Merge 10.10 into 10.11

cmake/cpack_rpm.cmake

@@ -155,6 +155,7 @@ SET(ignored
   "%ignore ${CMAKE_INSTALL_PREFIX}/share/doc"
   "%ignore ${CMAKE_INSTALL_PREFIX}/share/man"
   "%ignore ${CMAKE_INSTALL_PREFIX}/share/man/man1"
+  "%ignore ${CMAKE_INSTALL_PREFIX}/share/man/man3"
   "%ignore ${CMAKE_INSTALL_PREFIX}/share/man/man8"
   "%ignore ${CMAKE_INSTALL_PREFIX}/share/pkgconfig"
   )

include/mysql/service_wsrep.h

@@ -69,6 +69,9 @@ extern struct wsrep_service_st {
   void                        (*wsrep_thd_self_abort_func)(MYSQL_THD thd);
   int                         (*wsrep_thd_append_key_func)(MYSQL_THD thd, const struct wsrep_key* key,
                                                            int n_keys, enum Wsrep_service_key_type);
+  int                         (*wsrep_thd_append_table_key_func)(MYSQL_THD thd, const char* db,
+                                                           const char* table, enum Wsrep_service_key_type);
+  my_bool                     (*wsrep_thd_is_local_transaction)(const MYSQL_THD thd);
   const char*                 (*wsrep_thd_client_state_str_func)(const MYSQL_THD thd);
   const char*                 (*wsrep_thd_client_mode_str_func)(const MYSQL_THD thd);
   const char*                 (*wsrep_thd_transaction_state_str_func)(const MYSQL_THD thd);
@@ -121,6 +124,8 @@ extern struct wsrep_service_st {
 #define wsrep_thd_is_local(T) wsrep_service->wsrep_thd_is_local_func(T)
 #define wsrep_thd_self_abort(T) wsrep_service->wsrep_thd_self_abort_func(T)
 #define wsrep_thd_append_key(T,W,N,K) wsrep_service->wsrep_thd_append_key_func(T,W,N,K)
+#define wsrep_thd_append_table_key(T,D,B,K) wsrep_service->wsrep_thd_append_table_key_func(T,D,B,K)
+#define wsrep_thd_is_local_transaction(T) wsrep_service->wsrep_thd_is_local_transaction_func(T)
 #define wsrep_thd_client_state_str(T) wsrep_service->wsrep_thd_client_state_str_func(T)
 #define wsrep_thd_client_mode_str(T) wsrep_service->wsrep_thd_client_mode_str_func(T)
 #define wsrep_thd_transaction_state_str(T) wsrep_service->wsrep_thd_transaction_state_str_func(T)
@@ -226,6 +231,13 @@ extern "C" int wsrep_thd_append_key(MYSQL_THD thd,
                                     int n_keys,
                                     enum Wsrep_service_key_type);
 
+extern "C" int wsrep_thd_append_table_key(MYSQL_THD thd,
+                                    const char* db,
+                                    const char* table,
+                                    enum Wsrep_service_key_type);
+
+extern "C" my_bool wsrep_thd_is_local_transaction(const MYSQL_THD thd);
+
 extern const char* wsrep_sr_table_name_full;
 
 extern "C" const char* wsrep_get_sr_table_name();

mysql-test/suite/galera/disabled.def

@@ -11,7 +11,6 @@
 ##############################################################################
 
 galera_as_slave_ctas : MDEV-28378 timeout
-galera_bf_abort_at_after_statement : Timeout in wait_condition.inc for SELECT COUNT(*) = 1 FROM t1 where id = 1 and val = 3
 galera_pc_recovery : MDEV-25199 cluster fails to start up
 galera_sst_encrypted : MDEV-29876 Galera test failure on galera_sst_encrypted
 MW-284 : MDEV-29861 Galera test case hangs

mysql-test/suite/galera/r/galera_insert_bulk.result

@@ -0,0 +1,30 @@
+connection node_2;
+connection node_1;
+connection node_1;
+CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
+SET foreign_key_checks = 0;
+SET unique_checks = 0;
+START TRANSACTION;
+connection node_2;
+SET foreign_key_checks = 1;
+SET unique_checks = 1;
+INSERT INTO t1 VALUES (1001);
+connection node_1;
+COMMIT;
+ERROR 40001: Deadlock found when trying to get lock; try restarting transaction
+DROP TABLE t1;
+connection node_1;
+CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
+START TRANSACTION;
+connection node_2;
+SET foreign_key_checks = 1;
+SET unique_checks = 1;
+START TRANSACTION;
+INSERT INTO t1 VALUES (1001);
+connection node_1;
+COMMIT;
+2
+connection node_2;
+COMMIT;
+ERROR 40001: Deadlock found when trying to get lock; try restarting transaction
+DROP TABLE t1;

mysql-test/suite/galera/t/galera_insert_bulk.test

@@ -0,0 +1,88 @@
+#
+# Test that bulk insert replicates as table-level exclusive key and
+# rolls back properly if needed.
+#
+
+--source include/galera_cluster.inc
+--source include/have_innodb.inc
+
+#
+# Make bulk insert BF-abort, but regular insert succeed.
+#
+
+--connection node_1
+CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
+
+# Disable foreign and unique key checks to allow bulk insert.
+SET foreign_key_checks = 0;
+SET unique_checks = 0;
+
+START TRANSACTION;
+
+--let $count=0
+--disable_query_log
+while ($count < 1000)
+{
+  --eval INSERT INTO t1 VALUES ($count)
+  --inc $count
+}
+--enable_query_log
+
+--connection node_2
+
+# Disable bulk insert.
+SET foreign_key_checks = 1;
+SET unique_checks = 1;
+
+# Insert a value out of the bulk insert range.
+INSERT INTO t1 VALUES (1001);
+
+--connection node_1
+--error ER_LOCK_DEADLOCK
+COMMIT;
+
+DROP TABLE t1;
+
+#
+# Make bulk insert succeed, but regular insert BF-abort.
+#
+
+--connection node_1
+CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
+
+--let $before_bulk_keys = `SELECT VARIABLE_VALUE FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_repl_keys'`
+
+START TRANSACTION;
+
+--let $count=0
+--disable_query_log
+while ($count < 1000)
+{
+  --eval INSERT INTO t1 VALUES ($count)
+  --inc $count
+}
+--enable_query_log
+
+--connection node_2
+
+# Disable bulk insert.
+SET foreign_key_checks = 1;
+SET unique_checks = 1;
+
+START TRANSACTION;
+
+# Insert a value out of the bulk insert range.
+INSERT INTO t1 VALUES (1001);
+
+--connection node_1
+COMMIT;
+
+# Expect two keys to be added for bulk insert: DB-level shared key and table-level exclusive key.
+--let $bulk_keys_count = `SELECT VARIABLE_VALUE - $before_bulk_keys FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_repl_keys'`
+--echo $bulk_keys_count
+
+--connection node_2
+--error ER_LOCK_DEADLOCK
+COMMIT;
+
+DROP TABLE t1;

mysql-test/suite/galera_3nodes/disabled.def

@@ -12,10 +12,8 @@
 
 galera_2_cluster : MDEV-29877 Galera test failure on galera_2_cluster
 galera_gtid_2_cluster : MDEV-29877 Galera test failure on galera_2_cluster
-galera_parallel_apply_3nodes : MDEV-29368 DEBUG_SYNC timeout
 galera_ipv6_mariabackup : MDEV-24097
 galera_ipv6_mariabackup_section :  MDEV-24097, MDEV-22195
-galera_parallel_apply_3nodes : MDEV-29774 Galera test galera_parallel_apply_3nodes is unstable
 galera_vote_rejoin_mysqldump : MDEV-24481: galera_3nodes.galera_vote_rejoin_mysqldump MTR failed: mysql_shutdown failed
 galera_ssl_reload : MDEV-30172 At line 50: mysql_shutdown failed
 GCF-354 : mysqltest: At line 39: query 'DROP TABLE test.t1' failed: 1047: WSREP has not yet prepared node for application use

mysql-test/suite/innodb/r/innodb-change-buffer-recovery.result

@@ -1,51 +0,0 @@
-#
-# Bug#69122 - INNODB DOESN'T REDO-LOG INSERT BUFFER MERGE
-#             OPERATION IF IT IS DONE IN-PLACE
-#
-call mtr.add_suppression("InnoDB: innodb_read_only prevents crash recovery");
-call mtr.add_suppression("Plugin initialization aborted at srv0start\\.cc");
-call mtr.add_suppression("Plugin 'InnoDB'");
-FLUSH TABLES;
-CREATE TABLE t1(
-a INT AUTO_INCREMENT PRIMARY KEY,
-b CHAR(1),
-c INT,
-INDEX(b))
-ENGINE=InnoDB STATS_PERSISTENT=0;
-SET GLOBAL innodb_change_buffering_debug = 1;
-SET GLOBAL innodb_change_buffering = all;
-Warnings:
-Warning	1287	'@@innodb_change_buffering' is deprecated and will be removed in a future release
-INSERT INTO t1 SELECT 0,'x',1 FROM seq_1_to_8192;
-BEGIN;
-SELECT b FROM t1 LIMIT 3;
-b
-x
-x
-x
-connect  con1,localhost,root,,;
-BEGIN;
-DELETE FROM t1 WHERE a=1;
-INSERT INTO t1 VALUES(1,'X',1);
-SET DEBUG_DBUG='+d,crash_after_log_ibuf_upd_inplace';
-SELECT b FROM t1 LIMIT 3;
-ERROR HY000: Lost connection to server during query
-disconnect con1;
-connection default;
-FOUND 1 /Wrote log record for ibuf update in place operation/ in mysqld.1.err
-# restart: --innodb-read-only
-CHECK TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	check	Error	Unknown storage engine 'InnoDB'
-test.t1	check	error	Corrupt
-FOUND 1 /innodb_read_only prevents crash recovery/ in mysqld.1.err
-# restart: --innodb-force-recovery=5 --debug-dbug=d,crash_after_log_ibuf_upd_inplace
-SELECT * FROM t1 LIMIT 1;
-a	b	c
-1	X	1
-SET GLOBAL innodb_fast_shutdown=0;
-# restart
-CHECK TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	check	status	OK
-DROP TABLE t1;

