all checks.  This amortizes the cost of opening new
+	 * DB connections in case there are many DBs.
 	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
 
-	/*
-	 * PG 14 changed the function signature of encoding conversion functions.
-	 * Conversions from older versions cannot be upgraded automatically
-	 * because the user-defined functions used by the encoding conversions
-	 * need to be changed to match the new signature.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300)
-		check_for_user_defined_encoding_conversions(&old_cluster);
+	for (int dbnum = 0; dbnum < old_cluster.dbarr.ndbs; dbnum++)
+	{
+		DbInfo		*active_db = &old_cluster.dbarr.dbs[dbnum];
+		PGconn	    *conn = connectToServer(&old_cluster, active_db->db_name);
 
-	/*
-	 * Pre-PG 14 allowed user defined postfix operators, which are not
-	 * supported anymore.  Verify there are none, iff applicable.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300)
-		check_for_user_defined_postfix_ops(&old_cluster);
+		for (struct checks *check = checks; check->fn != NULL; check++)
+		{
+			bool		ret;
 
-	/*
-	 * PG 14 changed polymorphic functions from anyarray to
-	 * anycompatiblearray.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300)
-		check_for_incompatible_polymorphics(&old_cluster);
+			if (GET_MAJOR_VERSION(old_cluster.major_version) > check->maxmajor &&
+					check->maxmajor != 0)
+				continue;
 
-	/*
-	 * Pre-PG 12 allowed tables to be declared WITH OIDS, which is not
-	 * supported anymore. Verify there are none, iff applicable.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		check_for_tables_with_oids(&old_cluster);
+			if (check->scriptfp == NULL)
+			{
+				char		output_path[MAXPGPATH];
+				snprintf(output_path, sizeof(output_path), "%s/%s",
+						log_opts.basedir, check->scriptname);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
+				if ((check->scriptfp = fopen_priv(output_path, "w")) == NULL)
+					pg_fatal("could not open file \"%s\": %m", output_path);
+			}
+
+			ret = check->fn(&old_cluster, active_db, conn, check->scriptfp);
+			if (!ret)
+			{
+				if (!check->failedtests)
+					pg_log(PG_WARNING, "%s  %s", _(check->fataltext),
+							check->scriptname);
+				check->failedtests = true;
+			}
+		}
+
+		PQfinish(conn);
+	}
+
+	/* Remove empty script files for successful tests */
+	for (struct checks *check = checks; check->fn != NULL; check++)
+	{
+		char		output_path[MAXPGPATH];
+
+		if (check->failedtests)
+			continue;
+
+		/* This ought to be empty */
+		snprintf(output_path, sizeof(output_path), "%s/%s",
+				log_opts.basedir, check->scriptname);
+		unlink(output_path);
+	}
+
+	for (struct checks *check = checks; check->fn != NULL; check++)
+	{
+		if (check->failedtests)
+		{
+			pg_log(PG_REPORT, "fatal");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
@@ -160,7 +296,6 @@ check_and_dump_old_cluster(bool live_check)
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -169,14 +304,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -833,179 +960,116 @@ check_for_prepared_transactions(ClusterInfo *cluster)
  *	by value.  The schema dumps the CREATE TYPE PASSEDBYVALUE setting so
  *	it must match for the old and new servers.
  */
-static void
-check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster)
+static bool
+check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	int			dbnum;
-	FILE	   *script = NULL;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for contrib/isn with bigint-passing mismatch");
+	PGresult   *res;
+	bool		db_used = false;
+	int			ntups;
+	int			rowno;
+	int			i_nspname,
+				i_proname;
 
 	if (old_cluster.controldata.float8_pass_by_value ==
 		new_cluster.controldata.float8_pass_by_value)
 	{
 		/* no mismatch */
-		check_ok();
-		return;
+		return true;
 	}
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "contrib_isn_and_int8_pass_by_value.txt");
+	/* Find any functions coming from contrib/isn */
+	res = executeQueryOrDie(conn,
+							"SELECT n.nspname, p.proname "
+							"FROM	pg_catalog.pg_proc p, "
+							"		pg_catalog.pg_namespace n "
+							"WHERE	p.pronamespace = n.oid AND "
+							"		p.probin = '$libdir/isn'");
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	ntups = PQntuples(res);
+	i_nspname = PQfnumber(res, "nspname");
+	i_proname = PQfnumber(res, "proname");
+	for (rowno = 0; rowno < ntups; rowno++)
 	{
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_proname;
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-
-		/* Find any functions coming from contrib/isn */
-		res = executeQueryOrDie(conn,
-								"SELECT n.nspname, p.proname "
-								"FROM	pg_catalog.pg_proc p, "
-								"		pg_catalog.pg_namespace n "
-								"WHERE	p.pronamespace = n.oid AND "
-								"		p.probin = '$libdir/isn'");
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_proname = PQfnumber(res, "proname");
-		for (rowno = 0; rowno < ntups; rowno++)
+		if (!db_used)
 		{
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s",
-						 output_path, strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_proname));
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
 		}
 
-		PQclear(res);
-
-		PQfinish(conn);
+		fprintf(script, "  %s.%s\n",
+				PQgetvalue(res, rowno, i_nspname),
+				PQgetvalue(res, rowno, i_proname));
 	}
 
-	if (script)
-	{
-		fclose(script);
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains \"contrib/isn\" functions which rely on the\n"
-				 "bigint data type.  Your old and new clusters pass bigint values\n"
-				 "differently so this cluster cannot currently be upgraded.  You can\n"
-				 "manually dump databases in the old cluster that use \"contrib/isn\"\n"
-				 "facilities, drop them, perform the upgrade, and then restore them.  A\n"
-				 "list of the problem functions is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	PQclear(res);
+	return ntups == 0;
 }
 
 /*
  * Verify that no user defined postfix operators exist.
- */
-static void
-check_for_user_defined_postfix_ops(ClusterInfo *cluster)
-{
-	int			dbnum;
-	FILE	   *script = NULL;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for user-defined postfix operators");
+ *
+ * Pre-PG 14 allowed user defined postfix operators, which are not
+ * supported anymore.
+*/
+static bool
+check_for_user_defined_postfix_ops(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "postfix_ops.txt");
+{
+	PGresult   *res;
+	bool		db_used = false;
+	int			ntups;
+	int			rowno;
+	int			i_oproid,
+				i_oprnsp,
+				i_oprname,
+				i_typnsp,
+				i_typname;
 
-	/* Find any user defined postfix operators */
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	/*
+	 * The query below hardcodes FirstNormalObjectId as 16384 rather than
+	 * interpolating that C #define into the query because, if that
+	 * #define is ever changed, the cutoff we want to use is the value
+	 * used by pre-version 14 servers, not that of some future version.
+	 */
+	res = executeQueryOrDie(conn,
+							"SELECT o.oid AS oproid, "
+							"       n.nspname AS oprnsp, "
+							"       o.oprname, "
+							"       tn.nspname AS typnsp, "
+							"       t.typname "
+							"FROM pg_catalog.pg_operator o, "
+							"     pg_catalog.pg_namespace n, "
+							"     pg_catalog.pg_type t, "
+							"     pg_catalog.pg_namespace tn "
+							"WHERE o.oprnamespace = n.oid AND "
+							"      o.oprleft = t.oid AND "
+							"      t.typnamespace = tn.oid AND "
+							"      o.oprright = 0 AND "
+							"      o.oid >= 16384");
+	ntups = PQntuples(res);
+	i_oproid = PQfnumber(res, "oproid");
+	i_oprnsp = PQfnumber(res, "oprnsp");
+	i_oprname = PQfnumber(res, "oprname");
+	i_typnsp = PQfnumber(res, "typnsp");
+	i_typname = PQfnumber(res, "typname");
+	for (rowno = 0; rowno < ntups; rowno++)
 	{
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_oproid,
-					i_oprnsp,
-					i_oprname,
-					i_typnsp,
-					i_typname;
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-
-		/*
-		 * The query below hardcodes FirstNormalObjectId as 16384 rather than
-		 * interpolating that C #define into the query because, if that
-		 * #define is ever changed, the cutoff we want to use is the value
-		 * used by pre-version 14 servers, not that of some future version.
-		 */
-		res = executeQueryOrDie(conn,
-								"SELECT o.oid AS oproid, "
-								"       n.nspname AS oprnsp, "
-								"       o.oprname, "
-								"       tn.nspname AS typnsp, "
-								"       t.typname "
-								"FROM pg_catalog.pg_operator o, "
-								"     pg_catalog.pg_namespace n, "
-								"     pg_catalog.pg_type t, "
-								"     pg_catalog.pg_namespace tn "
-								"WHERE o.oprnamespace = n.oid AND "
-								"      o.oprleft = t.oid AND "
-								"      t.typnamespace = tn.oid AND "
-								"      o.oprright = 0 AND "
-								"      o.oid >= 16384");
-		ntups = PQntuples(res);
-		i_oproid = PQfnumber(res, "oproid");
-		i_oprnsp = PQfnumber(res, "oprnsp");
-		i_oprname = PQfnumber(res, "oprname");
-		i_typnsp = PQfnumber(res, "typnsp");
-		i_typname = PQfnumber(res, "typname");
-		for (rowno = 0; rowno < ntups; rowno++)
+		if (!db_used)
 		{
-			if (script == NULL &&
-				(script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s",
-						 output_path, strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  (oid=%s) %s.%s (%s.%s, NONE)\n",
-					PQgetvalue(res, rowno, i_oproid),
-					PQgetvalue(res, rowno, i_oprnsp),
-					PQgetvalue(res, rowno, i_oprname),
-					PQgetvalue(res, rowno, i_typnsp),
-					PQgetvalue(res, rowno, i_typname));
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
 		}
-
-		PQclear(res);
-
-		PQfinish(conn);
+		fprintf(script, "  (oid=%s) %s.%s (%s.%s, NONE)\n",
+				PQgetvalue(res, rowno, i_oproid),
+				PQgetvalue(res, rowno, i_oprnsp),
+				PQgetvalue(res, rowno, i_oprname),
+				PQgetvalue(res, rowno, i_typnsp),
+				PQgetvalue(res, rowno, i_typname));
 	}
 
-	if (script)
-	{
-		fclose(script);
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains user-defined postfix operators, which are not\n"
-				 "supported anymore.  Consider dropping the postfix operators and replacing\n"
-				 "them with prefix operators or function calls.\n"
-				 "A list of user-defined postfix operators is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	PQclear(res);
+
+	return ntups == 0;
 }
 
 /*
@@ -1014,19 +1078,16 @@ check_for_user_defined_postfix_ops(ClusterInfo *cluster)
  *	Make sure nothing is using old polymorphic functions with
  *	anyarray/anyelement rather than the new anycompatible variants.
  */
-static void
-check_for_incompatible_polymorphics(ClusterInfo *cluster)
+static bool
+check_for_incompatible_polymorphics(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
 	PGresult   *res;
-	FILE	   *script = NULL;
-	char		output_path[MAXPGPATH];
 	PQExpBufferData old_polymorphics;
 
-	prep_status("Checking for incompatible polymorphic functions");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "incompatible_polymorphics.txt");
+	bool		db_used = false;
+	int			ntups;
+	int			i_objkind,
+				i_objname;
 
 	/* The set of problematic functions varies a bit in different versions */
 	initPQExpBuffer(&old_polymorphics);
@@ -1048,167 +1109,109 @@ check_for_incompatible_polymorphics(ClusterInfo *cluster)
 							 ", 'array_positions(anyarray,anyelement)'"
 							 ", 'width_bucket(anyelement,anyarray)'");
 
-	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		bool		db_used = false;
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		int			ntups;
-		int			i_objkind,
-					i_objname;
-
-		/*
-		 * The query below hardcodes FirstNormalObjectId as 16384 rather than
-		 * interpolating that C #define into the query because, if that
-		 * #define is ever changed, the cutoff we want to use is the value
-		 * used by pre-version 14 servers, not that of some future version.
-		 */
-		res = executeQueryOrDie(conn,
-		/* Aggregate transition functions */
-								"SELECT 'aggregate' AS objkind, p.oid::regprocedure::text AS objname "
-								"FROM pg_proc AS p "
-								"JOIN pg_aggregate AS a ON a.aggfnoid=p.oid "
-								"JOIN pg_proc AS transfn ON transfn.oid=a.aggtransfn "
-								"WHERE p.oid >= 16384 "
-								"AND a.aggtransfn = ANY(ARRAY[%s]::regprocedure[]) "
-								"AND a.aggtranstype = ANY(ARRAY['anyarray', 'anyelement']::regtype[]) "
-
-		/* Aggregate final functions */
-								"UNION ALL "
-								"SELECT 'aggregate' AS objkind, p.oid::regprocedure::text AS objname "
-								"FROM pg_proc AS p "
-								"JOIN pg_aggregate AS a ON a.aggfnoid=p.oid "
-								"JOIN pg_proc AS finalfn ON finalfn.oid=a.aggfinalfn "
-								"WHERE p.oid >= 16384 "
-								"AND a.aggfinalfn = ANY(ARRAY[%s]::regprocedure[]) "
-								"AND a.aggtranstype = ANY(ARRAY['anyarray', 'anyelement']::regtype[]) "
-
-		/* Operators */
-								"UNION ALL "
-								"SELECT 'operator' AS objkind, op.oid::regoperator::text AS objname "
-								"FROM pg_operator AS op "
-								"WHERE op.oid >= 16384 "
-								"AND oprcode = ANY(ARRAY[%s]::regprocedure[]) "
-								"AND oprleft = ANY(ARRAY['anyarray', 'anyelement']::regtype[]);",
-								old_polymorphics.data,
-								old_polymorphics.data,
-								old_polymorphics.data);
-
-		ntups = PQntuples(res);
-
-		i_objkind = PQfnumber(res, "objkind");
-		i_objname = PQfnumber(res, "objname");
-
-		for (int rowno = 0; rowno < ntups; rowno++)
-		{
-			if (script == NULL &&
-				(script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s",
-						 output_path, strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
+	/*
+	 * The query below hardcodes FirstNormalObjectId as 16384 rather than
+	 * interpolating that C #define into the query because, if that
+	 * #define is ever changed, the cutoff we want to use is the value
+	 * used by pre-version 14 servers, not that of some future version.
+	 */
+	res = executeQueryOrDie(conn,
+	/* Aggregate transition functions */
+							"SELECT 'aggregate' AS objkind, p.oid::regprocedure::text AS objname "
+							"FROM pg_proc AS p "
+							"JOIN pg_aggregate AS a ON a.aggfnoid=p.oid "
+							"JOIN pg_proc AS transfn ON transfn.oid=a.aggtransfn "
+							"WHERE p.oid >= 16384 "
+							"AND a.aggtransfn = ANY(ARRAY[%s]::regprocedure[]) "
+							"AND a.aggtranstype = ANY(ARRAY['anyarray', 'anyelement']::regtype[]) "
+
+	/* Aggregate final functions */
+							"UNION ALL "
+							"SELECT 'aggregate' AS objkind, p.oid::regprocedure::text AS objname "
+							"FROM pg_proc AS p "
+							"JOIN pg_aggregate AS a ON a.aggfnoid=p.oid "
+							"JOIN pg_proc AS finalfn ON finalfn.oid=a.aggfinalfn "
+							"WHERE p.oid >= 16384 "
+							"AND a.aggfinalfn = ANY(ARRAY[%s]::regprocedure[]) "
+							"AND a.aggtranstype = ANY(ARRAY['anyarray', 'anyelement']::regtype[]) "
+
+	/* Operators */
+							"UNION ALL "
+							"SELECT 'operator' AS objkind, op.oid::regoperator::text AS objname "
+							"FROM pg_operator AS op "
+							"WHERE op.oid >= 16384 "
+							"AND oprcode = ANY(ARRAY[%s]::regprocedure[]) "
+							"AND oprleft = ANY(ARRAY['anyarray', 'anyelement']::regtype[]);",
+							old_polymorphics.data,
+							old_polymorphics.data,
+							old_polymorphics.data);
 