mysql-test/suite/innodb/r/innodb_wl6326.result

@@ -1,405 +0,0 @@
-SET GLOBAL innodb_adaptive_hash_index = false;
-SET GLOBAL innodb_stats_persistent = false;
-connect  con1,localhost,root,,;
-connect  con2,localhost,root,,;
-connect  con3,localhost,root,,;
-CREATE TABLE t1 (
-a00 CHAR(255) NOT NULL DEFAULT 'a',
-a01 CHAR(255) NOT NULL DEFAULT 'a',
-a02 CHAR(255) NOT NULL DEFAULT 'a',
-a03 CHAR(255) NOT NULL DEFAULT 'a',
-a04 CHAR(255) NOT NULL DEFAULT 'a',
-a05 CHAR(255) NOT NULL DEFAULT 'a',
-a06 CHAR(255) NOT NULL DEFAULT 'a',
-b INT NOT NULL DEFAULT 0
-) ENGINE = InnoDB;
-ALTER TABLE t1 ADD PRIMARY KEY(
-a00,
-a01,
-a02,
-a03,
-a04,
-a05,
-a06
-);
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-1
-SET GLOBAL innodb_limit_optimistic_insert_debug = 7;
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('aa');
-INSERT INTO t1 (a00) VALUES ('ab');
-INSERT INTO t1 (a00) VALUES ('ac');
-INSERT INTO t1 (a00) VALUES ('ad');
-INSERT INTO t1 (a00) VALUES ('ae');
-INSERT INTO t1 (a00) VALUES ('af');
-INSERT INTO t1 (a00) VALUES ('ag');
-INSERT INTO t1 (a00) VALUES ('ah');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-3
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('ai');
-INSERT INTO t1 (a00) VALUES ('aj');
-INSERT INTO t1 (a00) VALUES ('ak');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-4
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('al');
-INSERT INTO t1 (a00) VALUES ('am');
-INSERT INTO t1 (a00) VALUES ('an');
-INSERT INTO t1 (a00) VALUES ('ao');
-INSERT INTO t1 (a00) VALUES ('ap');
-INSERT INTO t1 (a00) VALUES ('aq');
-INSERT INTO t1 (a00) VALUES ('ar');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-5
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('as');
-INSERT INTO t1 (a00) VALUES ('at');
-INSERT INTO t1 (a00) VALUES ('au');
-INSERT INTO t1 (a00) VALUES ('av');
-INSERT INTO t1 (a00) VALUES ('aw');
-INSERT INTO t1 (a00) VALUES ('ax');
-INSERT INTO t1 (a00) VALUES ('ay');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-6
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('az');
-INSERT INTO t1 (a00) VALUES ('ba');
-INSERT INTO t1 (a00) VALUES ('bb');
-INSERT INTO t1 (a00) VALUES ('bc');
-INSERT INTO t1 (a00) VALUES ('bd');
-INSERT INTO t1 (a00) VALUES ('be');
-INSERT INTO t1 (a00) VALUES ('bf');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-7
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bg');
-INSERT INTO t1 (a00) VALUES ('bh');
-INSERT INTO t1 (a00) VALUES ('bi');
-INSERT INTO t1 (a00) VALUES ('bj');
-INSERT INTO t1 (a00) VALUES ('bk');
-INSERT INTO t1 (a00) VALUES ('bl');
-INSERT INTO t1 (a00) VALUES ('bm');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-8
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bn');
-INSERT INTO t1 (a00) VALUES ('bo');
-INSERT INTO t1 (a00) VALUES ('bp');
-INSERT INTO t1 (a00) VALUES ('bq');
-INSERT INTO t1 (a00) VALUES ('br');
-INSERT INTO t1 (a00) VALUES ('bs');
-INSERT INTO t1 (a00) VALUES ('bt');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-11
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bu');
-INSERT INTO t1 (a00) VALUES ('bv');
-INSERT INTO t1 (a00) VALUES ('bw');
-INSERT INTO t1 (a00) VALUES ('bx');
-INSERT INTO t1 (a00) VALUES ('by');
-INSERT INTO t1 (a00) VALUES ('bz');
-INSERT INTO t1 (a00) VALUES ('ca');
-INSERT INTO t1 (a00) VALUES ('cb');
-INSERT INTO t1 (a00) VALUES ('cc');
-INSERT INTO t1 (a00) VALUES ('cd');
-INSERT INTO t1 (a00) VALUES ('ce');
-INSERT INTO t1 (a00) VALUES ('cf');
-INSERT INTO t1 (a00) VALUES ('cg');
-INSERT INTO t1 (a00) VALUES ('ch');
-INSERT INTO t1 (a00) VALUES ('ci');
-INSERT INTO t1 (a00) VALUES ('cj');
-INSERT INTO t1 (a00) VALUES ('ck');
-INSERT INTO t1 (a00) VALUES ('cl');
-INSERT INTO t1 (a00) VALUES ('cm');
-INSERT INTO t1 (a00) VALUES ('cn');
-INSERT INTO t1 (a00) VALUES ('co');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-15
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('cp');
-INSERT INTO t1 (a00) VALUES ('cq');
-INSERT INTO t1 (a00) VALUES ('cr');
-INSERT INTO t1 (a00) VALUES ('cs');
-INSERT INTO t1 (a00) VALUES ('ct');
-INSERT INTO t1 (a00) VALUES ('cu');
-INSERT INTO t1 (a00) VALUES ('cv');
-INSERT INTO t1 (a00) VALUES ('cw');
-INSERT INTO t1 (a00) VALUES ('cx');
-INSERT INTO t1 (a00) VALUES ('cy');
-INSERT INTO t1 (a00) VALUES ('cz');
-INSERT INTO t1 (a00) VALUES ('da');
-INSERT INTO t1 (a00) VALUES ('db');
-INSERT INTO t1 (a00) VALUES ('dc');
-INSERT INTO t1 (a00) VALUES ('dd');
-INSERT INTO t1 (a00) VALUES ('de');
-INSERT INTO t1 (a00) VALUES ('df');
-INSERT INTO t1 (a00) VALUES ('dg');
-INSERT INTO t1 (a00) VALUES ('dh');
-INSERT INTO t1 (a00) VALUES ('di');
-INSERT INTO t1 (a00) VALUES ('dj');
-INSERT INTO t1 (a00) VALUES ('dk');
-INSERT INTO t1 (a00) VALUES ('dl');
-INSERT INTO t1 (a00) VALUES ('dm');
-INSERT INTO t1 (a00) VALUES ('dn');
-INSERT INTO t1 (a00) VALUES ('do');
-INSERT INTO t1 (a00) VALUES ('dp');
-INSERT INTO t1 (a00) VALUES ('dq');
-INSERT INTO t1 (a00) VALUES ('dr');
-INSERT INTO t1 (a00) VALUES ('ds');
-INSERT INTO t1 (a00) VALUES ('dt');
-INSERT INTO t1 (a00) VALUES ('du');
-INSERT INTO t1 (a00) VALUES ('dv');
-INSERT INTO t1 (a00) VALUES ('dw');
-INSERT INTO t1 (a00) VALUES ('dx');
-INSERT INTO t1 (a00) VALUES ('dy');
-INSERT INTO t1 (a00) VALUES ('dz');
-INSERT INTO t1 (a00) VALUES ('ea');
-INSERT INTO t1 (a00) VALUES ('eb');
-INSERT INTO t1 (a00) VALUES ('ec');
-INSERT INTO t1 (a00) VALUES ('ed');
-INSERT INTO t1 (a00) VALUES ('ee');
-INSERT INTO t1 (a00) VALUES ('ef');
-INSERT INTO t1 (a00) VALUES ('eg');
-INSERT INTO t1 (a00) VALUES ('eh');
-INSERT INTO t1 (a00) VALUES ('ei');
-INSERT INTO t1 (a00) VALUES ('ej');
-INSERT INTO t1 (a00) VALUES ('ek');
-INSERT INTO t1 (a00) VALUES ('el');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-23
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('em');
-INSERT INTO t1 (a00) VALUES ('en');
-INSERT INTO t1 (a00) VALUES ('eo');
-INSERT INTO t1 (a00) VALUES ('ep');
-INSERT INTO t1 (a00) VALUES ('eq');
-INSERT INTO t1 (a00) VALUES ('er');
-INSERT INTO t1 (a00) VALUES ('es');
-INSERT INTO t1 (a00) VALUES ('et');
-INSERT INTO t1 (a00) VALUES ('eu');
-INSERT INTO t1 (a00) VALUES ('ev');
-INSERT INTO t1 (a00) VALUES ('ew');
-INSERT INTO t1 (a00) VALUES ('ex');
-INSERT INTO t1 (a00) VALUES ('ey');
-INSERT INTO t1 (a00) VALUES ('ez');
-INSERT INTO t1 (a00) VALUES ('fa');
-INSERT INTO t1 (a00) VALUES ('fb');
-INSERT INTO t1 (a00) VALUES ('fc');
-INSERT INTO t1 (a00) VALUES ('fd');
-INSERT INTO t1 (a00) VALUES ('fe');
-INSERT INTO t1 (a00) VALUES ('ff');
-INSERT INTO t1 (a00) VALUES ('fg');
-INSERT INTO t1 (a00) VALUES ('fh');
-INSERT INTO t1 (a00) VALUES ('fi');
-INSERT INTO t1 (a00) VALUES ('fj');
-INSERT INTO t1 (a00) VALUES ('fk');
-INSERT INTO t1 (a00) VALUES ('fl');
-INSERT INTO t1 (a00) VALUES ('fm');
-INSERT INTO t1 (a00) VALUES ('fn');
-INSERT INTO t1 (a00) VALUES ('fo');
-INSERT INTO t1 (a00) VALUES ('fp');
-INSERT INTO t1 (a00) VALUES ('fq');
-INSERT INTO t1 (a00) VALUES ('fr');
-INSERT INTO t1 (a00) VALUES ('fs');
-INSERT INTO t1 (a00) VALUES ('ft');
-INSERT INTO t1 (a00) VALUES ('fu');
-INSERT INTO t1 (a00) VALUES ('fv');
-INSERT INTO t1 (a00) VALUES ('fw');
-INSERT INTO t1 (a00) VALUES ('fx');
-INSERT INTO t1 (a00) VALUES ('fy');
-INSERT INTO t1 (a00) VALUES ('fz');
-INSERT INTO t1 (a00) VALUES ('ga');
-INSERT INTO t1 (a00) VALUES ('gb');
-INSERT INTO t1 (a00) VALUES ('gc');
-INSERT INTO t1 (a00) VALUES ('gd');
-INSERT INTO t1 (a00) VALUES ('ge');
-INSERT INTO t1 (a00) VALUES ('gf');
-INSERT INTO t1 (a00) VALUES ('gg');
-INSERT INTO t1 (a00) VALUES ('gh');
-COMMIT;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-29
-SET GLOBAL innodb_limit_optimistic_insert_debug = 0;
-# Test start
-SET DEBUG_SYNC = 'RESET';
-INSERT INTO t1 (a00) VALUES ('bfa');
-connection con1;
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-INSERT INTO t1 (a00) VALUES ('bfb');
-connection con2;
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-a00	a01
-aa	a
-SELECT a00,a01 FROM t1 WHERE a00 = 'aq';
-a00	a01
-aq	a
-SELECT a00,a01 FROM t1 WHERE a00 = 'cp';
-a00	a01
-cp	a
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-a00	a01
-el	a
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-SELECT a00,a01 FROM t1 WHERE a00 = 'ar';
-connection con3;
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-SELECT a00,a01 FROM t1 WHERE a00 = 'cn';
-connection default;
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
-SET DEBUG_SYNC = 'now SIGNAL continue';
-connection con1;
-connection con2;
-a00	a01
-ar	a
-connection con3;
-a00	a01
-cn	a
-connection default;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-30
-SET DEBUG_SYNC = 'RESET';
-INSERT INTO t1 (a00) VALUES ('coa');
-connection con1;
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-INSERT INTO t1 (a00) VALUES ('cob');
-connection con2;
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-connection con3;
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-connection default;
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
-SET DEBUG_SYNC = 'now SIGNAL continue';
-connection con1;
-connection con2;
-a00	a01
-aa	a
-connection con3;
-a00	a01
-el	a
-connection default;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-31
-SET DEBUG_SYNC = 'RESET';
-INSERT INTO t1 (a00) VALUES ('gba');
-connection con1;
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-INSERT INTO t1 (a00) VALUES ('gbb');
-connection con2;
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-a00	a01
-aa	a
-SELECT a00,a01 FROM t1 WHERE a00 = 'ek';
-a00	a01
-ek	a
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-connection con3;
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-SELECT a00,a01 FROM t1 WHERE a00 = 'gb';
-connection default;
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
-SET DEBUG_SYNC = 'now SIGNAL continue';
-connection con1;
-connection con2;
-a00	a01
-el	a
-connection con3;
-a00	a01
-gb	a
-connection default;
-ANALYZE TABLE t1;
-Table	Op	Msg_type	Msg_text
-test.t1	analyze	status	Engine-independent statistics collected
-test.t1	analyze	status	OK
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-CLUST_INDEX_SIZE
-32
-SET DEBUG_SYNC = 'RESET';
-connection default;
-disconnect con1;
-disconnect con2;
-disconnect con3;
-DROP TABLE t1;

mysql-test/suite/innodb/r/insert_into_empty.result

@@ -45,6 +45,10 @@ SET tx_read_only=1;
 BEGIN;
 INSERT INTO t2 VALUES(0);
 INSERT INTO t VALUES(0);
+ROLLBACK;
+BEGIN;
+INSERT INTO t2 VALUES(0);
+INSERT INTO t VALUES(0);
 COMMIT;
 INSERT INTO t VALUES(0);
 DROP TEMPORARY TABLE t,t2;

mysql-test/suite/innodb/t/innodb-change-buffer-recovery-master.opt

@@ -1 +0,0 @@
---innodb_buffer_pool_size=24M

mysql-test/suite/innodb/t/innodb-change-buffer-recovery.test

@@ -1,78 +0,0 @@
---echo #
---echo # Bug#69122 - INNODB DOESN'T REDO-LOG INSERT BUFFER MERGE
---echo #             OPERATION IF IT IS DONE IN-PLACE
---echo #
---source include/have_innodb.inc
-# innodb_change_buffering_debug option is debug only
---source include/have_debug.inc
-# Embedded server does not support crashing
---source include/not_embedded.inc
-# DBUG_SUICIDE() hangs under valgrind
---source include/not_valgrind.inc
-# This test is slow on buildbot.
---source include/big_test.inc
---source include/have_sequence.inc
-
-call mtr.add_suppression("InnoDB: innodb_read_only prevents crash recovery");
-call mtr.add_suppression("Plugin initialization aborted at srv0start\\.cc");
-call mtr.add_suppression("Plugin 'InnoDB'");
-FLUSH TABLES;
-
-CREATE TABLE t1(
-	a INT AUTO_INCREMENT PRIMARY KEY,
-	b CHAR(1),
-	c INT,
-	INDEX(b))
-ENGINE=InnoDB STATS_PERSISTENT=0;
-
---let $_server_id= `SELECT @@server_id`
---let $_expect_file_name= $MYSQLTEST_VARDIR/tmp/mysqld.$_server_id.expect
-
-# The flag innodb_change_buffering_debug is only available in debug builds.
-# It instructs InnoDB to try to evict pages from the buffer pool when
-# change buffering is possible, so that the change buffer will be used
-# whenever possible.
-SET GLOBAL innodb_change_buffering_debug = 1;
-SET GLOBAL innodb_change_buffering = all;
-let SEARCH_FILE = $MYSQLTEST_VARDIR/log/mysqld.1.err;
-
-# Create enough rows for the table, so that the change buffer will be
-# used for modifying the secondary index page. There must be multiple
-# index pages, because changes to the root page are never buffered.
-INSERT INTO t1 SELECT 0,'x',1 FROM seq_1_to_8192;
-
-BEGIN;
-SELECT b FROM t1 LIMIT 3;
-
-connect (con1,localhost,root,,);
-BEGIN;
-DELETE FROM t1 WHERE a=1;
-# This should be buffered, if innodb_change_buffering_debug = 1 is in effect.
-INSERT INTO t1 VALUES(1,'X',1);
-
-SET DEBUG_DBUG='+d,crash_after_log_ibuf_upd_inplace';
---exec echo "wait" > $_expect_file_name
---error 2013
-# This should force a change buffer merge
-SELECT b FROM t1 LIMIT 3;
-disconnect con1;
-connection default;
-let SEARCH_PATTERN=Wrote log record for ibuf update in place operation;
---source include/search_pattern_in_file.inc
-
---let $restart_parameters= --innodb-read-only
---source include/start_mysqld.inc
-CHECK TABLE t1;
---source include/shutdown_mysqld.inc
-let SEARCH_PATTERN=innodb_read_only prevents crash recovery;
---source include/search_pattern_in_file.inc
-
---let $restart_parameters= --innodb-force-recovery=5 --debug-dbug=d,crash_after_log_ibuf_upd_inplace
---source include/start_mysqld.inc
-SELECT * FROM t1 LIMIT 1;
-# Slow shutdown will not merge the changes due to innodb_force_recovery=5.
-SET GLOBAL innodb_fast_shutdown=0;
---let $restart_parameters=
---source include/restart_mysqld.inc
-CHECK TABLE t1;
-DROP TABLE t1;