-			fprintf(script, "  %s: %s\n",
-					PQgetvalue(res, rowno, i_objkind),
-					PQgetvalue(res, rowno, i_objname));
-		}
+	ntups = PQntuples(res);
 
-		PQclear(res);
-		PQfinish(conn);
-	}
+	i_objkind = PQfnumber(res, "objkind");
+	i_objname = PQfnumber(res, "objname");
 
-	if (script)
+	for (int rowno = 0; rowno < ntups; rowno++)
 	{
-		fclose(script);
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains user-defined objects that refer to internal\n"
-				 "polymorphic functions with arguments of type \"anyarray\" or \"anyelement\".\n"
-				 "These user-defined objects must be dropped before upgrading and restored\n"
-				 "afterwards, changing them to refer to the new corresponding functions with\n"
-				 "arguments of type \"anycompatiblearray\" and \"anycompatible\".\n"
-				 "A list of the problematic objects is in the file:\n"
-				 "    %s", output_path);
+		if (!db_used)
+		{
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
+		}
+
+		fprintf(script, "  %s: %s\n",
+				PQgetvalue(res, rowno, i_objkind),
+				PQgetvalue(res, rowno, i_objname));
 	}
-	else
-		check_ok();
 
+	PQclear(res);
 	termPQExpBuffer(&old_polymorphics);
+
+	return ntups == 0;
 }
 
 /*
  * Verify that no tables are declared WITH OIDS.
+ *
+ * Pre-PG 12 allowed tables to be declared WITH OIDS, which is not
+ * supported anymore.
  */
-static void
-check_for_tables_with_oids(ClusterInfo *cluster)
+static bool
+check_for_tables_with_oids(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	int			dbnum;
-	FILE	   *script = NULL;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for tables WITH OIDS");
+	PGresult   *res;
+	bool		db_used = false;
+	int			ntups;
+	int			rowno;
+	int			i_nspname,
+				i_relname;
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_with_oids.txt");
+	res = executeQueryOrDie(conn,
+							"SELECT n.nspname, c.relname "
+							"FROM	pg_catalog.pg_class c, "
+							"		pg_catalog.pg_namespace n "
+							"WHERE	c.relnamespace = n.oid AND "
+							"		c.relhasoids AND"
+							"       n.nspname NOT IN ('pg_catalog')");
 
-	/* Find any tables declared WITH OIDS */
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	ntups = PQntuples(res);
+	i_nspname = PQfnumber(res, "nspname");
+	i_relname = PQfnumber(res, "relname");
+	for (rowno = 0; rowno < ntups; rowno++)
 	{
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname;
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-
-		res = executeQueryOrDie(conn,
-								"SELECT n.nspname, c.relname "
-								"FROM	pg_catalog.pg_class c, "
-								"		pg_catalog.pg_namespace n "
-								"WHERE	c.relnamespace = n.oid AND "
-								"		c.relhasoids AND"
-								"       n.nspname NOT IN ('pg_catalog')");
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		for (rowno = 0; rowno < ntups; rowno++)
+		if (!db_used)
 		{
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s",
-						 output_path, strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname));
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
 		}
-
-		PQclear(res);
-
-		PQfinish(conn);
+		fprintf(script, "  %s.%s\n",
+				PQgetvalue(res, rowno, i_nspname),
+				PQgetvalue(res, rowno, i_relname));
 	}
 
-	if (script)
-	{
-		fclose(script);
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains tables declared WITH OIDS, which is not\n"
-				 "supported anymore.  Consider removing the oid column using\n"
-				 "    ALTER TABLE ... SET WITHOUT OIDS;\n"
-				 "A list of tables with the problem is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	PQclear(res);
+
+	return ntups == 0;
 }
 
 
@@ -1221,20 +1224,13 @@ check_for_tables_with_oids(ClusterInfo *cluster)
  *	no mechanism for forcing them to be the same in the new cluster.
  *	Hence, if any user table uses one, that's problematic for pg_upgrade.
  */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
+static bool
+check_for_composite_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
 	bool		found;
 	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
 	char	   *base_query;
 
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
 	/*
 	 * Look for composite types that were made during initdb *or* belong to
 	 * information_schema; that's important in case information_schema was
@@ -1253,22 +1249,11 @@ check_for_composite_data_type_usage(ClusterInfo *cluster)
 						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
 						  firstUserOid);
 
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	found = check_for_data_types_usage(cluster, base_query, active_db, conn, script);
 
 	free(base_query);
 
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return !found;
 }
 
 /*
@@ -1282,17 +1267,10 @@ check_for_composite_data_type_usage(ClusterInfo *cluster)
  *	not preserved, and hence these data types cannot be used in user
  *	tables upgraded by pg_upgrade.
  */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
+static bool
+check_for_reg_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
 	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
 
 	/*
 	 * Note: older servers will not have all of these reg* types, so we have
@@ -1316,48 +1294,22 @@ check_for_reg_data_type_usage(ClusterInfo *cluster)
 	/* pg_authid.oid is preserved, so 'regrole' is OK */
 	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
 									   "         )",
-									   output_path);
+									   active_db, conn, script);
 
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return !found;
 }
 
 /*
  * check_for_aclitem_data_type_usage
  *
- *	aclitem changed its storage format in 16, so check for it.
+ * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+ * format for existing data.
  */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
+static bool
+check_for_aclitem_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	char		output_path[MAXPGPATH];
-
 	prep_status("Checking for incompatible aclitem data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return check_for_data_type_usage(cluster, "pg_catalog.aclitem", active_db, conn, script);
 }
 
 /*
@@ -1365,29 +1317,13 @@ check_for_aclitem_data_type_usage(ClusterInfo *cluster)
  *
  *	JSONB changed its storage format during 9.4 beta, so check for it.
  */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
+static bool
+check_for_jsonb_9_4_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
+	if (old_cluster.controldata.cat_ver >= JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return check_for_data_type_usage(cluster, "pg_catalog.jsonb", active_db, conn, script);
 }
 
 /*
@@ -1450,84 +1386,55 @@ check_for_pg_role_prefix(ClusterInfo *cluster)
 
 /*
  * Verify that no user-defined encoding conversions exist.
+ *
+ * PG 14 changed the function signature of encoding conversion functions.
+ * Conversions from older versions cannot be upgraded automatically
+ * because the user-defined functions used by the encoding conversions
+ * need to be changed to match the new signature.
  */
-static void
-check_for_user_defined_encoding_conversions(ClusterInfo *cluster)
+static bool
+check_for_user_defined_encoding_conversions(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	int			dbnum;
-	FILE	   *script = NULL;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for user-defined encoding conversions");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "encoding_conversions.txt");
+	PGresult   *res;
+	bool		db_used = false;
+	int			ntups;
+	int			rowno;
+	int			i_conoid,
+				i_conname,
+				i_nspname;
 
-	/* Find any user defined encoding conversions */
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	/*
+	 * The query below hardcodes FirstNormalObjectId as 16384 rather than
+	 * interpolating that C #define into the query because, if that
+	 * #define is ever changed, the cutoff we want to use is the value
+	 * used by pre-version 14 servers, not that of some future version.
+	 */
+	res = executeQueryOrDie(conn,
+							"SELECT c.oid as conoid, c.conname, n.nspname "
+							"FROM pg_catalog.pg_conversion c, "
+							"     pg_catalog.pg_namespace n "
+							"WHERE c.connamespace = n.oid AND "
+							"      c.oid >= 16384");
+	ntups = PQntuples(res);
+	i_conoid = PQfnumber(res, "conoid");
+	i_conname = PQfnumber(res, "conname");
+	i_nspname = PQfnumber(res, "nspname");
+	for (rowno = 0; rowno < ntups; rowno++)
 	{
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_conoid,
-					i_conname,
-					i_nspname;
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-
-		/*
-		 * The query below hardcodes FirstNormalObjectId as 16384 rather than
-		 * interpolating that C #define into the query because, if that
-		 * #define is ever changed, the cutoff we want to use is the value
-		 * used by pre-version 14 servers, not that of some future version.
-		 */
-		res = executeQueryOrDie(conn,
-								"SELECT c.oid as conoid, c.conname, n.nspname "
-								"FROM pg_catalog.pg_conversion c, "
-								"     pg_catalog.pg_namespace n "
-								"WHERE c.connamespace = n.oid AND "
-								"      c.oid >= 16384");
-		ntups = PQntuples(res);
-		i_conoid = PQfnumber(res, "conoid");
-		i_conname = PQfnumber(res, "conname");
-		i_nspname = PQfnumber(res, "nspname");
-		for (rowno = 0; rowno < ntups; rowno++)
+		if (!db_used)
 		{
-			if (script == NULL &&
-				(script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s",
-						 output_path, strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  (oid=%s) %s.%s\n",
-					PQgetvalue(res, rowno, i_conoid),
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_conname));
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
 		}
-
-		PQclear(res);
-
-		PQfinish(conn);
+		fprintf(script, "  (oid=%s) %s.%s\n",
+				PQgetvalue(res, rowno, i_conoid),
+				PQgetvalue(res, rowno, i_nspname),
+				PQgetvalue(res, rowno, i_conname));
 	}
 
-	if (script)
-	{
-		fclose(script);
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains user-defined encoding conversions.\n"
-				 "The conversion function parameters changed in PostgreSQL version 14\n"
-				 "so this cluster cannot currently be upgraded.  You can remove the\n"
-				 "encoding conversions in the old cluster and restart the upgrade.\n"
-				 "A list of user-defined encoding conversions is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	PQclear(res);
+
+	return ntups == 0;
 }
 
 
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 5f2a116f23e..39e8fd2c8d5 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -444,16 +444,16 @@ unsigned int str2uint(const char *str);
 
 bool		check_for_data_types_usage(ClusterInfo *cluster,
 									   const char *base_query,
-									   const char *output_path);
+									   DbInfo *active_db, PGconn *conn, FILE *script);
 bool		check_for_data_type_usage(ClusterInfo *cluster,
 									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+									  DbInfo *active_db, PGconn *conn, FILE *script);
+bool		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
+bool		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
+bool		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfaa..f2b885347a8 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -30,111 +30,96 @@
 bool
 check_for_data_types_usage(ClusterInfo *cluster,
 						   const char *base_query,
-						   const char *output_path)
+						   DbInfo *active_db, PGconn *conn, FILE *script)
 {
 	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	PQExpBufferData querybuf;
+	PGresult   *res;
+	bool		db_used = false;
+	int			ntups;
+	int			rowno;
+	int			i_nspname,
+				i_relname,
+				i_attname;
+
+	/*
+	 * The type(s) of interest might be wrapped in a domain, array,
+	 * composite, or range, and these container types can be nested (to
+	 * varying extents depending on server version, but that's not of
+	 * concern here).  To handle all these cases we need a recursive CTE.
+	 */
+	initPQExpBuffer(&querybuf);
+	appendPQExpBuffer(&querybuf,
+					  "WITH RECURSIVE oids AS ( "
+	/* start with the type(s) returned by base_query */
+					  "	%s "
+					  "	UNION ALL "
+					  "	SELECT * FROM ( "
+	/* inner WITH because we can only reference the CTE once */
+					  "		WITH x AS (SELECT oid FROM oids) "
+	/* domains on any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+					  "			UNION ALL "
+	/* arrays over any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+					  "			UNION ALL "
+	/* composite types containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+					  "			WHERE t.typtype = 'c' AND "
+					  "				  t.oid = c.reltype AND "
+					  "				  c.oid = a.attrelid AND "
+					  "				  NOT a.attisdropped AND "
+					  "				  a.atttypid = x.oid "
+					  "			UNION ALL "
+	/* ranges containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+					  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+					  "	) foo "
+					  ") "
+	/* now look for stored columns of any such type */
+					  "SELECT n.nspname, c.relname, a.attname "
+					  "FROM	pg_catalog.pg_class c, "
+					  "		pg_catalog.pg_namespace n, "
+					  "		pg_catalog.pg_attribute a "
+					  "WHERE	c.oid = a.attrelid AND "
+					  "		NOT a.attisdropped AND "
+					  "		a.atttypid IN (SELECT oid FROM oids) AND "
+					  "		c.relkind IN ("
+					  CppAsString2(RELKIND_RELATION) ", "
+					  CppAsString2(RELKIND_MATVIEW) ", "
+					  CppAsString2(RELKIND_INDEX) ") AND "
+					  "		c.relnamespace = n.oid AND "
+	/* exclude possible orphaned temp tables */
+					  "		n.nspname !~ '^pg_temp_' AND "
+					  "		n.nspname !~ '^pg_toast_temp_' AND "
+	/* exclude system catalogs, too */
+					  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+					  base_query);
+
+	res = executeQueryOrDie(conn, "%s", querybuf.data);
+
+	ntups = PQntuples(res);
+	i_nspname = PQfnumber(res, "nspname");
+	i_relname = PQfnumber(res, "relname");
+	i_attname = PQfnumber(res, "attname");
+	for (rowno = 0; rowno < ntups; rowno++)
 	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
+		found = true;
+		if (!db_used)
 		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
+			fprintf(script, "In database: %s\n", active_db->db_name);
+			db_used = true;
 		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
+		fprintf(script, "  %s.%s.%s\n",
+				PQgetvalue(res, rowno, i_nspname),
+				PQgetvalue(res, rowno, i_relname),
+				PQgetvalue(res, rowno, i_attname));
 	}
 
-	if (script)
-		fclose(script);
+	PQclear(res);
+
+	termPQExpBuffer(&querybuf);
 
 	return found;
 }
@@ -152,7 +137,7 @@ check_for_data_types_usage(ClusterInfo *cluster,
 bool
 check_for_data_type_usage(ClusterInfo *cluster,
 						  const char *type_name,
-						  const char *output_path)
+						  DbInfo *active_db, PGconn *conn, FILE *script)
 {
 	bool		found;
 	char	   *base_query;
@@ -160,7 +145,7 @@ check_for_data_type_usage(ClusterInfo *cluster,
 	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
 						  type_name);
 
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	found = check_for_data_types_usage(cluster, base_query, active_db, conn, script);
 
 	free(base_query);
 
@@ -176,30 +161,12 @@ check_for_data_type_usage(ClusterInfo *cluster,
  *	compile-time switch; as of 9.4 "line" has a different on-disk
  *	representation format.
  */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	char		output_path[MAXPGPATH];
-
 	prep_status("Checking for incompatible \"line\" data type");
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return check_for_data_type_usage(cluster, "pg_catalog.line", active_db, conn, script);
 }
 
 
@@ -216,29 +183,12 @@ old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
  *	DDL reload will silently change it to "text" which won't match the
  *	on-disk storage (which is like "cstring").  So we *must* reject that.
  */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	char		output_path[MAXPGPATH];
-
 	prep_status("Checking for invalid \"unknown\" user columns");
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return check_for_data_type_usage(cluster, "pg_catalog.unknown", active_db, conn, script);
 }
 