mysql-test/suite/innodb/t/innodb_wl6326.opt

@@ -1 +0,0 @@
---innodb-sys-tablestats

mysql-test/suite/innodb/t/innodb_wl6326.test

@@ -1,519 +0,0 @@
-#
-# WL#6326: InnoDB: fix index->lock contention
-#
-
---source include/have_innodb.inc
---source include/have_debug.inc
---source include/have_debug_sync.inc
---source include/have_innodb_16k.inc
-
---disable_query_log
-SET @old_innodb_limit_optimistic_insert_debug = @@innodb_limit_optimistic_insert_debug;
-SET @old_innodb_adaptive_hash_index = @@innodb_adaptive_hash_index;
-SET @old_innodb_stats_persistent = @@innodb_stats_persistent;
---enable_query_log
-
-# Save the initial number of concurrent sessions
---source include/count_sessions.inc
-
-SET GLOBAL innodb_adaptive_hash_index = false;
-SET GLOBAL innodb_stats_persistent = false;
-
---connect (con1,localhost,root,,)
---connect (con2,localhost,root,,)
---connect (con3,localhost,root,,)
-
-CREATE TABLE t1 (
-  a00 CHAR(255) NOT NULL DEFAULT 'a',
-  a01 CHAR(255) NOT NULL DEFAULT 'a',
-  a02 CHAR(255) NOT NULL DEFAULT 'a',
-  a03 CHAR(255) NOT NULL DEFAULT 'a',
-  a04 CHAR(255) NOT NULL DEFAULT 'a',
-  a05 CHAR(255) NOT NULL DEFAULT 'a',
-  a06 CHAR(255) NOT NULL DEFAULT 'a',
-  b INT NOT NULL DEFAULT 0
-) ENGINE = InnoDB;
-
-ALTER TABLE t1 ADD PRIMARY KEY(
-  a00,
-  a01,
-  a02,
-  a03,
-  a04,
-  a05,
-  a06
-);
-
-#
-# Prepare primary key index tree to be used for this test.
-#
-
-# Only root (1)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-# Make the first records sparse artificially,
-# not to cause modify_tree by single node_ptr insert operation.
-# * (7 - 2) records should be larger than a half of the page size
-# * (7 + 2) records should be fit to the page
-# (above t1 definition is already adjusted)
-SET GLOBAL innodb_limit_optimistic_insert_debug = 7;
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('aa');
-INSERT INTO t1 (a00) VALUES ('ab');
-INSERT INTO t1 (a00) VALUES ('ac');
-INSERT INTO t1 (a00) VALUES ('ad');
-INSERT INTO t1 (a00) VALUES ('ae');
-INSERT INTO t1 (a00) VALUES ('af');
-INSERT INTO t1 (a00) VALUES ('ag');
-INSERT INTO t1 (a00) VALUES ('ah');
-COMMIT;
-# Raise root (1-2)
-# (aa,ad)
-# (aa,ab,ac)(ad,ae,af,ag,ah)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('ai');
-INSERT INTO t1 (a00) VALUES ('aj');
-INSERT INTO t1 (a00) VALUES ('ak');
-COMMIT;
-# Split leaf (1-3)
-# (aa,ad,ak)
-# (aa,ab,ac)(ad,ae,af,ag,ah,ai,aj)(ak)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('al');
-INSERT INTO t1 (a00) VALUES ('am');
-INSERT INTO t1 (a00) VALUES ('an');
-INSERT INTO t1 (a00) VALUES ('ao');
-INSERT INTO t1 (a00) VALUES ('ap');
-INSERT INTO t1 (a00) VALUES ('aq');
-INSERT INTO t1 (a00) VALUES ('ar');
-COMMIT;
-# Split leaf (1-4)
-# (aa,ad,ak,ar)
-# (aa,ab,ac)(ad,ae,af,ag,ah,ai,aj)(ak,al,am,an,ao,ap,aq)(ar)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('as');
-INSERT INTO t1 (a00) VALUES ('at');
-INSERT INTO t1 (a00) VALUES ('au');
-INSERT INTO t1 (a00) VALUES ('av');
-INSERT INTO t1 (a00) VALUES ('aw');
-INSERT INTO t1 (a00) VALUES ('ax');
-INSERT INTO t1 (a00) VALUES ('ay');
-COMMIT;
-# Split leaf (1-5)
-# (aa,ad,ak,ar,ay)
-# (aa,ab,ac)(ad,ae,af,ag,ah,ai,aj)(ak,al,am,an,ao,ap,aq)(ar,as,at,au,av,aw,ax)(ay)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('az');
-INSERT INTO t1 (a00) VALUES ('ba');
-INSERT INTO t1 (a00) VALUES ('bb');
-INSERT INTO t1 (a00) VALUES ('bc');
-INSERT INTO t1 (a00) VALUES ('bd');
-INSERT INTO t1 (a00) VALUES ('be');
-INSERT INTO t1 (a00) VALUES ('bf');
-COMMIT;
-# Split leaf (1-6)
-# (aa,ad,ak,ar,ay,bf)
-# (aa,ab,ac)(ad..)(ak..)(ar,as,at,au,av,aw,ax)(ay,az,ba,bb,bc,bd,be)(bf)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bg');
-INSERT INTO t1 (a00) VALUES ('bh');
-INSERT INTO t1 (a00) VALUES ('bi');
-INSERT INTO t1 (a00) VALUES ('bj');
-INSERT INTO t1 (a00) VALUES ('bk');
-INSERT INTO t1 (a00) VALUES ('bl');
-INSERT INTO t1 (a00) VALUES ('bm');
-COMMIT;
-# Split leaf (1-7)
-# (aa,ad,ak,ar,ay,bf,bm)
-# (aa,ab,ac)(ad..)(ak..)(ar..)(ay,az,ba,bb,bc,bd,be)(bf,bg,bh,bi,bj,bk,bl)(bm)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bn');
-INSERT INTO t1 (a00) VALUES ('bo');
-INSERT INTO t1 (a00) VALUES ('bp');
-INSERT INTO t1 (a00) VALUES ('bq');
-INSERT INTO t1 (a00) VALUES ('br');
-INSERT INTO t1 (a00) VALUES ('bs');
-INSERT INTO t1 (a00) VALUES ('bt');
-COMMIT;
-# Raise root (1-2-8)
-# (aa,ar)
-# (aa,ad,ak)            (ar,ay,bf,bm,bt)
-# (aa,ab,ac)(ad..)(ak..)(ar..)(ay..)(bf..)(bm..)(bt)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('bu');
-INSERT INTO t1 (a00) VALUES ('bv');
-INSERT INTO t1 (a00) VALUES ('bw');
-INSERT INTO t1 (a00) VALUES ('bx');
-INSERT INTO t1 (a00) VALUES ('by');
-INSERT INTO t1 (a00) VALUES ('bz');
-INSERT INTO t1 (a00) VALUES ('ca');
-
-INSERT INTO t1 (a00) VALUES ('cb');
-INSERT INTO t1 (a00) VALUES ('cc');
-INSERT INTO t1 (a00) VALUES ('cd');
-INSERT INTO t1 (a00) VALUES ('ce');
-INSERT INTO t1 (a00) VALUES ('cf');
-INSERT INTO t1 (a00) VALUES ('cg');
-INSERT INTO t1 (a00) VALUES ('ch');
-
-INSERT INTO t1 (a00) VALUES ('ci');
-INSERT INTO t1 (a00) VALUES ('cj');
-INSERT INTO t1 (a00) VALUES ('ck');
-INSERT INTO t1 (a00) VALUES ('cl');
-INSERT INTO t1 (a00) VALUES ('cm');
-INSERT INTO t1 (a00) VALUES ('cn');
-INSERT INTO t1 (a00) VALUES ('co');
-COMMIT;
-# Split also at level 1 (1-3-11)
-# (aa,ar,co)
-# (aa,ad,ak)            (ar,ay,bf,bm,bt,ca,ch)                    (co)
-# (aa,ab,ac)(ad..)(ak..)(ar..)(ay..)(bf..)(bm..)(bt..)(ca..)(ch..)(co)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('cp');
-INSERT INTO t1 (a00) VALUES ('cq');
-INSERT INTO t1 (a00) VALUES ('cr');
-INSERT INTO t1 (a00) VALUES ('cs');
-INSERT INTO t1 (a00) VALUES ('ct');
-INSERT INTO t1 (a00) VALUES ('cu');
-INSERT INTO t1 (a00) VALUES ('cv');
-
-INSERT INTO t1 (a00) VALUES ('cw');
-INSERT INTO t1 (a00) VALUES ('cx');
-INSERT INTO t1 (a00) VALUES ('cy');
-INSERT INTO t1 (a00) VALUES ('cz');
-INSERT INTO t1 (a00) VALUES ('da');
-INSERT INTO t1 (a00) VALUES ('db');
-INSERT INTO t1 (a00) VALUES ('dc');
-
-INSERT INTO t1 (a00) VALUES ('dd');
-INSERT INTO t1 (a00) VALUES ('de');
-INSERT INTO t1 (a00) VALUES ('df');
-INSERT INTO t1 (a00) VALUES ('dg');
-INSERT INTO t1 (a00) VALUES ('dh');
-INSERT INTO t1 (a00) VALUES ('di');
-INSERT INTO t1 (a00) VALUES ('dj');
-
-INSERT INTO t1 (a00) VALUES ('dk');
-INSERT INTO t1 (a00) VALUES ('dl');
-INSERT INTO t1 (a00) VALUES ('dm');
-INSERT INTO t1 (a00) VALUES ('dn');
-INSERT INTO t1 (a00) VALUES ('do');
-INSERT INTO t1 (a00) VALUES ('dp');
-INSERT INTO t1 (a00) VALUES ('dq');
-
-INSERT INTO t1 (a00) VALUES ('dr');
-INSERT INTO t1 (a00) VALUES ('ds');
-INSERT INTO t1 (a00) VALUES ('dt');
-INSERT INTO t1 (a00) VALUES ('du');
-INSERT INTO t1 (a00) VALUES ('dv');
-INSERT INTO t1 (a00) VALUES ('dw');
-INSERT INTO t1 (a00) VALUES ('dx');
-
-INSERT INTO t1 (a00) VALUES ('dy');
-INSERT INTO t1 (a00) VALUES ('dz');
-INSERT INTO t1 (a00) VALUES ('ea');
-INSERT INTO t1 (a00) VALUES ('eb');
-INSERT INTO t1 (a00) VALUES ('ec');
-INSERT INTO t1 (a00) VALUES ('ed');
-INSERT INTO t1 (a00) VALUES ('ee');
-
-INSERT INTO t1 (a00) VALUES ('ef');
-INSERT INTO t1 (a00) VALUES ('eg');
-INSERT INTO t1 (a00) VALUES ('eh');
-INSERT INTO t1 (a00) VALUES ('ei');
-INSERT INTO t1 (a00) VALUES ('ej');
-INSERT INTO t1 (a00) VALUES ('ek');
-INSERT INTO t1 (a00) VALUES ('el');
-COMMIT;
-# Split also at level 1 (1-4-18)
-# (aa,ar,co,el)
-# (aa,ad,ak)            (ar,ay,bf,bm,bt,ca,ch)                    (co,cv,dc,dj,dq,dx,ee)                    (el)
-# (aa,ab,ac)(ad..)(ak..)(ar..)(ay..)(bf..)(bm..)(bt..)(ca..)(ch..)(co..)(cv..)(dc..)(dj..)(dq..)(dx..)(ee..)(el)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-BEGIN;
-INSERT INTO t1 (a00) VALUES ('em');
-INSERT INTO t1 (a00) VALUES ('en');
-INSERT INTO t1 (a00) VALUES ('eo');
-INSERT INTO t1 (a00) VALUES ('ep');
-INSERT INTO t1 (a00) VALUES ('eq');
-INSERT INTO t1 (a00) VALUES ('er');
-INSERT INTO t1 (a00) VALUES ('es');
-
-INSERT INTO t1 (a00) VALUES ('et');
-INSERT INTO t1 (a00) VALUES ('eu');
-INSERT INTO t1 (a00) VALUES ('ev');
-INSERT INTO t1 (a00) VALUES ('ew');
-INSERT INTO t1 (a00) VALUES ('ex');
-INSERT INTO t1 (a00) VALUES ('ey');
-INSERT INTO t1 (a00) VALUES ('ez');
-
-INSERT INTO t1 (a00) VALUES ('fa');
-INSERT INTO t1 (a00) VALUES ('fb');
-INSERT INTO t1 (a00) VALUES ('fc');
-INSERT INTO t1 (a00) VALUES ('fd');
-INSERT INTO t1 (a00) VALUES ('fe');
-INSERT INTO t1 (a00) VALUES ('ff');
-INSERT INTO t1 (a00) VALUES ('fg');
-
-INSERT INTO t1 (a00) VALUES ('fh');
-INSERT INTO t1 (a00) VALUES ('fi');
-INSERT INTO t1 (a00) VALUES ('fj');
-INSERT INTO t1 (a00) VALUES ('fk');
-INSERT INTO t1 (a00) VALUES ('fl');
-INSERT INTO t1 (a00) VALUES ('fm');
-INSERT INTO t1 (a00) VALUES ('fn');
-
-INSERT INTO t1 (a00) VALUES ('fo');
-INSERT INTO t1 (a00) VALUES ('fp');
-INSERT INTO t1 (a00) VALUES ('fq');
-INSERT INTO t1 (a00) VALUES ('fr');
-INSERT INTO t1 (a00) VALUES ('fs');
-INSERT INTO t1 (a00) VALUES ('ft');
-INSERT INTO t1 (a00) VALUES ('fu');
-
-INSERT INTO t1 (a00) VALUES ('fv');
-INSERT INTO t1 (a00) VALUES ('fw');
-INSERT INTO t1 (a00) VALUES ('fx');
-INSERT INTO t1 (a00) VALUES ('fy');
-INSERT INTO t1 (a00) VALUES ('fz');
-INSERT INTO t1 (a00) VALUES ('ga');
-INSERT INTO t1 (a00) VALUES ('gb');
-
-INSERT INTO t1 (a00) VALUES ('gc');
-INSERT INTO t1 (a00) VALUES ('gd');
-INSERT INTO t1 (a00) VALUES ('ge');
-INSERT INTO t1 (a00) VALUES ('gf');
-INSERT INTO t1 (a00) VALUES ('gg');
-INSERT INTO t1 (a00) VALUES ('gh');
-COMMIT;
-
-# Current tree form (1-4-24)
-# (aa,ar,co,el)
-# (aa,ad,ak)            (ar,ay,bf,bm,bt,ca,ch)                    (co,cv,dc,dj,dq,dx,ee)                    (el..,gb)
-# (aa,ab,ac)(ad..)(ak..)(ar..)(ay..)(bf..)(bm..)(bt..)(ca..)(ch..)(co..)(cv..)(dc..)(dj..)(dq..)(dx..)(ee..)(el..)..(gb..)
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-# Insert the rest of records normally
-SET GLOBAL innodb_limit_optimistic_insert_debug = 0;
-
---echo # Test start
-
-# (1) Insert records to leaf page (bf..) and cause modify_page.
-#     - root page is not X latched
-#     - latched from level 1 page (ar,ay,bf,bm,bt,ca,ch)
-
-SET DEBUG_SYNC = 'RESET';
-
-# Filling leaf page (bf..)
-INSERT INTO t1 (a00) VALUES ('bfa');
-
---connection con1
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-# Cause modify_tree
---send
-INSERT INTO t1 (a00) VALUES ('bfb');
-
---connection con2
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-# Not blocked searches
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-SELECT a00,a01 FROM t1 WHERE a00 = 'aq';
-# "where a00 = 'co'" is blocked because searching from smaller ('co','a','a',..).
-SELECT a00,a01 FROM t1 WHERE a00 = 'cp';
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'ar';
-
---connection con3
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'cn';
-
---connection default
-# FIXME: These occasionally time out!
---disable_warnings
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
---enable_warnings
-SET DEBUG_SYNC = 'now SIGNAL continue';
-
---connection con1
---reap
-
---connection con2
---reap
-
---connection con3
---reap
-
---connection default
-
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-
-
-# (2) Insert records to leaf page (co..) and cause modify_page
-#     - root page is X latched, because node_ptr for 'co'
-#       is 1st record for (co,cv,dc,dj,dq,dx,ee)
-#
-# * ordinary pessimitic insert might be done by pessistic update
-#   and we should consider possibility node_ptr to be deleted.
-
-SET DEBUG_SYNC = 'RESET';
-
-# Filling leaf page (co..)
-INSERT INTO t1 (a00) VALUES ('coa');
-
---connection con1
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-# Cause modify_tree
---send
-INSERT INTO t1 (a00) VALUES ('cob');
-
---connection con2
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-# All searches are blocked because root page is X latched
-
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-
---connection con3
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-
---connection default
-# FIXME: These occasionally time out!
---disable_warnings
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
---enable_warnings
-SET DEBUG_SYNC = 'now SIGNAL continue';
-
---connection con1
---reap
-
---connection con2
---reap
-
---connection con3
---reap
-
---connection default
-
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-
-
-# (3) Insert records to rightmost leaf page (gb..) and cause modify_page
-#     - root page is not X latched, because node_ptr for 'gb' is the last record
-#       of the level 1 though it is last record in the page.
-#     - lathed from level 1 page (el..,gb)
-
-SET DEBUG_SYNC = 'RESET';
-
-# Filling leaf page (gb..)
-INSERT INTO t1 (a00) VALUES ('gba');
-
---connection con1
-SET DEBUG_SYNC = 'before_insert_pessimitic_row_ins_clust SIGNAL reached WAIT_FOR continue';
-# Cause modify_tree
---send
-INSERT INTO t1 (a00) VALUES ('gbb');
-
---connection con2
-SET DEBUG_SYNC = 'now WAIT_FOR reached';
-# Not blocked searches
-SELECT a00,a01 FROM t1 WHERE a00 = 'aa';
-SELECT a00,a01 FROM t1 WHERE a00 = 'ek';
-
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait1';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'el';
-
---connection con3
-SET DEBUG_SYNC = 'rw_s_lock_waiting SIGNAL lockwait2';
-# Blocked
---send
-SELECT a00,a01 FROM t1 WHERE a00 = 'gb';
-
---connection default
-# FIXME: These occasionally time out!
---disable_warnings
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait1 TIMEOUT 1';
-SET DEBUG_SYNC = 'now WAIT_FOR lockwait2 TIMEOUT 1';
---enable_warnings
-SET DEBUG_SYNC = 'now SIGNAL continue';
-
---connection con1
---reap
-
---connection con2
---reap
-
---connection con3
---reap
-
---connection default
-ANALYZE TABLE t1;
-SELECT CLUST_INDEX_SIZE FROM information_schema.INNODB_SYS_TABLESTATS WHERE NAME = 'test/t1';
-
-
-
-# Cleanup
-SET DEBUG_SYNC = 'RESET';
-
---connection default
---disconnect con1
---disconnect con2
---disconnect con3
-
-DROP TABLE t1;
-
---disable_query_log
-SET GLOBAL innodb_limit_optimistic_insert_debug = @old_innodb_limit_optimistic_insert_debug;
-SET GLOBAL innodb_adaptive_hash_index = @old_innodb_adaptive_hash_index;
-SET GLOBAL innodb_stats_persistent = @old_innodb_stats_persistent;
---enable_query_log
-
-# Wait till all disconnects are completed.
---source include/wait_until_count_sessions.inc