 /*
@@ -358,33 +308,15 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
  *	11 -> 12
  *	In 12, the sql_identifier data type was switched from name to varchar,
  *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
+ *	means user objects using sql_identifier for columns are broken because
  *	the on-disk format is different.
  */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
+bool
+old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster, DbInfo *active_db, PGconn *conn, FILE *script)
 {
-	char		output_path[MAXPGPATH];
-
 	prep_status("Checking for invalid \"sql_identifier\" user columns");
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return check_for_data_type_usage(cluster, "information_schema.sql_identifier", active_db, conn, script);
 }
 
 
-- 
2.34.1

diff --git a/src/bin/pg_upgrade/info.c b/src/bin/pg_upgrade/info.c
index c1399c09b9..5c47e4463c 100644
--- a/src/bin/pg_upgrade/info.c
+++ b/src/bin/pg_upgrade/info.c
@@ -11,6 +11,8 @@
 
 #include "access/transam.h"
 #include "catalog/pg_class_d.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
 #include "pg_upgrade.h"
 
 static void create_rel_filename_map(const char *old_data, const char *new_data,
@@ -26,6 +28,28 @@ static void free_rel_infos(RelInfoArr *rel_arr);
 static void print_db_infos(DbInfoArr *db_arr);
 static void print_rel_infos(RelInfoArr *rel_arr);
 
+static uint32 hash_string_pointer(const char *s);
+#define SH_PREFIX		spacehash
+#define SH_ELEMENT_TYPE	space_entry_t
+#define SH_KEY_TYPE		const char *
+#define SH_KEY			name
+#define SH_HASH_KEY(tb, key)	hash_string_pointer(key)
+#define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
+#define SH_SCOPE		extern
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+/*
+ * Helper function for spacehash hash table.
+ */
+static uint32
+hash_string_pointer(const char *s)
+{
+	unsigned char *ss = (unsigned char *) s;
+
+	return hash_bytes(ss, strlen(s));
+}
 
 /*
  * gen_db_file_maps()
@@ -402,11 +426,13 @@ get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo)
 				i_relfilenumber,
 				i_reltablespace;
 	char		query[QUERY_ALLOC];
-	char	   *last_namespace = NULL,
-			   *last_tablespace = NULL;
 
 	query[0] = '\0';			/* initialize query string to empty */
 
+	/* TODO: What is a good initial size? */
+	dbinfo->db_namespaces = spacehash_create(16, NULL);
+	dbinfo->db_tablespaces = spacehash_create(16, NULL);
+
 	/*
 	 * Create a CTE that collects OIDs of regular user tables and matviews,
 	 * but excluding toast tables and indexes.  We assume that relations with
@@ -501,33 +527,29 @@ get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo)
 	for (relnum = 0; relnum < ntups; relnum++)
 	{
 		RelInfo    *curr = &relinfos[num_rels++];
+		bool 		found;
+		space_entry_t *sp;
 
 		curr->reloid = atooid(PQgetvalue(res, relnum, i_reloid));
 		curr->indtable = atooid(PQgetvalue(res, relnum, i_indtable));
 		curr->toastheap = atooid(PQgetvalue(res, relnum, i_toastheap));
 
 		nspname = PQgetvalue(res, relnum, i_nspname);
-		curr->nsp_alloc = false;
 
 		/*
 		 * Many of the namespace and tablespace strings are identical, so we
-		 * try to reuse the allocated string pointers where possible to reduce
-		 * memory consumption.
+		 * try to minimize allocated space by storing the names in a hash-
+		 * table from which they can be referenced.
 		 */
-		/* Can we reuse the previous string allocation? */
-		if (last_namespace && strcmp(nspname, last_namespace) == 0)
-			curr->nspname = last_namespace;
-		else
-		{
-			last_namespace = curr->nspname = pg_strdup(nspname);
-			curr->nsp_alloc = true;
-		}
+		sp = spacehash_insert(dbinfo->db_namespaces, nspname, &found);
+		if (!found)
+			sp->name = pstrdup(nspname);
+		curr->nspname = sp->name;
 
 		relname = PQgetvalue(res, relnum, i_relname);
 		curr->relname = pg_strdup(relname);
 
 		curr->relfilenumber = atooid(PQgetvalue(res, relnum, i_relfilenumber));
-		curr->tblsp_alloc = false;
 
 		/* Is the tablespace oid non-default? */
 		if (atooid(PQgetvalue(res, relnum, i_reltablespace)) != 0)
@@ -538,14 +560,10 @@ get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo)
 			 */
 			tablespace = PQgetvalue(res, relnum, i_spclocation);
 
-			/* Can we reuse the previous string allocation? */
-			if (last_tablespace && strcmp(tablespace, last_tablespace) == 0)
-				curr->tablespace = last_tablespace;
-			else
-			{
-				last_tablespace = curr->tablespace = pg_strdup(tablespace);
-				curr->tblsp_alloc = true;
-			}
+			sp = spacehash_insert(dbinfo->db_tablespaces, tablespace, &found);
+			if (!found)
+				sp->name = pstrdup(tablespace);
+			curr->tablespace = sp->name;
 		}
 		else
 			/* A zero reltablespace oid indicates the database tablespace. */
@@ -569,6 +587,9 @@ free_db_and_rel_infos(DbInfoArr *db_arr)
 	{
 		free_rel_infos(&db_arr->dbs[dbnum].rel_arr);
 		pg_free(db_arr->dbs[dbnum].db_name);
+
+		spacehash_destroy(db_arr->dbs[dbnum].db_namespaces);
+		spacehash_destroy(db_arr->dbs[dbnum].db_tablespaces);
 	}
 	pg_free(db_arr->dbs);
 	db_arr->dbs = NULL;
@@ -582,13 +603,7 @@ free_rel_infos(RelInfoArr *rel_arr)
 	int			relnum;
 
 	for (relnum = 0; relnum < rel_arr->nrels; relnum++)
-	{
-		if (rel_arr->rels[relnum].nsp_alloc)
-			pg_free(rel_arr->rels[relnum].nspname);
 		pg_free(rel_arr->rels[relnum].relname);
-		if (rel_arr->rels[relnum].tblsp_alloc)
-			pg_free(rel_arr->rels[relnum].tablespace);
-	}
 	pg_free(rel_arr->rels);
 	rel_arr->nrels = 0;
 }
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 5f2a116f23..239c5c468a 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -133,15 +133,13 @@ extern char *output_files[];
 typedef struct
 {
 	/* Can't use NAMEDATALEN; not guaranteed to be same on client */
-	char	   *nspname;		/* namespace name */
+	const char *nspname;		/* namespace name */
 	char	   *relname;		/* relation name */
 	Oid			reloid;			/* relation OID */
 	RelFileNumber relfilenumber;	/* relation file number */
 	Oid			indtable;		/* if index, OID of its table, else 0 */
 	Oid			toastheap;		/* if toast table, OID of base table, else 0 */
-	char	   *tablespace;		/* tablespace path; "" for cluster default */
-	bool		nsp_alloc;		/* should nspname be freed? */
-	bool		tblsp_alloc;	/* should tablespace be freed? */
+	const char *tablespace;		/* tablespace path; "" for cluster default */
 } RelInfo;
 
 typedef struct
@@ -162,10 +160,29 @@ typedef struct
 	Oid			db_oid;
 	RelFileNumber relfilenumber;
 	/* the rest are used only for logging and error reporting */
-	char	   *nspname;		/* namespaces */
+	const char *nspname;		/* namespaces */
 	char	   *relname;
 } FileNameMap;
 
+/*
+ * space_entry_t
+ *
+ * Hash table entries for recording namespace and tablespace names.
+ */
+typedef struct space_entry_t
+{
+	uint32		status;			/* hash status */
+	const char *name;
+} space_entry_t;
+
+#define SH_PREFIX		spacehash
+#define SH_ELEMENT_TYPE	space_entry_t
+#define SH_KEY_TYPE		const char *
+#define SH_SCOPE		extern
+#define SH_RAW_ALLOCATOR	pg_malloc0
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 /*
  * Structure to store database information
  */
@@ -181,6 +198,8 @@ typedef struct
 	char	   *db_iculocale;
 	int			db_encoding;
 	RelInfoArr	rel_arr;		/* array of all user relinfos */
+	spacehash_hash  *db_namespaces;		/* hash of namespaces */
+	spacehash_hash  *db_tablespaces;	/* hash of tablespaces */
 } DbInfo;
 
 typedef struct

From fe151dd41642ca866a68e51a8c9de4da4e0cce9a Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Wed, 22 Feb 2023 10:32:31 +0100
Subject: [PATCH v2] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 573 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  27 +-
 src/bin/pg_upgrade/version.c    | 269 ++-------------
 3 files changed, 421 insertions(+), 448 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 7cf68dc9af..ca304a0101 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -26,15 +27,378 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
+static bool check_for_aclitem_data_type_usage(ClusterInfo *cluster);
+static bool check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 static char *get_canonical_locale_name(int category, const char *locale);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static int n_data_types_usage_checks = 7;
+static DataTypesUsageChecks data_types_usage_checks[] = {
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{.status = "Checking for system-defined composite types in user tables",
+	 .report_filename = "tables_using_composite.txt",
+	 .base_query =
+	 "SELECT t.oid FROM pg_catalog.pg_type t "
+	 "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+	 " WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+	 .report_text =
+	 "Your installation contains system-defined composite type(s) in user tables.\n"
+	 "These type OIDs are not stable across PostgreSQL versions,\n"
+	 "so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * 9.3 -> 9.4
+	 *	Fully implement the 'line' data type in 9.4, which previously returned
+	 *	"not enabled" by default and was only functionally enabled with a
+	 *	compile-time switch; as of 9.4 "line" has a different on-disk
+	 *	representation format.
+	 */
+	{.status = "Checking for incompatible \"line\" data type",
+	 .report_filename = "tables_using_line.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "your installation contains the \"line\" data type in user tables.\n"
+	 "this data type changed its internal and input/output format\n"
+	 "between your old and new versions so this\n"
+	 "cluster cannot currently be upgraded.  you can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "a list of the problem columns is in the file:",
+	 .version_hook = old_9_3_check_for_line_data_type_usage},
+
+	/*
+	 *	pg_upgrade only preserves these system values:
+	 *		pg_class.oid
+	 *		pg_type.oid
+	 *		pg_enum.oid
+	 *
+	 *	Many of the reg* data types reference system catalog info that is
+	 *	not preserved, and hence these data types cannot be used in user
+	 *	tables upgraded by pg_upgrade.
+	 */
+	{.status = "Checking for reg* data types in user tables",
+	 .report_filename = "tables_using_reg.txt",
+	 /*
+	  * Note: older servers will not have all of these reg* types, so we have
+	  * to write the query like this rather than depending on casts to regtype.
+	  */
+	 .base_query =
+	 "SELECT oid FROM pg_catalog.pg_type t "
+	 "WHERE t.typnamespace = "
+	 "        (SELECT oid FROM pg_catalog.pg_namespace "
+	 "         WHERE nspname = 'pg_catalog') "
+	 "  AND t.typname IN ( "
+	 /* pg_class.oid is preserved, so 'regclass' is OK */
+	 "           'regcollation', "
+	 "           'regconfig', "
+	 "           'regdictionary', "
+	 "           'regnamespace', "
+	 "           'regoper', "
+	 "           'regoperator', "
+	 "           'regproc', "
+	 "           'regprocedure' "
+	 /* pg_authid.oid is preserved, so 'regrole' is OK */
+	 /* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+	 "         )",
+	 .report_text =
+	 "Your installation contains one of the reg* data types in user tables.\n"
+	 "These data types reference system OIDs that are not preserved by\n"
+	 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	{.status = "Checking for incompatible aclitem data type in user tables",
+	 .report_filename = "tables_using_aclitem.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"aclitem\" data type in user tables.\n"
+	 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+	 "so this cluster cannot currently be upgraded.  You can drop the\n"
+	 "problem columns and restart the upgrade.  A list of the problem\n"
+	 "columns is in the file:",
+	 .version_hook = check_for_aclitem_data_type_usage},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that
+	 * by hand.  However, if there's a table with such a column, the DDL
+	 * reload will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the
+	 * DDL reload will silently change it to "text" which won't match the
+	 * on-disk storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{.status = "Checking for invalid \"unknown\" user columns",
+	 .report_filename = "tables_using_unknown.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"unknown\" data type in user tables.\n"
+	 "This data type is no longer allowed in tables, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_9_6_check_for_unknown_data_type_usage},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 * In 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{.status = "Checking for invalid \"sql_identifier\" user columns",
+	 .report_filename = "tables_using_sql_identifier.txt",
+	 .base_query =
+	 "SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"sql_identifier\" data type in user tables.\n"
+	 "The on-disk format for this data type has changed, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_11_check_for_sql_identifier_data_type_usage},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{.status = "Checking for incompatible \"jsonb\" data type",
+	 .report_filename = "tables_using_jsonb.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"jsonb\" data type in user tables.\n"
+	 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = check_for_jsonb_9_4_usage},
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool	found = false;
+	bool   *results;
+	PQExpBufferData report;
+
+	prep_status("Checking for data type usage");
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult *res;
+			int 	ntups;
+			int 	i_nspname;
+			int 	i_relname;
+			int 	i_attname;
+			FILE   *script = NULL;
+			bool 	db_used = false;
+			char	output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+			{
+				cur_check++;
+				continue;
+			}
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested (to
+			 * varying extents depending on server version, but that's not of
+			 * concern here).  To handle all these cases we need a recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+							  "WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+							  "	%s "
+					  "	UNION ALL "
+					  "	SELECT * FROM ( "
+	/* inner WITH because we can only reference the CTE once */
+					  "		WITH x AS (SELECT oid FROM oids) "
+	/* domains on any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+					  "			UNION ALL "
+	/* arrays over any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+					  "			UNION ALL "
+	/* composite types containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+					  "			WHERE t.typtype = 'c' AND "
+					  "				  t.oid = c.reltype AND "
+					  "				  c.oid = a.attrelid AND "
+					  "				  NOT a.attisdropped AND "
+					  "				  a.atttypid = x.oid "
+					  "			UNION ALL "
+	/* ranges containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+					  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+					  "	) foo "
+					  ") "
+	/* now look for stored columns of any such type */
+					  "SELECT n.nspname, c.relname, a.attname "
+					  "FROM	pg_catalog.pg_class c, "
+					  "		pg_catalog.pg_namespace n, "
+					  "		pg_catalog.pg_attribute a "
+					  "WHERE	c.oid = a.attrelid AND "
+					  "		NOT a.attisdropped AND "
+					  "		a.atttypid IN (SELECT oid FROM oids) AND "
+					  "		c.relkind IN ("
+					  CppAsString2(RELKIND_RELATION) ", "
+					  CppAsString2(RELKIND_MATVIEW) ", "
+					  CppAsString2(RELKIND_INDEX) ") AND "
+					  "		c.relnamespace = n.oid AND "
+	/* exclude possible orphaned temp tables */
+					  "		n.nspname !~ '^pg_temp_' AND "
+					  "		n.nspname !~ '^pg_toast_temp_' AND "
+	/* exclude system catalogs, too */
+					  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+					  cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_STATUS, "failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					found = true;
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, " %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+			cur_check++;
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -104,16 +468,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
-	 * format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -145,21 +502,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -168,14 +516,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1207,182 +1547,37 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_aclitem_data_type_usage
  *
- *	aclitem changed its storage format in 16, so check for it.
+ *     aclitem changed its storage format in 16, so check for it.
  */
-static void
+static bool
 check_for_aclitem_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible aclitem data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
  * check_for_jsonb_9_4_usage()
  *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
+ *     JSONB changed its storage format during 9.4 beta, so check for it.
  */
-static void
+static bool
 check_for_jsonb_9_4_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 5f2a116f23..fcee6cee1f 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -320,6 +320,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck)(ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+} DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -442,18 +457,12 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
+bool		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..ccf078f13d 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,26 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
-bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
-{
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
-}
-
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
-{
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
 old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
+bool
 old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
 /*
@@ -353,41 +143,20 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
+bool
 old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
 }
 