mysql-test/suite/innodb/t/insert_into_empty.test

@@ -51,6 +51,10 @@ SET tx_read_only=1;
 BEGIN;
 INSERT INTO t2 VALUES(0);
 INSERT INTO t VALUES(0);
+ROLLBACK;
+BEGIN;
+INSERT INTO t2 VALUES(0);
+INSERT INTO t VALUES(0);
 COMMIT;
 INSERT INTO t VALUES(0);
 

mysql-test/suite/innodb/t/undo_truncate.opt

@@ -1 +1,2 @@
 --innodb-buffer-pool-size=24M
+--innodb-immediate-scrub-data-uncompressed=ON

mysql-test/suite/innodb_gis/r/rtree_split.result

@@ -61,3 +61,15 @@ select count(*) from t1 where MBRWithin(t1.c2, @g1);
 count(*)
 57344
 drop table t1;
+#
+# MDEV-30400 Assertion height == btr_page_get_level ... on INSERT
+#
+CREATE TABLE t1 (c POINT NOT NULL,SPATIAL (c)) ENGINE=InnoDB;
+SET @save_limit=@@GLOBAL.innodb_limit_optimistic_insert_debug;
+SET GLOBAL innodb_limit_optimistic_insert_debug=2;
+BEGIN;
+INSERT INTO t1 SELECT POINTFROMTEXT ('POINT(0 0)') FROM seq_1_to_6;
+ROLLBACK;
+SET GLOBAL innodb_limit_optimistic_insert_debug=@save_limit;
+DROP TABLE t1;
+# End of 10.6 tests

mysql-test/suite/innodb_gis/t/rtree_split.test

@@ -73,3 +73,18 @@ select count(*) from t1 where MBRWithin(t1.c2, @g1);
 
 # Clean up.
 drop table t1;
+
+--echo #
+--echo # MDEV-30400 Assertion height == btr_page_get_level ... on INSERT
+--echo #
+
+CREATE TABLE t1 (c POINT NOT NULL,SPATIAL (c)) ENGINE=InnoDB;
+SET @save_limit=@@GLOBAL.innodb_limit_optimistic_insert_debug;
+SET GLOBAL innodb_limit_optimistic_insert_debug=2;
+BEGIN;
+INSERT INTO t1 SELECT POINTFROMTEXT ('POINT(0 0)') FROM seq_1_to_6;
+ROLLBACK;
+SET GLOBAL innodb_limit_optimistic_insert_debug=@save_limit;
+DROP TABLE t1;
+
+--echo # End of 10.6 tests

plugin/type_inet/mysql-test/type_inet/type_inet4_plugin.result

@@ -24,7 +24,7 @@ PLUGIN_TYPE	DATA TYPE
 PLUGIN_AUTHOR	MariaDB Corporation
 PLUGIN_DESCRIPTION	Data type INET4
 PLUGIN_LICENSE	GPL
-PLUGIN_MATURITY	Alpha
+PLUGIN_MATURITY	Gamma
 PLUGIN_AUTH_VERSION	1.0
 #
 # End of 10.10 tests

plugin/type_inet/plugin.cc

@@ -189,7 +189,7 @@ maria_declare_plugin(type_inet)
   NULL,                         // Status variables
   NULL,                         // System variables
   "1.0",                        // String version representation
-  MariaDB_PLUGIN_MATURITY_ALPHA // Maturity(see include/mysql/plugin.h)*/
+  MariaDB_PLUGIN_MATURITY_GAMMA // Maturity(see include/mysql/plugin.h)*/
 },
 {
   MariaDB_DATA_TYPE_PLUGIN,     // the plugin type (see include/mysql/plugin.h)

sql/service_wsrep.cc

@@ -238,7 +238,7 @@ extern "C" my_bool wsrep_thd_bf_abort(THD *bf_thd, THD *victim_thd,
     }
 
     victim_thd->wsrep_aborter= bf_thd->thread_id;
-    victim_thd->awake_no_mutex(KILL_QUERY);
+    victim_thd->awake_no_mutex(KILL_QUERY_HARD);
     mysql_mutex_unlock(&victim_thd->LOCK_thd_data);
   } else {
     WSREP_DEBUG("wsrep_thd_bf_abort skipped awake, signal %d", signal);
@@ -417,3 +417,23 @@ extern "C" void  wsrep_thd_set_PA_unsafe(THD *thd)
     WSREP_DEBUG("session does not have active transaction, can not mark as PA unsafe");
   }
 }
+
+extern "C" int wsrep_thd_append_table_key(MYSQL_THD thd,
+                                    const char* db,
+                                    const char* table,
+                                    enum Wsrep_service_key_type key_type)
+{
+  wsrep_key_arr_t key_arr = {0, 0};
+  int ret = wsrep_prepare_keys_for_isolation(thd, db, table, NULL, &key_arr);
+  ret = ret || wsrep_thd_append_key(thd, key_arr.keys,
+                                    (int)key_arr.keys_len, key_type);
+  wsrep_keys_free(&key_arr);
+  return ret;
+}
+
+extern "C" my_bool wsrep_thd_is_local_transaction(const THD *thd)
+{
+  return (wsrep_thd_is_local(thd) &&
+	  thd->wsrep_cs().transaction().active());
+}
+

sql/sp_head.cc

@@ -1520,7 +1520,7 @@ sp_head::execute(THD *thd, bool merge_da_on_success)
                                wsrep_current_error_status(thd));
           thd->wsrep_cs().reset_error();
           /* Reset also thd->killed if it has been set during BF abort. */
-          if (thd->killed == KILL_QUERY)
+          if (killed_mask_hard(thd->killed) == KILL_QUERY)
             thd->killed= NOT_KILLED;
           /* if failed transaction was not replayed, must return with error from here */
           if (!must_replay) err_status = 1;

sql/sql_plugin_services.inl

@@ -162,6 +162,8 @@ static struct wsrep_service_st wsrep_handler = {
   wsrep_thd_is_local,
   wsrep_thd_self_abort,
   wsrep_thd_append_key,
+  wsrep_thd_append_table_key,
+  wsrep_thd_is_local_transaction,
   wsrep_thd_client_state_str,
   wsrep_thd_client_mode_str,
   wsrep_thd_transaction_state_str,

sql/wsrep_dummy.cc

@@ -101,6 +101,12 @@ void wsrep_thd_self_abort(THD *)
 int wsrep_thd_append_key(THD *, const struct wsrep_key*, int, enum Wsrep_service_key_type)
 { return 0; }
 
+int wsrep_thd_append_table_key(THD *, const char*, const char*, enum Wsrep_service_key_type)
+{ return 0; }
+
+my_bool wsrep_thd_is_local_transaction(const THD*)
+{ return 0; }
+
 const char* wsrep_thd_client_state_str(const THD*)
 { return 0; }
 

storage/innobase/CMakeLists.txt

@@ -332,12 +332,14 @@ SET(INNOBASE_SOURCES
 	include/row0upd.inl
 	include/row0vers.h
 	include/rw_lock.h
+	include/small_vector.h
 	include/srv0mon.h
 	include/srv0mon.inl
 	include/srv0srv.h
 	include/srv0start.h
 	include/srw_lock.h
 	include/sux_lock.h
+	include/transactional_lock_guard.h
 	include/trx0i_s.h
 	include/trx0purge.h
 	include/trx0rec.h

storage/innobase/btr/btr0btr.cc

@@ -2,7 +2,7 @@
 
 Copyright (c) 1994, 2016, Oracle and/or its affiliates. All Rights Reserved.
 Copyright (c) 2012, Facebook Inc.
-Copyright (c) 2014, 2022, MariaDB Corporation.
+Copyright (c) 2014, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -460,6 +460,54 @@ btr_page_create(
   }
 }
 