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From ec6d973c9570fac4bdc3ba58ba4d62914dd7e17f Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <daniel@yesql.se>
Date: Mon, 13 Mar 2023 14:46:24 +0100
Subject: [PATCH v3] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 575 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 289 +++-------------
 3 files changed, 433 insertions(+), 460 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index b71b00be37..77818f287f 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,375 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static int n_data_types_usage_checks = 7;
+static DataTypesUsageChecks data_types_usage_checks[] = {
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{.status = "Checking for system-defined composite types in user tables",
+	 .report_filename = "tables_using_composite.txt",
+	 .base_query =
+	 "SELECT t.oid FROM pg_catalog.pg_type t "
+	 "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+	 " WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+	 .report_text =
+	 "Your installation contains system-defined composite type(s) in user tables.\n"
+	 "These type OIDs are not stable across PostgreSQL versions,\n"
+	 "so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * 9.3 -> 9.4
+	 *	Fully implement the 'line' data type in 9.4, which previously returned
+	 *	"not enabled" by default and was only functionally enabled with a
+	 *	compile-time switch; as of 9.4 "line" has a different on-disk
+	 *	representation format.
+	 */
+	{.status = "Checking for incompatible \"line\" data type",
+	 .report_filename = "tables_using_line.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "your installation contains the \"line\" data type in user tables.\n"
+	 "this data type changed its internal and input/output format\n"
+	 "between your old and new versions so this\n"
+	 "cluster cannot currently be upgraded.  you can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "a list of the problem columns is in the file:",
+	 .version_hook = old_9_3_check_for_line_data_type_usage},
+
+	/*
+	 *	pg_upgrade only preserves these system values:
+	 *		pg_class.oid
+	 *		pg_type.oid
+	 *		pg_enum.oid
+	 *
+	 *	Many of the reg* data types reference system catalog info that is
+	 *	not preserved, and hence these data types cannot be used in user
+	 *	tables upgraded by pg_upgrade.
+	 */
+	{.status = "Checking for reg* data types in user tables",
+	 .report_filename = "tables_using_reg.txt",
+	 /*
+	  * Note: older servers will not have all of these reg* types, so we have
+	  * to write the query like this rather than depending on casts to regtype.
+	  */
+	 .base_query =
+	 "SELECT oid FROM pg_catalog.pg_type t "
+	 "WHERE t.typnamespace = "
+	 "        (SELECT oid FROM pg_catalog.pg_namespace "
+	 "         WHERE nspname = 'pg_catalog') "
+	 "  AND t.typname IN ( "
+	 /* pg_class.oid is preserved, so 'regclass' is OK */
+	 "           'regcollation', "
+	 "           'regconfig', "
+	 "           'regdictionary', "
+	 "           'regnamespace', "
+	 "           'regoper', "
+	 "           'regoperator', "
+	 "           'regproc', "
+	 "           'regprocedure' "
+	 /* pg_authid.oid is preserved, so 'regrole' is OK */
+	 /* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+	 "         )",
+	 .report_text =
+	 "Your installation contains one of the reg* data types in user tables.\n"
+	 "These data types reference system OIDs that are not preserved by\n"
+	 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	{.status = "Checking for incompatible aclitem data type in user tables",
+	 .report_filename = "tables_using_aclitem.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"aclitem\" data type in user tables.\n"
+	 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+	 "so this cluster cannot currently be upgraded.  You can drop the\n"
+	 "problem columns and restart the upgrade.  A list of the problem\n"
+	 "columns is in the file:",
+	 .version_hook = check_for_aclitem_data_type_usage},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that
+	 * by hand.  However, if there's a table with such a column, the DDL
+	 * reload will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the
+	 * DDL reload will silently change it to "text" which won't match the
+	 * on-disk storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{.status = "Checking for invalid \"unknown\" user columns",
+	 .report_filename = "tables_using_unknown.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"unknown\" data type in user tables.\n"
+	 "This data type is no longer allowed in tables, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_9_6_check_for_unknown_data_type_usage},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 * In 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{.status = "Checking for invalid \"sql_identifier\" user columns",
+	 .report_filename = "tables_using_sql_identifier.txt",
+	 .base_query =
+	 "SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"sql_identifier\" data type in user tables.\n"
+	 "The on-disk format for this data type has changed, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_11_check_for_sql_identifier_data_type_usage},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{.status = "Checking for incompatible \"jsonb\" data type",
+	 .report_filename = "tables_using_jsonb.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"jsonb\" data type in user tables.\n"
+	 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = check_for_jsonb_9_4_usage},
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool	found = false;
+	bool   *results;
+	PQExpBufferData report;
+
+	prep_status("Checking for data type usage");
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult *res;
+			int 	ntups;
+			int 	i_nspname;
+			int 	i_relname;
+			int 	i_attname;
+			FILE   *script = NULL;
+			bool 	db_used = false;
+			char	output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+			{
+				cur_check++;
+				continue;
+			}
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested (to
+			 * varying extents depending on server version, but that's not of
+			 * concern here).  To handle all these cases we need a recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+							  "WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+							  "	%s "
+					  "	UNION ALL "
+					  "	SELECT * FROM ( "
+	/* inner WITH because we can only reference the CTE once */
+					  "		WITH x AS (SELECT oid FROM oids) "
+	/* domains on any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+					  "			UNION ALL "
+	/* arrays over any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+					  "			UNION ALL "
+	/* composite types containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+					  "			WHERE t.typtype = 'c' AND "
+					  "				  t.oid = c.reltype AND "
+					  "				  c.oid = a.attrelid AND "
+					  "				  NOT a.attisdropped AND "
+					  "				  a.atttypid = x.oid "
+					  "			UNION ALL "
+	/* ranges containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+					  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+					  "	) foo "
+					  ") "
+	/* now look for stored columns of any such type */
+					  "SELECT n.nspname, c.relname, a.attname "
+					  "FROM	pg_catalog.pg_class c, "
+					  "		pg_catalog.pg_namespace n, "
+					  "		pg_catalog.pg_attribute a "
+					  "WHERE	c.oid = a.attrelid AND "
+					  "		NOT a.attisdropped AND "
+					  "		a.atttypid IN (SELECT oid FROM oids) AND "
+					  "		c.relkind IN ("
+					  CppAsString2(RELKIND_RELATION) ", "
+					  CppAsString2(RELKIND_MATVIEW) ", "
+					  CppAsString2(RELKIND_INDEX) ") AND "
+					  "		c.relnamespace = n.oid AND "
+	/* exclude possible orphaned temp tables */
+					  "		n.nspname !~ '^pg_temp_' AND "
+					  "		n.nspname !~ '^pg_toast_temp_' AND "
+	/* exclude system catalogs, too */
+					  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+					  cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					found = true;
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, " %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+			cur_check++;
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +462,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
-	 * format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +496,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +510,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1422,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible aclitem data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 3eea0139c7..208bfbb68e 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck)(ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+} DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,19 +465,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
+bool		check_for_jsonb_9_4_usage(ClusterInfo *cluster);
+bool		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
+bool		check_for_aclitem_data_type_usage(ClusterInfo *cluster);
 
 /* parallel.c */
 void		parallel_exec_prog(const char *log_file, const char *opt_log_file,
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..828a975ac0 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,41 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	return found;
+	return false;
 }
 
 /*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
+ * check_for_jsonb_9_4_usage()
  *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
+ *     JSONB changed its storage format during 9.4 beta, so check for it.
  */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
-{
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+check_for_jsonb_9_4_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
+bool
 old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
 /*
@@ -353,41 +158,20 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
+bool
 old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
 }
 
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
@@ -459,3 +243,22 @@ report_extension_updates(ClusterInfo *cluster)
 	else
 		check_ok();
 }
+
+/*
+ * check_for_aclitem_data_type_usage
+ *
+ *     aclitem changed its storage format in 16, so check for it.
+ */
+bool
+check_for_aclitem_data_type_usage(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
+
-- 
2.32.1 (Apple Git-133)

From ee5805dc450f081b77ae3a7df315ceafb6ccc5e1 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <daniel@yesql.se>
Date: Mon, 13 Mar 2023 14:46:24 +0100
Subject: [PATCH v4 1/1] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 575 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 289 +++-------------
 3 files changed, 433 insertions(+), 460 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 64024e3b9e..c829aed26e 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,375 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static int n_data_types_usage_checks = 7;
+static DataTypesUsageChecks data_types_usage_checks[] = {
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{.status = "Checking for system-defined composite types in user tables",
+	 .report_filename = "tables_using_composite.txt",
+	 .base_query =
+	 "SELECT t.oid FROM pg_catalog.pg_type t "
+	 "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+	 " WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+	 .report_text =
+	 "Your installation contains system-defined composite type(s) in user tables.\n"
+	 "These type OIDs are not stable across PostgreSQL versions,\n"
+	 "so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * 9.3 -> 9.4
+	 *	Fully implement the 'line' data type in 9.4, which previously returned
+	 *	"not enabled" by default and was only functionally enabled with a
+	 *	compile-time switch; as of 9.4 "line" has a different on-disk
+	 *	representation format.
+	 */
+	{.status = "Checking for incompatible \"line\" data type",
+	 .report_filename = "tables_using_line.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "your installation contains the \"line\" data type in user tables.\n"
+	 "this data type changed its internal and input/output format\n"
+	 "between your old and new versions so this\n"
+	 "cluster cannot currently be upgraded.  you can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "a list of the problem columns is in the file:",
+	 .version_hook = old_9_3_check_for_line_data_type_usage},
+
+	/*
+	 *	pg_upgrade only preserves these system values:
+	 *		pg_class.oid
+	 *		pg_type.oid
+	 *		pg_enum.oid
+	 *
+	 *	Many of the reg* data types reference system catalog info that is
+	 *	not preserved, and hence these data types cannot be used in user
+	 *	tables upgraded by pg_upgrade.
+	 */
+	{.status = "Checking for reg* data types in user tables",
+	 .report_filename = "tables_using_reg.txt",
+	 /*
+	  * Note: older servers will not have all of these reg* types, so we have
+	  * to write the query like this rather than depending on casts to regtype.
+	  */
+	 .base_query =
+	 "SELECT oid FROM pg_catalog.pg_type t "
+	 "WHERE t.typnamespace = "
+	 "        (SELECT oid FROM pg_catalog.pg_namespace "
+	 "         WHERE nspname = 'pg_catalog') "
+	 "  AND t.typname IN ( "
+	 /* pg_class.oid is preserved, so 'regclass' is OK */
+	 "           'regcollation', "
+	 "           'regconfig', "
+	 "           'regdictionary', "
+	 "           'regnamespace', "
+	 "           'regoper', "
+	 "           'regoperator', "
+	 "           'regproc', "
+	 "           'regprocedure' "
+	 /* pg_authid.oid is preserved, so 'regrole' is OK */
+	 /* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+	 "         )",
+	 .report_text =
+	 "Your installation contains one of the reg* data types in user tables.\n"
+	 "These data types reference system OIDs that are not preserved by\n"
+	 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = NULL},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	{.status = "Checking for incompatible aclitem data type in user tables",
+	 .report_filename = "tables_using_aclitem.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"aclitem\" data type in user tables.\n"
+	 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+	 "so this cluster cannot currently be upgraded.  You can drop the\n"
+	 "problem columns and restart the upgrade.  A list of the problem\n"
+	 "columns is in the file:",
+	 .version_hook = check_for_aclitem_data_type_usage},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that
+	 * by hand.  However, if there's a table with such a column, the DDL
+	 * reload will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the
+	 * DDL reload will silently change it to "text" which won't match the
+	 * on-disk storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{.status = "Checking for invalid \"unknown\" user columns",
+	 .report_filename = "tables_using_unknown.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"unknown\" data type in user tables.\n"
+	 "This data type is no longer allowed in tables, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_9_6_check_for_unknown_data_type_usage},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 * In 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{.status = "Checking for invalid \"sql_identifier\" user columns",
+	 .report_filename = "tables_using_sql_identifier.txt",
+	 .base_query =
+	 "SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"sql_identifier\" data type in user tables.\n"
+	 "The on-disk format for this data type has changed, so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = old_11_check_for_sql_identifier_data_type_usage},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{.status = "Checking for incompatible \"jsonb\" data type",
+	 .report_filename = "tables_using_jsonb.txt",
+	 .base_query =
+	 "SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+	 .report_text =
+	 "Your installation contains the \"jsonb\" data type in user tables.\n"
+	 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+	 "cluster cannot currently be upgraded.  You can\n"
+	 "drop the problem columns and restart the upgrade.\n"
+	 "A list of the problem columns is in the file:",
+	 .version_hook = check_for_jsonb_9_4_usage},
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool	found = false;
+	bool   *results;
+	PQExpBufferData report;
+
+	prep_status("Checking for data type usage");
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult *res;
+			int 	ntups;
+			int 	i_nspname;
+			int 	i_relname;
+			int 	i_attname;
+			FILE   *script = NULL;
+			bool 	db_used = false;
+			char	output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+			{
+				cur_check++;
+				continue;
+			}
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested (to
+			 * varying extents depending on server version, but that's not of
+			 * concern here).  To handle all these cases we need a recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+							  "WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+							  "	%s "
+					  "	UNION ALL "
+					  "	SELECT * FROM ( "
+	/* inner WITH because we can only reference the CTE once */
+					  "		WITH x AS (SELECT oid FROM oids) "
+	/* domains on any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+					  "			UNION ALL "
+	/* arrays over any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+					  "			UNION ALL "
+	/* composite types containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+					  "			WHERE t.typtype = 'c' AND "
+					  "				  t.oid = c.reltype AND "
+					  "				  c.oid = a.attrelid AND "
+					  "				  NOT a.attisdropped AND "
+					  "				  a.atttypid = x.oid "
+					  "			UNION ALL "
+	/* ranges containing any type selected so far */
+					  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+					  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+					  "	) foo "
+					  ") "
+	/* now look for stored columns of any such type */
+					  "SELECT n.nspname, c.relname, a.attname "
+					  "FROM	pg_catalog.pg_class c, "
+					  "		pg_catalog.pg_namespace n, "
+					  "		pg_catalog.pg_attribute a "
+					  "WHERE	c.oid = a.attrelid AND "
+					  "		NOT a.attisdropped AND "
+					  "		a.atttypid IN (SELECT oid FROM oids) AND "
+					  "		c.relkind IN ("
+					  CppAsString2(RELKIND_RELATION) ", "
+					  CppAsString2(RELKIND_MATVIEW) ", "
+					  CppAsString2(RELKIND_INDEX) ") AND "
+					  "		c.relnamespace = n.oid AND "
+	/* exclude possible orphaned temp tables */
+					  "		n.nspname !~ '^pg_temp_' AND "
+					  "		n.nspname !~ '^pg_toast_temp_' AND "
+	/* exclude system catalogs, too */
+					  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+					  cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					found = true;
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, " %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+			cur_check++;
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +462,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +496,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +510,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1422,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 3eea0139c7..208bfbb68e 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck)(ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+} DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,19 +465,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
+bool		check_for_jsonb_9_4_usage(ClusterInfo *cluster);
+bool		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
+bool		check_for_aclitem_data_type_usage(ClusterInfo *cluster);
 
 /* parallel.c */
 void		parallel_exec_prog(const char *log_file, const char *opt_log_file,
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..828a975ac0 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,41 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	return found;
+	return false;
 }
 
 /*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
+ * check_for_jsonb_9_4_usage()
  *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
+ *     JSONB changed its storage format during 9.4 beta, so check for it.
  */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
-{
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+check_for_jsonb_9_4_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
+bool
 old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
 /*
@@ -353,41 +158,20 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
+bool
 old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
 }
 
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
@@ -459,3 +243,22 @@ report_extension_updates(ClusterInfo *cluster)
 	else
 		check_ok();
 }
+
+/*
+ * check_for_aclitem_data_type_usage
+ *
+ *     aclitem changed its storage format in 16, so check for it.
+ */
+bool
+check_for_aclitem_data_type_usage(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the on-disk
+	 * format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
+
-- 
2.25.1

From 084f64939eff769d6c9810e2c55dbcd942f79154 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Thu, 6 Jul 2023 17:55:45 +0200
Subject: [PATCH v5] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 589 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 288 +++-------------
 3 files changed, 446 insertions(+), 460 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 64024e3b9e..388555822f 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,389 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static int	n_data_types_usage_checks = 7;
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = "Checking for system-defined composite types in user tables",
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite type(s) in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = "Checking for incompatible \"line\" data type",
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = old_9_3_check_for_line_data_type_usage
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = "Checking for reg* data types in user tables",
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = "Checking for incompatible aclitem data type in user tables",
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = check_for_aclitem_data_type_usage
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = "Checking for invalid \"unknown\" user columns",
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = old_9_6_check_for_unknown_data_type_usage
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = "Checking for invalid \"sql_identifier\" user columns",
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = old_11_check_for_sql_identifier_data_type_usage
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = "Checking for incompatible \"jsonb\" data type",
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = check_for_jsonb_9_4_usage
+	},
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+
+	prep_status("Checking for data type usage");
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+			{
+				cur_check++;
+				continue;
+			}
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, " %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+			cur_check++;
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +476,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +510,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +524,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1436,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 3eea0139c7..aeb2c60a89 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,19 +465,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
+bool		check_for_jsonb_9_4_usage(ClusterInfo *cluster);
+bool		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
+bool		check_for_aclitem_data_type_usage(ClusterInfo *cluster);
 
 /* parallel.c */
 void		parallel_exec_prog(const char *log_file, const char *opt_log_file,
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..b1c5628bd7 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,41 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
 /*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
+ * check_for_jsonb_9_4_usage()
  *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
+ *     JSONB changed its storage format during 9.4 beta, so check for it.
  */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+check_for_jsonb_9_4_usage(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
+bool
 old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
 /*
@@ -353,41 +158,20 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
+bool
 old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
 }
 
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
@@ -459,3 +243,21 @@ report_extension_updates(ClusterInfo *cluster)
 	else
 		check_ok();
 }
+
+/*
+ * check_for_aclitem_data_type_usage
+ *
+ *     aclitem changed its storage format in 16, so check for it.
+ */
+bool
+check_for_aclitem_data_type_usage(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
-- 
2.32.1 (Apple Git-133)

From 723fd82ce174426619dadcb9f2d8b81b3ff532ea Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Thu, 6 Jul 2023 17:55:45 +0200
Subject: [PATCH v6] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 595 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 288 +++-------------
 3 files changed, 450 insertions(+), 462 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 64024e3b9e..cc9aa3cec2 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,395 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = "Checking for system-defined composite types in user tables",
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite type(s) in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = "Checking for incompatible \"line\" data type",
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = "Checking for reg* data types in user tables",
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = "Checking for incompatible aclitem data type in user tables",
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = "Checking for invalid \"unknown\" user columns",
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = "Checking for invalid \"sql_identifier\" user columns",
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = "Checking for incompatible \"jsonb\" data type",
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+		n_data_types_usage_checks++;
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +482,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +516,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +530,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1442,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 3eea0139c7..4d73ed8fb7 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,18 +465,14 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..a51cb7eafa 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,69 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
 }
 
 /*
@@ -353,41 +186,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 4ec6774b676e0e68d486e5a10e29b148fcfe509c Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Thu, 6 Jul 2023 17:55:45 +0200
Subject: [PATCH v7] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 598 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 288 +++------------
 3 files changed, 453 insertions(+), 462 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 64024e3b9e..815ff58540 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,398 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = "Checking for system-defined composite types in user tables",
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite type(s) in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = "Checking for incompatible \"line\" data type",
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = "Checking for reg* data types in user tables",
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = "Checking for incompatible aclitem data type in user tables",
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = "Checking for invalid \"unknown\" user columns",
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = "Checking for invalid \"sql_identifier\" user columns",
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = "Checking for incompatible \"jsonb\" data type",
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +485,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +519,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +533,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1445,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite type(s) in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 3eea0139c7..4d73ed8fb7 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,18 +465,14 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..a51cb7eafa 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,69 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
 }
 
 /*
@@ -353,41 +186,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 37922039d3439f88b115f57d61ced98b32bbd953 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Thu, 31 Aug 2023 23:28:34 +0200
Subject: [PATCH v8] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 598 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 288 +++------------
 3 files changed, 453 insertions(+), 462 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 56e313f562..b548aebae3 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,398 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = "Checking for system-defined composite types in user tables",
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite type(s) in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = "Checking for incompatible \"line\" data type",
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = "Checking for reg* data types in user tables",
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = "Checking for incompatible aclitem data type in user tables",
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = "Checking for invalid \"unknown\" user columns",
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = "Checking for invalid \"sql_identifier\" user columns",
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = "Checking for incompatible \"jsonb\" data type",
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	prep_status_progress("checking all databases");
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", cur_check->status);
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +485,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +519,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +533,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1445,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 7afa96716e..83fe15efca 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -328,6 +328,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -450,18 +465,14 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..a51cb7eafa 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,69 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
 }
 
 /*
@@ -353,41 +186,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 05791b7f3ebee5706940dba146fc2733d8b71669 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Thu, 14 Sep 2023 10:30:47 +0200
Subject: [PATCH v9] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 596 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  29 +-
 src/bin/pg_upgrade/version.c    | 288 +++------------
 3 files changed, 451 insertions(+), 462 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 56e313f562..5422d424a4 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,14 +24,396 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite type(s) in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible aclitem data type in user tables"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -100,16 +483,9 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -141,21 +517,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -164,14 +531,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1084,185 +1443,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 		check_ok();
 }
 
-
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"aclitem\" data type in user tables");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index 842f3b6cd3..313d635198 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -329,6 +329,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -451,18 +466,14 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..a51cb7eafa 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,69 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
 }
 
 /*
@@ -353,41 +186,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 08a69b7220279db98462e0b96dadeba4d227eba4 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Fri, 27 Oct 2023 13:44:28 +0200
Subject: [PATCH v10] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 687 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  30 +-
 src/bin/pg_upgrade/version.c    | 295 +++-----------
 3 files changed, 504 insertions(+), 508 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index fa52aa2c22..d94e2fe401 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,19 +24,441 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
 static void check_new_cluster_logical_replication_slots(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite types in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+		.report_filename = "tables_using_abstime.txt",
+		.base_query =
+		"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+		.report_text =
+		"Your installation contains the \"abstime\" data type in user tables.\n"
+		"The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+		"so this cluster cannot currently be upgraded.  You can drop the\n"
+		"problem columns, or change them to another data type, and restart\n"
+		"the upgrade.  A list of the problem columns is in the file:\n",
+		.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+		.report_filename = "tables_using_reltime.txt",
+		.base_query =
+		"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+		.report_text =
+		"Your installation contains the \"reltime\" data type in user tables.\n"
+		"The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+		"so this cluster cannot currently be upgraded.  You can drop the\n"
+		"problem columns, or change them to another data type, and restart\n"
+		"the upgrade.  A list of the problem columns is in the file:\n",
+		.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+		.report_filename = "tables_using_tinterval.txt",
+		.base_query =
+		"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+		.report_text =
+		"Your installation contains the \"tinterval\" data type in user tables.\n"
+		"The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+		"so this cluster cannot currently be upgraded.  You can drop the\n"
+		"problem columns, or change them to another data type, and restart\n"
+		"the upgrade.  A list of the problem columns is in the file:\n",
+		.version_hook = removed_data_types_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks *checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc(sizeof(bool) * n_data_types_usage_checks);
+	memset(results, true, sizeof(*results));
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = false;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -108,8 +531,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	/*
@@ -119,22 +540,7 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
 		check_old_cluster_for_valid_slots(live_check);
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -166,21 +572,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -189,14 +586,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1112,220 +1501,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index a710f325de..f949d5de9b 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -348,6 +348,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -471,18 +486,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
+bool		removed_data_types_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 403a6d7cfa..4382957b59 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,80 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	prep_status("Checking for invalid \"unknown\" user columns");
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+bool
+removed_data_types_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 12 removed abstime, reltime and tinterval */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -353,41 +197,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 2909537daddd43231a13f73f13adec91974a4f90 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Wed, 7 Feb 2024 13:36:46 +0100
Subject: [PATCH v11] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 686 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  30 +-
 src/bin/pg_upgrade/version.c    | 296 +++-----------
 3 files changed, 504 insertions(+), 508 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index e36a7328bf..566b49dbba 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,13 +24,6 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
@@ -38,6 +32,434 @@ static void check_new_cluster_subscription_configuration(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 static void check_old_cluster_subscription_state(void);
 
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			"Your installation contains system-defined composite types in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			"your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  you can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"a list of the problem columns is in the file:",
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			"Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:",
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:",
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+			.report_filename = "tables_using_abstime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"abstime\" data type in user tables.\n"
+			"The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:\n",
+			.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+			.report_filename = "tables_using_reltime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"reltime\" data type in user tables.\n"
+			"The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:\n",
+			.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+			.report_filename = "tables_using_tinterval.txt",
+			.base_query =
+			"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+			.report_text =
+			"Your installation contains the \"tinterval\" data type in user tables.\n"
+			"The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:\n",
+			.version_hook = removed_data_types_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc0(sizeof(bool) * n_data_types_usage_checks);
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (!results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  cur_check->report_text, output_path);
+				}
+				results[checknum] = true;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -110,8 +532,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
@@ -129,22 +549,7 @@ check_and_dump_old_cluster(bool live_check)
 		check_old_cluster_subscription_state();
 	}
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -176,21 +581,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -199,14 +595,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1124,220 +1512,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index d9a848cbfd..23b665527f 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -351,6 +351,21 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
 /*
  * Global variables
  */
@@ -475,18 +490,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
+bool		removed_data_types_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 13b2c0f012..2e060782ec 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,81 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	prep_status("Checking for invalid \"unknown\" user columns");
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+bool
+removed_data_types_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 12 removed abstime, reltime and tinterval
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -353,41 +198,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From c02fdf0e6dc29f53fef42dcead85c2079be597f6 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Wed, 7 Feb 2024 13:36:46 +0100
Subject: [PATCH v12] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 698 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  18 +-
 src/bin/pg_upgrade/version.c    | 296 +++-----------
 3 files changed, 504 insertions(+), 508 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index e36a7328bf..1ac8587059 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,13 +24,6 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
@@ -38,6 +32,446 @@ static void check_new_cluster_subscription_configuration(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 static void check_old_cluster_subscription_state(void);
 
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			gettext_noop("Your installation contains system-defined composite types in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = NULL
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = line_type_check_applicable
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			gettext_noop("Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = NULL
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:"),
+			.version_hook = aclitem_type_check_applicable
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = unknown_type_check_applicable
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = sql_identifier_type_check_applicable
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+			.report_filename = "tables_using_abstime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"abstime\" data type in user tables.\n"
+			"The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+			.report_filename = "tables_using_reltime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"reltime\" data type in user tables.\n"
+			"The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.version_hook = removed_data_types_check_applicable
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+			.report_filename = "tables_using_tinterval.txt",
+			.base_query =
+			"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"tinterval\" data type in user tables.\n"
+			"The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.version_hook = removed_data_types_check_applicable
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc0(sizeof(bool) * n_data_types_usage_checks);
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			/*
+			 * Make sure that the check applies to the current cluster version
+			 * and skip if not. If no check hook has been defined we run the
+			 * check for all versions.
+			 */
+			if (cur_check->version_hook && !cur_check->version_hook(cluster))
+				continue;
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (!results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  _(cur_check->report_text), output_path);
+				}
+				results[checknum] = true;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -110,8 +544,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
@@ -129,22 +561,7 @@ check_and_dump_old_cluster(bool live_check)
 		check_old_cluster_subscription_state();
 	}
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -176,21 +593,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -199,14 +607,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1124,220 +1524,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index d9a848cbfd..494335ea93 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -351,6 +351,9 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
 /*
  * Global variables
  */
@@ -475,18 +478,15 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		line_type_check_applicable(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
+bool		unknown_type_check_applicable(ClusterInfo *cluster);
+bool		sql_identifier_type_check_applicable(ClusterInfo *cluster);
+bool		aclitem_type_check_applicable(ClusterInfo *cluster);
+bool		removed_data_types_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 13b2c0f012..2e060782ec 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,81 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+line_type_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
+	/* Pre-PG 9.4 had a different 'line' data type internal format */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 903)
+		return true;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
+	return false;
 }
 
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
+	return false;
 }
 
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
+bool
+unknown_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	/* Pre-PG 10 allowed tables with 'unknown' type columns */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 906)
+		return true;
+	return false;
 }
 
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
+bool
+sql_identifier_type_check_applicable(ClusterInfo *cluster)
 {
-	char		output_path[MAXPGPATH];
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...).
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
+
+	return false;
+}
 
-	prep_status("Checking for invalid \"unknown\" user columns");
+bool
+aclitem_type_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1500)
+		return true;
+
+	return false;
+}
 
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
+bool
+removed_data_types_check_applicable(ClusterInfo *cluster)
+{
+	/*
+	 * PG 12 removed abstime, reltime and tinterval
+	 */
+	if (GET_MAJOR_VERSION(cluster->major_version) <= 1100)
+		return true;
 
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -353,41 +198,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 7e8ec96cf4ff291595482ae2226e82cbdf16662e Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Wed, 7 Feb 2024 13:36:46 +0100
Subject: [PATCH v13] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 715 ++++++++++++++++++++------------
 src/bin/pg_upgrade/pg_upgrade.h |  13 +-
 src/bin/pg_upgrade/version.c    | 266 +-----------
 3 files changed, 472 insertions(+), 522 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index e36a7328bf..663e270f30 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,13 +24,6 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
@@ -38,6 +32,463 @@ static void check_new_cluster_subscription_configuration(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 static void check_old_cluster_subscription_state(void);
 