+buf_block_t *
+mtr_t::get_already_latched(const page_id_t id, mtr_memo_type_t type) const
+{
+  ut_ad(is_active());
+  ut_ad(type == MTR_MEMO_PAGE_X_FIX || type == MTR_MEMO_PAGE_SX_FIX ||
+        type == MTR_MEMO_PAGE_S_FIX);
+  for (ulint i= 0; i < m_memo.size(); i++)
+  {
+    const mtr_memo_slot_t &slot= m_memo[i];
+    const auto slot_type= mtr_memo_type_t(slot.type & ~MTR_MEMO_MODIFY);
+    if (slot_type == MTR_MEMO_PAGE_X_FIX || slot_type == type)
+    {
+      buf_block_t *block= static_cast<buf_block_t*>(slot.object);
+      if (block->page.id() == id)
+        return block;
+    }
+  }
+  return nullptr;
+}
+
+/** Fetch an index root page that was already latched in the
+mini-transaction. */
+static buf_block_t *btr_get_latched_root(const dict_index_t &index, mtr_t *mtr)
+{
+  return mtr->get_already_latched(page_id_t{index.table->space_id, index.page},
+                                  MTR_MEMO_PAGE_SX_FIX);
+}
+
+/** Fetch an index page that should have been already latched in the
+mini-transaction. */
+static buf_block_t *
+btr_block_reget(mtr_t *mtr, const dict_index_t &index,
+                const page_id_t id, rw_lock_type_t rw_latch,
+                dberr_t *err)
+{
+  if (buf_block_t *block=
+      mtr->get_already_latched(id, mtr_memo_type_t(rw_latch)))
+  {
+    *err= DB_SUCCESS;
+    return block;
+  }
+
+#if 0 /* MDEV-29385 FIXME: Acquire the page latch upfront. */
+  ut_ad(mtr->memo_contains_flagged(&index.lock, MTR_MEMO_X_LOCK));
+#endif
+  return btr_block_get(index, id.page_no(), rw_latch, true, mtr, err);
+}
+
 /**************************************************************//**
 Allocates a new file page to be used in an ibuf tree. Takes the page from
 the free list of the tree, which must contain pages!
@@ -472,18 +520,16 @@ btr_page_alloc_for_ibuf(
 	mtr_t*		mtr,	/*!< in: mtr */
 	dberr_t*	err)	/*!< out: error code */
 {
-  buf_block_t *root= btr_root_block_get(index, RW_SX_LATCH, mtr, err);
+  buf_block_t *root= btr_get_latched_root(*index, mtr);
   if (UNIV_UNLIKELY(!root))
     return root;
-
   buf_block_t *new_block=
-    buf_page_get_gen(page_id_t(index->table->space_id,
+    buf_page_get_gen(page_id_t(IBUF_SPACE_ID,
                                mach_read_from_4(PAGE_HEADER +
                                                 PAGE_BTR_IBUF_FREE_LIST +
                                                 FLST_FIRST + FIL_ADDR_PAGE +
                                                 root->page.frame)),
-                     index->table->space->zip_size(), RW_X_LATCH, nullptr,
+                     0, RW_X_LATCH, nullptr, BUF_GET, mtr, err);
-                     BUF_GET, mtr, err);
   if (new_block)
     *err= flst_remove(root, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST, new_block,
                 PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST_NODE, mtr);
@@ -523,11 +569,11 @@ btr_page_alloc_low(
 #ifdef BTR_CUR_HASH_ADAPT
     ut_ad(!root->index || !root->index->freed());
 #endif
-    mtr->release_block_at_savepoint(savepoint, root);
+    mtr->rollback_to_savepoint(savepoint);
   }
   else
   {
-    mtr->u_lock_register(savepoint);
+    mtr->lock_register(savepoint, MTR_MEMO_PAGE_SX_FIX);
     root->page.lock.u_lock();
 #ifdef BTR_CUR_HASH_ADAPT
     btr_search_drop_page_hash_index(root, true);
@@ -579,15 +625,12 @@ btr_page_free_for_ibuf(
 	mtr_t*		mtr)	/*!< in: mtr */
 {
   ut_ad(mtr->memo_contains_flagged(block, MTR_MEMO_PAGE_X_FIX));
-
+  buf_block_t *root= btr_get_latched_root(*index, mtr);
-  dberr_t err;
+  dberr_t err=
-  if (buf_block_t *root= btr_root_block_get(index, RW_SX_LATCH, mtr, &err))
+    flst_add_first(root, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST,
-  {
-    err= flst_add_first(root, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST,
                    block, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST_NODE, mtr);
-    ut_d(if (err == DB_SUCCESS)
+  ut_d(if (err == DB_SUCCESS)
-           flst_validate(root, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST, mtr));
+         flst_validate(root, PAGE_HEADER + PAGE_BTR_IBUF_FREE_LIST, mtr));
-  }
   return err;
 }
 
@@ -637,11 +680,11 @@ dberr_t btr_page_free(dict_index_t* index, buf_block_t* block, mtr_t* mtr,
 #ifdef BTR_CUR_HASH_ADAPT
       ut_ad(!root->index || !root->index->freed());
 #endif
-      mtr->release_block_at_savepoint(savepoint, root);
+      mtr->rollback_to_savepoint(savepoint);
     }
     else
     {
-      mtr->u_lock_register(savepoint);
+      mtr->lock_register(savepoint, MTR_MEMO_PAGE_SX_FIX);
       root->page.lock.u_lock();
 #ifdef BTR_CUR_HASH_ADAPT
       btr_search_drop_page_hash_index(root, true);
@@ -712,35 +755,27 @@ btr_node_ptr_get_child(
 		mtr, err);
 }
 
-MY_ATTRIBUTE((nonnull(2,3,5), warn_unused_result))
+MY_ATTRIBUTE((nonnull(2,3,4), warn_unused_result))
 /************************************************************//**
 Returns the upper level node pointer to a page. It is assumed that mtr holds
 an sx-latch on the tree.
 @return rec_get_offsets() of the node pointer record */
 static
 rec_offs*
-btr_page_get_father_node_ptr_func(
+btr_page_get_father_node_ptr_for_validate(
-/*==============================*/
 	rec_offs*	offsets,/*!< in: work area for the return value */
 	mem_heap_t*	heap,	/*!< in: memory heap to use */
 	btr_cur_t*	cursor,	/*!< in: cursor pointing to user record,
 				out: cursor on node pointer record,
 				its page x-latched */
-	btr_latch_mode	latch_mode,/*!< in: BTR_CONT_MODIFY_TREE
-				or BTR_CONT_SEARCH_TREE */
 	mtr_t*		mtr)	/*!< in: mtr */
 {
-	ut_ad(latch_mode == BTR_CONT_MODIFY_TREE
-	      || latch_mode == BTR_CONT_SEARCH_TREE);
-
 	const uint32_t page_no = btr_cur_get_block(cursor)->page.id().page_no();
 	dict_index_t* index = btr_cur_get_index(cursor);
 	ut_ad(!dict_index_is_spatial(index));
 
-	ut_ad(srv_read_only_mode
+	ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
-	      || mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
+					 | MTR_MEMO_SX_LOCK));
-					    | MTR_MEMO_SX_LOCK));
-
 	ut_ad(dict_index_get_page(index) != page_no);
 
 	const auto level = btr_page_get_level(btr_cur_get_page(cursor));
@@ -752,12 +787,16 @@ btr_page_get_father_node_ptr_func(
 					dict_index_build_node_ptr(index,
 								  user_rec, 0,
 								  heap, level),
-					PAGE_CUR_LE, latch_mode,
+					RW_S_LATCH,
 					cursor, mtr) != DB_SUCCESS) {
 		return nullptr;
 	}
 
 	const rec_t* node_ptr = btr_cur_get_rec(cursor);
+#if 0 /* MDEV-29835 FIXME */
+	ut_ad(!btr_cur_get_block(cursor)->page.lock.not_recursive()
+	      || mtr->memo_contains(index->lock, MTR_MEMO_X_LOCK));
+#endif
 
 	offsets = rec_get_offsets(node_ptr, index, offsets, 0,
 				  ULINT_UNDEFINED, &heap);
@@ -769,13 +808,65 @@ btr_page_get_father_node_ptr_func(
 	return(offsets);
 }
 
-#define btr_page_get_father_node_ptr(of,heap,cur,mtr)			\
+MY_ATTRIBUTE((nonnull(2,3,4), warn_unused_result))
-	btr_page_get_father_node_ptr_func(				\
+/** Return the node pointer to a page.
-		of,heap,cur,BTR_CONT_MODIFY_TREE,mtr)
+@param offsets   work area for the return value
+@param heap      memory heap
+@param cursor    in: child page; out: node pointer to it
+@param mtr       mini-transaction
+@return rec_get_offsets() of the node pointer record
+@retval nullptr  if the parent page had not been latched in mtr */
+static rec_offs *btr_page_get_parent(rec_offs *offsets, mem_heap_t *heap,
+                                     btr_cur_t *cursor, mtr_t *mtr)
+{
+  const uint32_t page_no= cursor->block()->page.id().page_no();
+  const dict_index_t *index= cursor->index();
+  ut_ad(!index->is_spatial());
+  ut_ad(index->page != page_no);
 
-#define btr_page_get_father_node_ptr_for_validate(of,heap,cur,mtr)	\
+  uint32_t p= index->page;
-	btr_page_get_father_node_ptr_func(				\
+  auto level= btr_page_get_level(cursor->block()->page.frame);
-		of,heap,cur,BTR_CONT_SEARCH_TREE,mtr)
+  const dtuple_t *tuple=
+    dict_index_build_node_ptr(index, btr_cur_get_rec(cursor), 0, heap, level);
+  level++;
+
+  ulint i;
+  for (i= 0; i < mtr->get_savepoint(); i++)
+    if (buf_block_t *block= mtr->block_at_savepoint(i))
+      if (block->page.id().page_no() == p)
+      {
+        ut_ad(block->page.lock.have_u_or_x() ||
+              (!block->page.lock.have_s() && index->lock.have_x()));
+        ulint up_match= 0, low_match= 0;
+        cursor->page_cur.block= block;
+        if (page_cur_search_with_match(tuple, PAGE_CUR_LE, &up_match,
+                                       &low_match, &cursor->page_cur,
+                                       nullptr))
+          return nullptr;
+        offsets= rec_get_offsets(cursor->page_cur.rec, index, offsets, 0,
+                                 ULINT_UNDEFINED, &heap);
+        p= btr_node_ptr_get_child_page_no(cursor->page_cur.rec, offsets);
+        if (p != page_no)
+        {
+          if (btr_page_get_level(block->page.frame) == level)
+            return nullptr;
+          i= 0; // MDEV-29835 FIXME: require all pages to be latched in order!
+          continue;
+        }
+        ut_ad(block->page.lock.have_u_or_x());
+        if (block->page.lock.have_u_not_x())
+        {
+          /* btr_cur_t::search_leaf(BTR_MODIFY_TREE) only U-latches the
+          root page initially. */
+          ut_ad(block->page.id().page_no() == index->page);
+          block->page.lock.u_x_upgrade();
+          mtr->page_lock_upgrade(*block);
+        }
+        return offsets;
+      }
+
+  return nullptr;
+}
 