+#define MANUAL_CHECK 0
+#define ALL_VERSIONS -1
+
+/*
+ * DataTypesUsageChecks
+ */
+typedef struct
+{
+	const char *status;			/* status line to print to the user */
+	const char *report_filename;	/* filename to store report to */
+	const char *base_query;		/* Query to extract the oid of the datatype */
+	const char *report_text;	/* Text to store to report in case of error */
+	int threshold_version;
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
+/*
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and a function pointer for determining if the check should be executed
+ * for the current version.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			gettext_noop("Your installation contains system-defined composite types in user tables.\n"
+			"These type OIDs are not stable across PostgreSQL versions,\n"
+			"so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"line\" data type in user tables.\n"
+			"this data type changed its internal and input/output format\n"
+			"between your old and new versions so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = 903
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			gettext_noop("Your installation contains one of the reg* data types in user tables.\n"
+			"These data types reference system OIDs that are not preserved by\n"
+			"pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"aclitem\" data type in user tables.\n"
+			"The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns and restart the upgrade.  A list of the problem\n"
+			"columns is in the file:"),
+			.threshold_version = 1500
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"unknown\" data type in user tables.\n"
+			"This data type is no longer allowed in tables, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = 906
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"sql_identifier\" data type in user tables.\n"
+			"The on-disk format for this data type has changed, so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = 1100
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"jsonb\" data type in user tables.\n"
+			"The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+			"cluster cannot currently be upgraded.  You can\n"
+			"drop the problem columns and restart the upgrade.\n"
+			"A list of the problem columns is in the file:"),
+			.threshold_version = MANUAL_CHECK,
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+			.report_filename = "tables_using_abstime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"abstime\" data type in user tables.\n"
+			"The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+			.report_filename = "tables_using_reltime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"reltime\" data type in user tables.\n"
+			"The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+			.report_filename = "tables_using_tinterval.txt",
+			.base_query =
+			"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"tinterval\" data type in user tables.\n"
+			"The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+			"so this cluster cannot currently be upgraded.  You can drop the\n"
+			"problem columns, or change them to another data type, and restart\n"
+			"the upgrade.  A list of the problem columns is in the file:"),
+			.threshold_version = 1100
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, 0, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc0(sizeof(bool) * n_data_types_usage_checks);
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			if (cur_check->threshold_version == MANUAL_CHECK)
+			{
+				Assert(cur_check->version_hook);
+
+				/*
+				 * Make sure that the check applies to the current cluster version
+				 * and skip if not. If no check hook has been defined we run the
+				 * check for all versions.
+				 */
+				if (!cur_check->version_hook(cluster))
+					continue;
+			}
+			else if (cur_check->threshold_version != ALL_VERSIONS)
+			{
+				if (GET_MAJOR_VERSION(cluster->major_version) > cur_check->threshold_version)
+					continue;
+			}
+			else
+				Assert(cur_check->threshold_version == ALL_VERSIONS);
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (!results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n    %s\n",
+									  _(cur_check->report_text), output_path);
+				}
+				results[checknum] = true;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -110,8 +561,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
@@ -129,22 +578,7 @@ check_and_dump_old_cluster(bool live_check)
 		check_old_cluster_subscription_state();
 	}
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -176,21 +610,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -199,14 +624,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1124,220 +1541,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index d9a848cbfd..7daa67f809 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -351,6 +351,9 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
 /*
  * Global variables
  */
@@ -475,18 +478,10 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 13b2c0f012..e3c7b4109c 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,23 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
-bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
-{
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
-}
-
 /*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -353,41 +140,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 2d9ec92dd3af34ab240364445a404fef2d46caa1 Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Wed, 7 Feb 2024 13:36:46 +0100
Subject: [PATCH v14] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On cluster which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize connection
setup/teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 750 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  13 +-
 src/bin/pg_upgrade/version.c    | 266 +----------
 3 files changed, 507 insertions(+), 522 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index e36a7328bf..6d640d7bb0 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,13 +24,6 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
@@ -38,6 +32,498 @@ static void check_new_cluster_subscription_configuration(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 static void check_old_cluster_subscription_state(void);
 
+/*
+ * DataTypesUsageChecks - definitions of data type checks for the old cluster
+ * in order to determine if an upgrade can be performed.  See the comment on
+ * data_types_usage_checks below for a more detailed description.
+ */
+typedef struct
+{
+	/* Status line to print to the user */
+	const char *status;
+	/* Filename to store report to */
+	const char *report_filename;
+	/* Query to extract the oid of the datatype */
+	const char *base_query;
+	/* Text to store to report in case of error */
+	const char *report_text;
+	/* The latest version where the check applies */
+	int			threshold_version;
+	/* A function pointer for determining if the check applies */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
+/*
+ * Special values for threshold_version for indicating that a check applies to
+ * all versions, or that a custom function needs to be invoked to determine
+ * if the check applies.
+ */
+#define MANUAL_CHECK 1
+#define ALL_VERSIONS -1
+
+/*--
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and functionality for deciding if the check is applicable to the version
+ * of the old cluster. The struct members are described in detail below:
+ *
+ * status				A oneline string which can be printed to the user to
+ *						inform about progress. Should not end with newline.
+ * report_filename		The filename in which the list of problems detected by
+ *						the check will be printed.
+ * base_query			A query which extracts the Oid of the datatype checked
+ *						for.
+ * report_text			The text which will be printed to the user to explain
+ *						what the check did, and why it failed. The text should
+ *						end with a newline, and does not need to refer to the
+ *						report_filename as that is automatically appended to
+ *						the report with the path to the log folder.
+ * threshold_version	The major version of PostgreSQL for which to run the
+ *						check. Iff the old cluster is less than, or equal to,
+ *						the threshold version then the check will be executed.
+ *						If the old version is greater than the threshold then
+ *						the check is skipped. If the threshold_version is set
+ *						to ALL_VERSIONS then it will be run unconditionally,
+ *						if set to MANUAL_CHECK then the version_hook function
+ *						will be executed in order to determine whether or not
+ *						to run.
+ * version_hook			A function pointer to a version check function of type
+ *						DataTypesUsageVersionCheck which is used to determine
+ *						if the check is applicable to the old cluster. If the
+ *						version_hook returns true then the check will be run,
+ *						else it will be skipped. The function will only be
+ *						executed iff threshold_version is set to MANUAL_CHECK.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			gettext_noop("Your installation contains system-defined composite types in user tables.\n"
+						 "These type OIDs are not stable across PostgreSQL versions,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns and restart the upgrade.\n"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"line\" data type in user tables.\n"
+						 "this data type changed its internal and input/output format\n"
+						 "between your old and new versions so this\n"
+						 "cluster cannot currently be upgraded.  You can\n"
+						 "drop the problem columns and restart the upgrade.\n"),
+			.threshold_version = 903
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			gettext_noop("Your installation contains one of the reg* data types in user tables.\n"
+						 "These data types reference system OIDs that are not preserved by\n"
+						 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+						 "drop the problem columns and restart the upgrade.\n"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"aclitem\" data type in user tables.\n"
+						 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns and restart the upgrade.\n"),
+			.threshold_version = 1500
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"unknown\" data type in user tables.\n"
+						 "This data type is no longer allowed in tables, so this cluster\n"
+						 "cannot currently be upgraded.  You can drop the problem columns\n"
+						 "and restart the upgrade.\n"),
+			.threshold_version = 906
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"sql_identifier\" data type in user tables.\n"
+						 "The on-disk format for this data type has changed, so this\n"
+						 "cluster cannot currently be upgraded.  You can drop the problem\n"
+						 "columns and restart the upgrade.\n"),
+			.threshold_version = 1100
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"jsonb\" data type in user tables.\n"
+						 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+						 "cluster cannot currently be upgraded.  You can drop the problem \n"
+						 "columns and restart the upgrade.\n"),
+			.threshold_version = MANUAL_CHECK,
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+			.report_filename = "tables_using_abstime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"abstime\" data type in user tables.\n"
+						 "The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+			.report_filename = "tables_using_reltime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"reltime\" data type in user tables.\n"
+						 "The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+			.report_filename = "tables_using_tinterval.txt",
+			.base_query =
+			"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"tinterval\" data type in user tables.\n"
+						 "The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, 0, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc0(sizeof(bool) * n_data_types_usage_checks);
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			if (cur_check->threshold_version == MANUAL_CHECK)
+			{
+				Assert(cur_check->version_hook);
+
+				/*
+				 * Make sure that the check applies to the current cluster
+				 * version and skip if not. If no check hook has been defined
+				 * we run the check for all versions.
+				 */
+				if (!cur_check->version_hook(cluster))
+					continue;
+			}
+			else if (cur_check->threshold_version != ALL_VERSIONS)
+			{
+				if (GET_MAJOR_VERSION(cluster->major_version) > cur_check->threshold_version)
+					continue;
+			}
+			else
+				Assert(cur_check->threshold_version == ALL_VERSIONS);
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (!results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n%s    %s\n",
+									  _(cur_check->report_text),
+									  _("A list of the problem columns is in the file:"),
+									  output_path);
+				}
+				results[checknum] = true;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %s",
+								 output_path,
+								 strerror(errno));
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -110,8 +596,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
@@ -129,22 +613,7 @@ check_and_dump_old_cluster(bool live_check)
 		check_old_cluster_subscription_state();
 	}
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -176,21 +645,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -199,14 +659,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1124,220 +1576,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index d9a848cbfd..7daa67f809 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -351,6 +351,9 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
 /*
  * Global variables
  */
@@ -475,18 +478,10 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 13b2c0f012..e3c7b4109c 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,236 +9,23 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
-/*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
- */
-bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
-{
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
-
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %s", output_path,
-						 strerror(errno));
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
-}
-
 /*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -353,41 +140,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)

From 428da9b257e73ef01abe3f2ffff218066b0afdaa Mon Sep 17 00:00:00 2001
From: Daniel Gustafsson <dgustafsson@postgresql.org>
Date: Mon, 18 Mar 2024 10:54:45 +0100
Subject: [PATCH v15] pg_upgrade: run all data type checks per connection

The checks for data type usage were each connecting to all databases
in the cluster and running their query. On clusters which have a lot
of databases this can become unnecessarily expensive. This moves the
checks to run in a single connection instead to minimize setup and
teardown overhead.

Reviewed-by: Nathan Bossart <nathandbossart@gmail.com>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/BB4C76F-D416-4F9F-949E-DBE950D37787@yesql.se
---
 src/bin/pg_upgrade/check.c      | 749 +++++++++++++++++++++-----------
 src/bin/pg_upgrade/pg_upgrade.h |  13 +-
 src/bin/pg_upgrade/version.c    | 265 +----------
 3 files changed, 506 insertions(+), 521 deletions(-)

diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c
index 8ce6c674e3..c198896c9f 100644
--- a/src/bin/pg_upgrade/check.c
+++ b/src/bin/pg_upgrade/check.c
@@ -10,6 +10,7 @@
 #include "postgres_fe.h"
 
 #include "catalog/pg_authid_d.h"
+#include "catalog/pg_class_d.h"
 #include "catalog/pg_collation.h"
 #include "fe_utils/string_utils.h"
 #include "mb/pg_wchar.h"
@@ -23,13 +24,6 @@ static void check_for_isn_and_int8_passing_mismatch(ClusterInfo *cluster);
 static void check_for_user_defined_postfix_ops(ClusterInfo *cluster);
 static void check_for_incompatible_polymorphics(ClusterInfo *cluster);
 static void check_for_tables_with_oids(ClusterInfo *cluster);
-static void check_for_composite_data_type_usage(ClusterInfo *cluster);
-static void check_for_reg_data_type_usage(ClusterInfo *cluster);
-static void check_for_aclitem_data_type_usage(ClusterInfo *cluster);
-static void check_for_removed_data_type_usage(ClusterInfo *cluster,
-											  const char *version,
-											  const char *datatype);
-static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(void);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
@@ -38,6 +32,497 @@ static void check_new_cluster_subscription_configuration(void);
 static void check_old_cluster_for_valid_slots(bool live_check);
 static void check_old_cluster_subscription_state(void);
 
+/*
+ * DataTypesUsageChecks - definitions of data type checks for the old cluster
+ * in order to determine if an upgrade can be performed.  See the comment on
+ * data_types_usage_checks below for a more detailed description.
+ */
+typedef struct
+{
+	/* Status line to print to the user */
+	const char *status;
+	/* Filename to store report to */
+	const char *report_filename;
+	/* Query to extract the oid of the datatype */
+	const char *base_query;
+	/* Text to store to report in case of error */
+	const char *report_text;
+	/* The latest version where the check applies */
+	int			threshold_version;
+	/* A function pointer for determining if the check applies */
+	DataTypesUsageVersionCheck version_hook;
+}			DataTypesUsageChecks;
+
+/*
+ * Special values for threshold_version for indicating that a check applies to
+ * all versions, or that a custom function needs to be invoked to determine
+ * if the check applies.
+ */
+#define MANUAL_CHECK 1
+#define ALL_VERSIONS -1
+
+/*--
+ * Data type usage checks. Each check for problematic data type usage is
+ * defined in this array with metadata, SQL query for finding the data type
+ * and functionality for deciding if the check is applicable to the version
+ * of the old cluster. The struct members are described in detail below:
+ *
+ * status				A oneline string which can be printed to the user to
+ *						inform about progress. Should not end with newline.
+ * report_filename		The filename in which the list of problems detected by
+ *						the check will be printed.
+ * base_query			A query which extracts the Oid of the datatype checked
+ *						for.
+ * report_text			The text which will be printed to the user to explain
+ *						what the check did, and why it failed. The text should
+ *						end with a newline, and does not need to refer to the
+ *						report_filename as that is automatically appended to
+ *						the report with the path to the log folder.
+ * threshold_version	The major version of PostgreSQL for which to run the
+ *						check. Iff the old cluster is less than, or equal to,
+ *						the threshold version then the check will be executed.
+ *						If the old version is greater than the threshold then
+ *						the check is skipped. If the threshold_version is set
+ *						to ALL_VERSIONS then it will be run unconditionally,
+ *						if set to MANUAL_CHECK then the version_hook function
+ *						will be executed in order to determine whether or not
+ *						to run.
+ * version_hook			A function pointer to a version check function of type
+ *						DataTypesUsageVersionCheck which is used to determine
+ *						if the check is applicable to the old cluster. If the
+ *						version_hook returns true then the check will be run,
+ *						else it will be skipped. The function will only be
+ *						executed iff threshold_version is set to MANUAL_CHECK.
+ */
+static DataTypesUsageChecks data_types_usage_checks[] =
+{
+	/*
+	 * Look for composite types that were made during initdb *or* belong to
+	 * information_schema; that's important in case information_schema was
+	 * dropped and reloaded.
+	 *
+	 * The cutoff OID here should match the source cluster's value of
+	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
+	 * because, if that #define is ever changed, our own version's value is
+	 * NOT what to use.  Eventually we may need a test on the source cluster's
+	 * version to select the correct value.
+	 */
+	{
+		.status = gettext_noop("Checking for system-defined composite types in user tables"),
+			.report_filename = "tables_using_composite.txt",
+			.base_query =
+			"SELECT t.oid FROM pg_catalog.pg_type t "
+			"LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
+			" WHERE typtype = 'c' AND (t.oid < 16384 OR nspname = 'information_schema')",
+			.report_text =
+			gettext_noop("Your installation contains system-defined composite types in user tables.\n"
+						 "These type OIDs are not stable across PostgreSQL versions,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns and restart the upgrade.\n"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * 9.3 -> 9.4 Fully implement the 'line' data type in 9.4, which
+	 * previously returned "not enabled" by default and was only functionally
+	 * enabled with a compile-time switch; as of 9.4 "line" has a different
+	 * on-disk representation format.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"line\" data type"),
+			.report_filename = "tables_using_line.txt",
+			.base_query =
+			"SELECT 'pg_catalog.line'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"line\" data type in user tables.\n"
+						 "this data type changed its internal and input/output format\n"
+						 "between your old and new versions so this\n"
+						 "cluster cannot currently be upgraded.  You can\n"
+						 "drop the problem columns and restart the upgrade.\n"),
+			.threshold_version = 903
+	},
+
+	/*
+	 * pg_upgrade only preserves these system values: pg_class.oid pg_type.oid
+	 * pg_enum.oid
+	 *
+	 * Many of the reg* data types reference system catalog info that is not
+	 * preserved, and hence these data types cannot be used in user tables
+	 * upgraded by pg_upgrade.
+	 */
+	{
+		.status = gettext_noop("Checking for reg* data types in user tables"),
+			.report_filename = "tables_using_reg.txt",
+
+		/*
+		 * Note: older servers will not have all of these reg* types, so we
+		 * have to write the query like this rather than depending on casts to
+		 * regtype.
+		 */
+			.base_query =
+			"SELECT oid FROM pg_catalog.pg_type t "
+			"WHERE t.typnamespace = "
+			"        (SELECT oid FROM pg_catalog.pg_namespace "
+			"         WHERE nspname = 'pg_catalog') "
+			"  AND t.typname IN ( "
+		/* pg_class.oid is preserved, so 'regclass' is OK */
+			"           'regcollation', "
+			"           'regconfig', "
+			"           'regdictionary', "
+			"           'regnamespace', "
+			"           'regoper', "
+			"           'regoperator', "
+			"           'regproc', "
+			"           'regprocedure' "
+		/* pg_authid.oid is preserved, so 'regrole' is OK */
+		/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
+			"         )",
+			.report_text =
+			gettext_noop("Your installation contains one of the reg* data types in user tables.\n"
+						 "These data types reference system OIDs that are not preserved by\n"
+						 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
+						 "drop the problem columns and restart the upgrade.\n"),
+			.threshold_version = ALL_VERSIONS
+	},
+
+	/*
+	 * PG 16 increased the size of the 'aclitem' type, which breaks the
+	 * on-disk format for existing data.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"aclitem\" data type"),
+			.report_filename = "tables_using_aclitem.txt",
+			.base_query =
+			"SELECT 'pg_catalog.aclitem'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"aclitem\" data type in user tables.\n"
+						 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns and restart the upgrade.\n"),
+			.threshold_version = 1500
+	},
+
+	/*
+	 * It's no longer allowed to create tables or views with "unknown"-type
+	 * columns.  We do not complain about views with such columns, because
+	 * they should get silently converted to "text" columns during the DDL
+	 * dump and reload; it seems unlikely to be worth making users do that by
+	 * hand.  However, if there's a table with such a column, the DDL reload
+	 * will fail, so we should pre-detect that rather than failing
+	 * mid-upgrade.  Worse, if there's a matview with such a column, the DDL
+	 * reload will silently change it to "text" which won't match the on-disk
+	 * storage (which is like "cstring").  So we *must* reject that.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"unknown\" user columns"),
+			.report_filename = "tables_using_unknown.txt",
+			.base_query =
+			"SELECT 'pg_catalog.unknown'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"unknown\" data type in user tables.\n"
+						 "This data type is no longer allowed in tables, so this cluster\n"
+						 "cannot currently be upgraded.  You can drop the problem columns\n"
+						 "and restart the upgrade.\n"),
+			.threshold_version = 906
+	},
+
+	/*
+	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
+	 * not varchar, which breaks on-disk format for existing data. So we need
+	 * to prevent upgrade when used in user objects (tables, indexes, ...). In
+	 * 12, the sql_identifier data type was switched from name to varchar,
+	 * which does affect the storage (name is by-ref, but not varlena). This
+	 * means user tables using sql_identifier for columns are broken because
+	 * the on-disk format is different.
+	 */
+	{
+		.status = gettext_noop("Checking for invalid \"sql_identifier\" user columns"),
+			.report_filename = "tables_using_sql_identifier.txt",
+			.base_query =
+			"SELECT 'information_schema.sql_identifier'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"sql_identifier\" data type in user tables.\n"
+						 "The on-disk format for this data type has changed, so this\n"
+						 "cluster cannot currently be upgraded.  You can drop the problem\n"
+						 "columns and restart the upgrade.\n"),
+			.threshold_version = 1100
+	},
+
+	/*
+	 * JSONB changed its storage format during 9.4 beta, so check for it.
+	 */
+	{
+		.status = gettext_noop("Checking for incompatible \"jsonb\" data type in user tables"),
+			.report_filename = "tables_using_jsonb.txt",
+			.base_query =
+			"SELECT 'pg_catalog.jsonb'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"jsonb\" data type in user tables.\n"
+						 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
+						 "cluster cannot currently be upgraded.  You can drop the problem \n"
+						 "columns and restart the upgrade.\n"),
+			.threshold_version = MANUAL_CHECK,
+			.version_hook = jsonb_9_4_check_applicable
+	},
+
+	/*
+	 * PG 12 removed types abstime, reltime, tinterval.
+	 */
+	{
+		.status = gettext_noop("Checking for removed \"abstime\" data type in user tables"),
+			.report_filename = "tables_using_abstime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.abstime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"abstime\" data type in user tables.\n"
+						 "The \"abstime\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"reltime\" data type in user tables"),
+			.report_filename = "tables_using_reltime.txt",
+			.base_query =
+			"SELECT 'pg_catalog.reltime'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"reltime\" data type in user tables.\n"
+						 "The \"reltime\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+	{
+		.status = gettext_noop("Checking for removed \"tinterval\" data type in user tables"),
+			.report_filename = "tables_using_tinterval.txt",
+			.base_query =
+			"SELECT 'pg_catalog.tinterval'::pg_catalog.regtype AS oid",
+			.report_text =
+			gettext_noop("Your installation contains the \"tinterval\" data type in user tables.\n"
+						 "The \"tinterval\" type has been removed in PostgreSQL version 12,\n"
+						 "so this cluster cannot currently be upgraded.  You can drop the\n"
+						 "problem columns, or change them to another data type, and restart\n"
+						 "the upgrade.\n"),
+			.threshold_version = 1100
+	},
+
+	/* End of checks marker, must remain last */
+	{
+		NULL, NULL, NULL, NULL, 0, NULL
+	}
+};
+
+/*
+ * check_for_data_types_usage()
+ *	Detect whether there are any stored columns depending on given type(s)
+ *
+ * If so, write a report to the given file name and signal a failure to the
+ * user.
+ *
+ * The checks to run are defined in a DataTypesUsageChecks structure where
+ * each check has a metadata for explaining errors to the user, a base_query,
+ * a report filename and a function pointer hook for validating if the check
+ * should be executed given the cluster at hand.
+ *
+ * base_query should be a SELECT yielding a single column named "oid",
+ * containing the pg_type OIDs of one or more types that are known to have
+ * inconsistent on-disk representations across server versions.
+ *
+ * We check for the type(s) in tables, matviews, and indexes, but not views;
+ * there's no storage involved in a view.
+ */
+static void
+check_for_data_types_usage(ClusterInfo *cluster, DataTypesUsageChecks * checks)
+{
+	bool		found = false;
+	bool	   *results;
+	PQExpBufferData report;
+	DataTypesUsageChecks *tmp = checks;
+	int			n_data_types_usage_checks = 0;
+
+	prep_status("Checking for data type usage");
+
+	/* Gather number of checks to perform */
+	while (tmp->status != NULL)
+	{
+		n_data_types_usage_checks++;
+		tmp++;
+	}
+
+	/* Prepare an array to store the results of checks in */
+	results = pg_malloc0(sizeof(bool) * n_data_types_usage_checks);
+
+	/*
+	 * Connect to each database in the cluster and run all defined checks
+	 * against that database before trying the next one.
+	 */
+	for (int dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
+	{
+		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
+		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
+
+		for (int checknum = 0; checknum < n_data_types_usage_checks; checknum++)
+		{
+			PGresult   *res;
+			int			ntups;
+			int			i_nspname;
+			int			i_relname;
+			int			i_attname;
+			FILE	   *script = NULL;
+			bool		db_used = false;
+			char		output_path[MAXPGPATH];
+			DataTypesUsageChecks *cur_check = &checks[checknum];
+
+			if (cur_check->threshold_version == MANUAL_CHECK)
+			{
+				Assert(cur_check->version_hook);
+
+				/*
+				 * Make sure that the check applies to the current cluster
+				 * version and skip if not. If no check hook has been defined
+				 * we run the check for all versions.
+				 */
+				if (!cur_check->version_hook(cluster))
+					continue;
+			}
+			else if (cur_check->threshold_version != ALL_VERSIONS)
+			{
+				if (GET_MAJOR_VERSION(cluster->major_version) > cur_check->threshold_version)
+					continue;
+			}
+			else
+				Assert(cur_check->threshold_version == ALL_VERSIONS);
+
+			snprintf(output_path, sizeof(output_path), "%s/%s",
+					 log_opts.basedir,
+					 cur_check->report_filename);
+
+			/*
+			 * The type(s) of interest might be wrapped in a domain, array,
+			 * composite, or range, and these container types can be nested
+			 * (to varying extents depending on server version, but that's not
+			 * of concern here).  To handle all these cases we need a
+			 * recursive CTE.
+			 */
+			res = executeQueryOrDie(conn,
+									"WITH RECURSIVE oids AS ( "
+			/* start with the type(s) returned by base_query */
+									"	%s "
+									"	UNION ALL "
+									"	SELECT * FROM ( "
+			/* inner WITH because we can only reference the CTE once */
+									"		WITH x AS (SELECT oid FROM oids) "
+			/* domains on any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
+									"			UNION ALL "
+			/* arrays over any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
+									"			UNION ALL "
+			/* composite types containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
+									"			WHERE t.typtype = 'c' AND "
+									"				  t.oid = c.reltype AND "
+									"				  c.oid = a.attrelid AND "
+									"				  NOT a.attisdropped AND "
+									"				  a.atttypid = x.oid "
+									"			UNION ALL "
+			/* ranges containing any type selected so far */
+									"			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
+									"			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
+									"	) foo "
+									") "
+			/* now look for stored columns of any such type */
+									"SELECT n.nspname, c.relname, a.attname "
+									"FROM	pg_catalog.pg_class c, "
+									"		pg_catalog.pg_namespace n, "
+									"		pg_catalog.pg_attribute a "
+									"WHERE	c.oid = a.attrelid AND "
+									"		NOT a.attisdropped AND "
+									"		a.atttypid IN (SELECT oid FROM oids) AND "
+									"		c.relkind IN ("
+									CppAsString2(RELKIND_RELATION) ", "
+									CppAsString2(RELKIND_MATVIEW) ", "
+									CppAsString2(RELKIND_INDEX) ") AND "
+									"		c.relnamespace = n.oid AND "
+			/* exclude possible orphaned temp tables */
+									"		n.nspname !~ '^pg_temp_' AND "
+									"		n.nspname !~ '^pg_toast_temp_' AND "
+			/* exclude system catalogs, too */
+									"		n.nspname NOT IN ('pg_catalog', 'information_schema')",
+									cur_check->base_query);
+
+			ntups = PQntuples(res);
+
+			/*
+			 * The datatype was found, so extract the data and log to the
+			 * requested filename. We need to open the file for appending
+			 * since the check might have already found the type in another
+			 * database earlier in the loop.
+			 */
+			if (ntups)
+			{
+				/*
+				 * Make sure we have a buffer to save reports to now that we
+				 * found a first failing check.
+				 */
+				if (!found)
+					initPQExpBuffer(&report);
+				found = true;
+
+				/*
+				 * If this is the first time we see an error for the check in
+				 * question then print a status message of the failure.
+				 */
+				if (!results[checknum])
+				{
+					pg_log(PG_REPORT, "    failed check: %s", _(cur_check->status));
+					appendPQExpBuffer(&report, "\n%s\n%s    %s\n",
+									  _(cur_check->report_text),
+									  _("A list of the problem columns is in the file:"),
+									  output_path);
+				}
+				results[checknum] = true;
+
+				i_nspname = PQfnumber(res, "nspname");
+				i_relname = PQfnumber(res, "relname");
+				i_attname = PQfnumber(res, "attname");
+
+				for (int rowno = 0; rowno < ntups; rowno++)
+				{
+					if (script == NULL && (script = fopen_priv(output_path, "a")) == NULL)
+						pg_fatal("could not open file \"%s\": %m", output_path);
+
+					if (!db_used)
+					{
+						fprintf(script, "In database: %s\n", active_db->db_name);
+						db_used = true;
+					}
+					fprintf(script, "  %s.%s.%s\n",
+							PQgetvalue(res, rowno, i_nspname),
+							PQgetvalue(res, rowno, i_relname),
+							PQgetvalue(res, rowno, i_attname));
+				}
+
+				if (script)
+				{
+					fclose(script);
+					script = NULL;
+				}
+			}
+
+			PQclear(res);
+		}
+
+		PQfinish(conn);
+	}
+
+	if (found)
+		pg_fatal("Data type checks failed: %s", report.data);
+
+	check_ok();
+}
 
 /*
  * fix_path_separator
@@ -110,8 +595,6 @@ check_and_dump_old_cluster(bool live_check)
 	check_is_install_user(&old_cluster);
 	check_proper_datallowconn(&old_cluster);
 	check_for_prepared_transactions(&old_cluster);
-	check_for_composite_data_type_usage(&old_cluster);
-	check_for_reg_data_type_usage(&old_cluster);
 	check_for_isn_and_int8_passing_mismatch(&old_cluster);
 
 	if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700)
@@ -129,22 +612,7 @@ check_and_dump_old_cluster(bool live_check)
 		check_old_cluster_subscription_state();
 	}
 
-	/*
-	 * PG 16 increased the size of the 'aclitem' type, which breaks the
-	 * on-disk format for existing data.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1500)
-		check_for_aclitem_data_type_usage(&old_cluster);
-
-	/*
-	 * PG 12 removed types abstime, reltime, tinterval.
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-	{
-		check_for_removed_data_type_usage(&old_cluster, "12", "abstime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "reltime");
-		check_for_removed_data_type_usage(&old_cluster, "12", "tinterval");
-	}
+	check_for_data_types_usage(&old_cluster, data_types_usage_checks);
 
 	/*
 	 * PG 14 changed the function signature of encoding conversion functions.
@@ -176,21 +644,12 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
 		check_for_tables_with_oids(&old_cluster);
 
-	/*
-	 * PG 12 changed the 'sql_identifier' type storage to be based on name,
-	 * not varchar, which breaks on-disk format for existing data. So we need
-	 * to prevent upgrade when used in user objects (tables, indexes, ...).
-	 */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1100)
-		old_11_check_for_sql_identifier_data_type_usage(&old_cluster);
-
 	/*
 	 * Pre-PG 10 allowed tables with 'unknown' type columns and non WAL logged
 	 * hash indexes
 	 */
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906)
 	{
-		old_9_6_check_for_unknown_data_type_usage(&old_cluster);
 		if (user_opts.check)
 			old_9_6_invalidate_hash_indexes(&old_cluster, true);
 	}
@@ -199,14 +658,6 @@ check_and_dump_old_cluster(bool live_check)
 	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 905)
 		check_for_pg_role_prefix(&old_cluster);
 
-	if (GET_MAJOR_VERSION(old_cluster.major_version) == 904 &&
-		old_cluster.controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
-		check_for_jsonb_9_4_usage(&old_cluster);
-
-	/* Pre-PG 9.4 had a different 'line' data type internal format */
-	if (GET_MAJOR_VERSION(old_cluster.major_version) <= 903)
-		old_9_3_check_for_line_data_type_usage(&old_cluster);
-
 	/*
 	 * While not a check option, we do this now because this is the only time
 	 * the old server is running.
@@ -1122,220 +1573,6 @@ check_for_tables_with_oids(ClusterInfo *cluster)
 }
 
 
-/*
- * check_for_composite_data_type_usage()
- *	Check for system-defined composite types used in user tables.
- *
- *	The OIDs of rowtypes of system catalogs and information_schema views
- *	can change across major versions; unlike user-defined types, we have
- *	no mechanism for forcing them to be the same in the new cluster.
- *	Hence, if any user table uses one, that's problematic for pg_upgrade.
- */
-static void
-check_for_composite_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	Oid			firstUserOid;
-	char		output_path[MAXPGPATH];
-	char	   *base_query;
-
-	prep_status("Checking for system-defined composite types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_composite.txt");
-
-	/*
-	 * Look for composite types that were made during initdb *or* belong to
-	 * information_schema; that's important in case information_schema was
-	 * dropped and reloaded.
-	 *
-	 * The cutoff OID here should match the source cluster's value of
-	 * FirstNormalObjectId.  We hardcode it rather than using that C #define
-	 * because, if that #define is ever changed, our own version's value is
-	 * NOT what to use.  Eventually we may need a test on the source cluster's
-	 * version to select the correct value.
-	 */
-	firstUserOid = 16384;
-
-	base_query = psprintf("SELECT t.oid FROM pg_catalog.pg_type t "
-						  "LEFT JOIN pg_catalog.pg_namespace n ON t.typnamespace = n.oid "
-						  " WHERE typtype = 'c' AND (t.oid < %u OR nspname = 'information_schema')",
-						  firstUserOid);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains system-defined composite types in user tables.\n"
-				 "These type OIDs are not stable across PostgreSQL versions,\n"
-				 "so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_reg_data_type_usage()
- *	pg_upgrade only preserves these system values:
- *		pg_class.oid
- *		pg_type.oid
- *		pg_enum.oid
- *
- *	Many of the reg* data types reference system catalog info that is
- *	not preserved, and hence these data types cannot be used in user
- *	tables upgraded by pg_upgrade.
- */
-static void
-check_for_reg_data_type_usage(ClusterInfo *cluster)
-{
-	bool		found;
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for reg* data types in user tables");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_reg.txt");
-
-	/*
-	 * Note: older servers will not have all of these reg* types, so we have
-	 * to write the query like this rather than depending on casts to regtype.
-	 */
-	found = check_for_data_types_usage(cluster,
-									   "SELECT oid FROM pg_catalog.pg_type t "
-									   "WHERE t.typnamespace = "
-									   "        (SELECT oid FROM pg_catalog.pg_namespace "
-									   "         WHERE nspname = 'pg_catalog') "
-									   "  AND t.typname IN ( "
-	/* pg_class.oid is preserved, so 'regclass' is OK */
-									   "           'regcollation', "
-									   "           'regconfig', "
-									   "           'regdictionary', "
-									   "           'regnamespace', "
-									   "           'regoper', "
-									   "           'regoperator', "
-									   "           'regproc', "
-									   "           'regprocedure' "
-	/* pg_authid.oid is preserved, so 'regrole' is OK */
-	/* pg_type.oid is (mostly) preserved, so 'regtype' is OK */
-									   "         )",
-									   output_path);
-
-	if (found)
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains one of the reg* data types in user tables.\n"
-				 "These data types reference system OIDs that are not preserved by\n"
-				 "pg_upgrade, so this cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_aclitem_data_type_usage
- *
- *	aclitem changed its storage format in 16, so check for it.
- */
-static void
-check_for_aclitem_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"%s\" data type in user tables",
-				"aclitem");
-
-	snprintf(output_path, sizeof(output_path), "tables_using_aclitem.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.aclitem", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"aclitem\" data type in user tables.\n"
-				 "The internal format of \"aclitem\" changed in PostgreSQL version 16\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns and restart the upgrade.  A list of the problem\n"
-				 "columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-/*
- * check_for_removed_data_type_usage
- *
- *	Check for in-core data types that have been removed.  Callers know
- *	the exact list.
- */
-static void
-check_for_removed_data_type_usage(ClusterInfo *cluster, const char *version,
-								  const char *datatype)
-{
-	char		output_path[MAXPGPATH];
-	char		typename[NAMEDATALEN];
-
-	prep_status("Checking for removed \"%s\" data type in user tables",
-				datatype);
-
-	snprintf(output_path, sizeof(output_path), "tables_using_%s.txt",
-			 datatype);
-	snprintf(typename, sizeof(typename), "pg_catalog.%s", datatype);
-
-	if (check_for_data_type_usage(cluster, typename, output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"%s\" data type in user tables.\n"
-				 "The \"%s\" type has been removed in PostgreSQL version %s,\n"
-				 "so this cluster cannot currently be upgraded.  You can drop the\n"
-				 "problem columns, or change them to another data type, and restart\n"
-				 "the upgrade.  A list of the problem columns is in the file:\n"
-				 "    %s", datatype, datatype, version, output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * check_for_jsonb_9_4_usage()
- *
- *	JSONB changed its storage format during 9.4 beta, so check for it.
- */
-static void
-check_for_jsonb_9_4_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"jsonb\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_jsonb.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.jsonb", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"jsonb\" data type in user tables.\n"
-				 "The internal format of \"jsonb\" changed during 9.4 beta so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
 /*
  * check_for_pg_role_prefix()
  *
diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h
index c0bfb002d2..92bcb693fb 100644
--- a/src/bin/pg_upgrade/pg_upgrade.h
+++ b/src/bin/pg_upgrade/pg_upgrade.h
@@ -352,6 +352,9 @@ typedef struct
 } OSInfo;
 
 
+/* Function signature for data type check version hook */
+typedef bool (*DataTypesUsageVersionCheck) (ClusterInfo *cluster);
+
 /*
  * Global variables
  */
@@ -479,18 +482,10 @@ unsigned int str2uint(const char *str);
 
 /* version.c */
 
-bool		check_for_data_types_usage(ClusterInfo *cluster,
-									   const char *base_query,
-									   const char *output_path);
-bool		check_for_data_type_usage(ClusterInfo *cluster,
-									  const char *type_name,
-									  const char *output_path);
-void		old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster);
-void		old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster);
+bool		jsonb_9_4_check_applicable(ClusterInfo *cluster);
 void		old_9_6_invalidate_hash_indexes(ClusterInfo *cluster,
 											bool check_mode);
 
-void		old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster);
 void		report_extension_updates(ClusterInfo *cluster);
 
 /* parallel.c */
diff --git a/src/bin/pg_upgrade/version.c b/src/bin/pg_upgrade/version.c
index 9dc1399f36..2de6dffccd 100644
--- a/src/bin/pg_upgrade/version.c
+++ b/src/bin/pg_upgrade/version.c
@@ -9,235 +9,23 @@
 
 #include "postgres_fe.h"
 
-#include "catalog/pg_class_d.h"
 #include "fe_utils/string_utils.h"
 #include "pg_upgrade.h"
 
-
 /*
- * check_for_data_types_usage()
- *	Detect whether there are any stored columns depending on given type(s)
- *
- * If so, write a report to the given file name, and return true.
- *
- * base_query should be a SELECT yielding a single column named "oid",
- * containing the pg_type OIDs of one or more types that are known to have
- * inconsistent on-disk representations across server versions.
- *
- * We check for the type(s) in tables, matviews, and indexes, but not views;
- * there's no storage involved in a view.
+ * version_hook functions for check_for_data_types_usage in order to determine
+ * whether a data type check should be executed for the cluster in question or
+ * not.
  */
 bool
-check_for_data_types_usage(ClusterInfo *cluster,
-						   const char *base_query,
-						   const char *output_path)
+jsonb_9_4_check_applicable(ClusterInfo *cluster)
 {
-	bool		found = false;
-	FILE	   *script = NULL;
-	int			dbnum;
+	/* JSONB changed its storage format during 9.4 beta */
+	if (GET_MAJOR_VERSION(cluster->major_version) == 904 &&
+		cluster->controldata.cat_ver < JSONB_FORMAT_CHANGE_CAT_VER)
+		return true;
 
-	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
-	{
-		DbInfo	   *active_db = &cluster->dbarr.dbs[dbnum];
-		PGconn	   *conn = connectToServer(cluster, active_db->db_name);
-		PQExpBufferData querybuf;
-		PGresult   *res;
-		bool		db_used = false;
-		int			ntups;
-		int			rowno;
-		int			i_nspname,
-					i_relname,
-					i_attname;
-
-		/*
-		 * The type(s) of interest might be wrapped in a domain, array,
-		 * composite, or range, and these container types can be nested (to
-		 * varying extents depending on server version, but that's not of
-		 * concern here).  To handle all these cases we need a recursive CTE.
-		 */
-		initPQExpBuffer(&querybuf);
-		appendPQExpBuffer(&querybuf,
-						  "WITH RECURSIVE oids AS ( "
-		/* start with the type(s) returned by base_query */
-						  "	%s "
-						  "	UNION ALL "
-						  "	SELECT * FROM ( "
-		/* inner WITH because we can only reference the CTE once */
-						  "		WITH x AS (SELECT oid FROM oids) "
-		/* domains on any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typbasetype = x.oid AND typtype = 'd' "
-						  "			UNION ALL "
-		/* arrays over any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, x WHERE typelem = x.oid AND typtype = 'b' "
-						  "			UNION ALL "
-		/* composite types containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_class c, pg_catalog.pg_attribute a, x "
-						  "			WHERE t.typtype = 'c' AND "
-						  "				  t.oid = c.reltype AND "
-						  "				  c.oid = a.attrelid AND "
-						  "				  NOT a.attisdropped AND "
-						  "				  a.atttypid = x.oid "
-						  "			UNION ALL "
-		/* ranges containing any type selected so far */
-						  "			SELECT t.oid FROM pg_catalog.pg_type t, pg_catalog.pg_range r, x "
-						  "			WHERE t.typtype = 'r' AND r.rngtypid = t.oid AND r.rngsubtype = x.oid"
-						  "	) foo "
-						  ") "
-		/* now look for stored columns of any such type */
-						  "SELECT n.nspname, c.relname, a.attname "
-						  "FROM	pg_catalog.pg_class c, "
-						  "		pg_catalog.pg_namespace n, "
-						  "		pg_catalog.pg_attribute a "
-						  "WHERE	c.oid = a.attrelid AND "
-						  "		NOT a.attisdropped AND "
-						  "		a.atttypid IN (SELECT oid FROM oids) AND "
-						  "		c.relkind IN ("
-						  CppAsString2(RELKIND_RELATION) ", "
-						  CppAsString2(RELKIND_MATVIEW) ", "
-						  CppAsString2(RELKIND_INDEX) ") AND "
-						  "		c.relnamespace = n.oid AND "
-		/* exclude possible orphaned temp tables */
-						  "		n.nspname !~ '^pg_temp_' AND "
-						  "		n.nspname !~ '^pg_toast_temp_' AND "
-		/* exclude system catalogs, too */
-						  "		n.nspname NOT IN ('pg_catalog', 'information_schema')",
-						  base_query);
-
-		res = executeQueryOrDie(conn, "%s", querybuf.data);
-
-		ntups = PQntuples(res);
-		i_nspname = PQfnumber(res, "nspname");
-		i_relname = PQfnumber(res, "relname");
-		i_attname = PQfnumber(res, "attname");
-		for (rowno = 0; rowno < ntups; rowno++)
-		{
-			found = true;
-			if (script == NULL && (script = fopen_priv(output_path, "w")) == NULL)
-				pg_fatal("could not open file \"%s\": %m", output_path);
-			if (!db_used)
-			{
-				fprintf(script, "In database: %s\n", active_db->db_name);
-				db_used = true;
-			}
-			fprintf(script, "  %s.%s.%s\n",
-					PQgetvalue(res, rowno, i_nspname),
-					PQgetvalue(res, rowno, i_relname),
-					PQgetvalue(res, rowno, i_attname));
-		}
-
-		PQclear(res);
-
-		termPQExpBuffer(&querybuf);
-
-		PQfinish(conn);
-	}
-
-	if (script)
-		fclose(script);
-
-	return found;
-}
-
-/*
- * check_for_data_type_usage()
- *	Detect whether there are any stored columns depending on the given type
- *
- * If so, write a report to the given file name, and return true.
- *
- * type_name should be a fully qualified type name.  This is just a
- * trivial wrapper around check_for_data_types_usage() to convert a
- * type name into a base query.
- */
-bool
-check_for_data_type_usage(ClusterInfo *cluster,
-						  const char *type_name,
-						  const char *output_path)
-{
-	bool		found;
-	char	   *base_query;
-
-	base_query = psprintf("SELECT '%s'::pg_catalog.regtype AS oid",
-						  type_name);
-
-	found = check_for_data_types_usage(cluster, base_query, output_path);
-
-	free(base_query);
-
-	return found;
-}
-
-
-/*
- * old_9_3_check_for_line_data_type_usage()
- *	9.3 -> 9.4
- *	Fully implement the 'line' data type in 9.4, which previously returned
- *	"not enabled" by default and was only functionally enabled with a
- *	compile-time switch; as of 9.4 "line" has a different on-disk
- *	representation format.
- */
-void
-old_9_3_check_for_line_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for incompatible \"line\" data type");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_line.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.line", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"line\" data type in user tables.\n"
-				 "This data type changed its internal and input/output format\n"
-				 "between your old and new versions so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
-/*
- * old_9_6_check_for_unknown_data_type_usage()
- *	9.6 -> 10
- *	It's no longer allowed to create tables or views with "unknown"-type
- *	columns.  We do not complain about views with such columns, because
- *	they should get silently converted to "text" columns during the DDL
- *	dump and reload; it seems unlikely to be worth making users do that
- *	by hand.  However, if there's a table with such a column, the DDL
- *	reload will fail, so we should pre-detect that rather than failing
- *	mid-upgrade.  Worse, if there's a matview with such a column, the
- *	DDL reload will silently change it to "text" which won't match the
- *	on-disk storage (which is like "cstring").  So we *must* reject that.
- */
-void
-old_9_6_check_for_unknown_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"unknown\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_unknown.txt");
-
-	if (check_for_data_type_usage(cluster, "pg_catalog.unknown", output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"unknown\" data type in user tables.\n"
-				 "This data type is no longer allowed in tables, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
+	return false;
 }
 
 /*
@@ -351,41 +139,6 @@ old_9_6_invalidate_hash_indexes(ClusterInfo *cluster, bool check_mode)
 		check_ok();
 }
 
-/*
- * old_11_check_for_sql_identifier_data_type_usage()
- *	11 -> 12
- *	In 12, the sql_identifier data type was switched from name to varchar,
- *	which does affect the storage (name is by-ref, but not varlena). This
- *	means user tables using sql_identifier for columns are broken because
- *	the on-disk format is different.
- */
-void
-old_11_check_for_sql_identifier_data_type_usage(ClusterInfo *cluster)
-{
-	char		output_path[MAXPGPATH];
-
-	prep_status("Checking for invalid \"sql_identifier\" user columns");
-
-	snprintf(output_path, sizeof(output_path), "%s/%s",
-			 log_opts.basedir,
-			 "tables_using_sql_identifier.txt");
-
-	if (check_for_data_type_usage(cluster, "information_schema.sql_identifier",
-								  output_path))
-	{
-		pg_log(PG_REPORT, "fatal");
-		pg_fatal("Your installation contains the \"sql_identifier\" data type in user tables.\n"
-				 "The on-disk format for this data type has changed, so this\n"
-				 "cluster cannot currently be upgraded.  You can\n"
-				 "drop the problem columns and restart the upgrade.\n"
-				 "A list of the problem columns is in the file:\n"
-				 "    %s", output_path);
-	}
-	else
-		check_ok();
-}
-
-
 /*
  * report_extension_updates()
  *	Report extensions that should be updated.
-- 
2.32.1 (Apple Git-133)