 /************************************************************//**
 Returns the upper level node pointer to a page. It is assumed that mtr holds
@@ -796,7 +887,7 @@ btr_page_get_father_block(
   if (UNIV_UNLIKELY(!rec))
     return nullptr;
   cursor->page_cur.rec= rec;
-  return btr_page_get_father_node_ptr(offsets, heap, cursor, mtr);
+  return btr_page_get_parent(offsets, heap, cursor, mtr);
 }
 
 /** Seek to the parent page of a B-tree page.
@@ -811,7 +902,7 @@ bool btr_page_get_father(mtr_t* mtr, btr_cur_t* cursor)
     return false;
   cursor->page_cur.rec= rec;
   mem_heap_t *heap= mem_heap_create(100);
-  const bool got= btr_page_get_father_node_ptr(nullptr, heap, cursor, mtr);
+  const bool got= btr_page_get_parent(nullptr, heap, cursor, mtr);
   mem_heap_free(heap);
   return got;
 }
@@ -1718,48 +1809,43 @@ void btr_set_instant(buf_block_t* root, const dict_index_t& index, mtr_t* mtr)
 /** Reset the table to the canonical format on ROLLBACK of instant ALTER TABLE.
 @param[in]      index   clustered index with instant ALTER TABLE
 @param[in]      all     whether to reset FIL_PAGE_TYPE as well
-@param[in,out]  mtr     mini-transaction
+@param[in,out]  mtr     mini-transaction */
-@return error code */
 ATTRIBUTE_COLD
-dberr_t btr_reset_instant(const dict_index_t &index, bool all, mtr_t *mtr)
+void btr_reset_instant(const dict_index_t &index, bool all, mtr_t *mtr)
 {
   ut_ad(!index.table->is_temporary());
   ut_ad(index.is_primary());
-  dberr_t err;
+  buf_block_t *root= btr_get_latched_root(index, mtr);
-  if (buf_block_t *root= btr_root_block_get(&index, RW_SX_LATCH, mtr, &err))
+  byte *page_type= root->page.frame + FIL_PAGE_TYPE;
+  if (all)
   {
-    byte *page_type= root->page.frame + FIL_PAGE_TYPE;
+    ut_ad(mach_read_from_2(page_type) == FIL_PAGE_TYPE_INSTANT ||
-    if (all)
+          mach_read_from_2(page_type) == FIL_PAGE_INDEX);
-    {
+    mtr->write<2,mtr_t::MAYBE_NOP>(*root, page_type, FIL_PAGE_INDEX);
-      ut_ad(mach_read_from_2(page_type) == FIL_PAGE_TYPE_INSTANT ||
+    byte *instant= PAGE_INSTANT + PAGE_HEADER + root->page.frame;
-            mach_read_from_2(page_type) == FIL_PAGE_INDEX);
+    mtr->write<2,mtr_t::MAYBE_NOP>(*root, instant,
-      mtr->write<2,mtr_t::MAYBE_NOP>(*root, page_type, FIL_PAGE_INDEX);
+                                   page_ptr_get_direction(instant + 1));
-      byte *instant= PAGE_INSTANT + PAGE_HEADER + root->page.frame;
-      mtr->write<2,mtr_t::MAYBE_NOP>(*root, instant,
-                                     page_ptr_get_direction(instant + 1));
-    }
-    else
-      ut_ad(mach_read_from_2(page_type) == FIL_PAGE_TYPE_INSTANT);
-    static const byte supremuminfimum[8 + 8] = "supremuminfimum";
-    uint16_t infimum, supremum;
-    if (page_is_comp(root->page.frame))
-    {
-      infimum= PAGE_NEW_INFIMUM;
-      supremum= PAGE_NEW_SUPREMUM;
-    }
-    else
-    {
-      infimum= PAGE_OLD_INFIMUM;
-      supremum= PAGE_OLD_SUPREMUM;
-    }
-    ut_ad(!memcmp(&root->page.frame[infimum], supremuminfimum + 8, 8) ==
-          !memcmp(&root->page.frame[supremum], supremuminfimum, 8));
-    mtr->memcpy<mtr_t::MAYBE_NOP>(*root, &root->page.frame[infimum],
-                                  supremuminfimum + 8, 8);
-    mtr->memcpy<mtr_t::MAYBE_NOP>(*root, &root->page.frame[supremum],
-                                  supremuminfimum, 8);
   }
-  return err;
+  else
+    ut_ad(mach_read_from_2(page_type) == FIL_PAGE_TYPE_INSTANT);
+  static const byte supremuminfimum[8 + 8] = "supremuminfimum";
+  uint16_t infimum, supremum;
+  if (page_is_comp(root->page.frame))
+  {
+    infimum= PAGE_NEW_INFIMUM;
+    supremum= PAGE_NEW_SUPREMUM;
+  }
+  else
+  {
+    infimum= PAGE_OLD_INFIMUM;
+    supremum= PAGE_OLD_SUPREMUM;
+  }
+  ut_ad(!memcmp(&root->page.frame[infimum], supremuminfimum + 8, 8) ==
+        !memcmp(&root->page.frame[supremum], supremuminfimum, 8));
+  mtr->memcpy<mtr_t::MAYBE_NOP>(*root, &root->page.frame[infimum],
+                                supremuminfimum + 8, 8);
+  mtr->memcpy<mtr_t::MAYBE_NOP>(*root, &root->page.frame[supremum],
+                                supremuminfimum, 8);
 }
 
 /*************************************************************//**
@@ -1856,11 +1942,6 @@ btr_root_raise_and_insert(
 	}
 
 	/* Copy the records from root to the new page one by one. */
-	dberr_t e;
-	if (!err) {
-		err = &e;
-	}
-
 	if (0
 #ifdef UNIV_ZIP_COPY
 	    || new_page_zip
@@ -2004,21 +2085,15 @@ btr_root_raise_and_insert(
 	page_cursor->block = new_block;
 	page_cursor->index = index;
 
-	if (tuple) {
+	ut_ad(dtuple_check_typed(tuple));
-		ut_ad(dtuple_check_typed(tuple));
+	/* Reposition the cursor to the child node */
-		/* Reposition the cursor to the child node */
+	ulint low_match = 0, up_match = 0;
-		ulint low_match = 0, up_match = 0;
 
-		if (page_cur_search_with_match(tuple, PAGE_CUR_LE,
+	if (page_cur_search_with_match(tuple, PAGE_CUR_LE,
-					       &up_match, &low_match,
+				       &up_match, &low_match,
-					       page_cursor, nullptr)) {
+				       page_cursor, nullptr)) {
-			if (err) {
+		*err = DB_CORRUPTION;
-				*err = DB_CORRUPTION;
+		return nullptr;
-			}
-			return nullptr;
-		}
-	} else {
-		page_cursor->rec = page_get_infimum_rec(new_block->page.frame);
 	}
 
 	/* Split the child and insert tuple */
@@ -2237,6 +2312,7 @@ func_exit:
 	return(rec);
 }
 
+#ifdef UNIV_DEBUG
 /*************************************************************//**
 Returns TRUE if the insert fits on the appropriate half-page with the
 chosen split_rec.
@@ -2335,6 +2411,7 @@ got_rec:
 
 	return(false);
 }
+#endif
 
 /*******************************************************//**
 Inserts a data tuple to a tree on a non-leaf level. It is assumed
@@ -2357,25 +2434,34 @@ btr_insert_on_non_leaf_level(
 	rtr_info_t	rtr_info;
 
 	ut_ad(level > 0);
-	auto mode = PAGE_CUR_LE;
-
-	if (index->is_spatial()) {
-		mode = PAGE_CUR_RTREE_INSERT;
-		/* For spatial index, initialize structures to track
-		its parents etc. */
-		rtr_init_rtr_info(&rtr_info, false, &cursor, index, false);
-
-		rtr_info_update_btr(&cursor, &rtr_info);
-	}
 
 	flags |= BTR_NO_LOCKING_FLAG | BTR_KEEP_SYS_FLAG
 		| BTR_NO_UNDO_LOG_FLAG;
 	cursor.page_cur.index = index;
 
-	dberr_t err = btr_cur_search_to_nth_level(level, tuple, mode,
+	dberr_t err;
-						  BTR_CONT_MODIFY_TREE,
+
+	if (index->is_spatial()) {
+		/* For spatial index, initialize structures to track
+		its parents etc. */
+		rtr_init_rtr_info(&rtr_info, false, &cursor, index, false);
+
+		rtr_info_update_btr(&cursor, &rtr_info);
+		err = rtr_search_to_nth_level(level, tuple,
+					      PAGE_CUR_RTREE_INSERT,
+					      BTR_CONT_MODIFY_TREE,
+					      &cursor, mtr);
+	} else {
+		err = btr_cur_search_to_nth_level(level, tuple, RW_X_LATCH,
 						  &cursor, mtr);
+	}
+
 	ut_ad(cursor.flag == BTR_CUR_BINARY);
+#if 0 /* MDEV-29835 FIXME */
+	ut_ad(!btr_cur_get_block(&cursor)->page.lock.not_recursive()
+	      || index->is_spatial()
+	      || mtr->memo_contains(index->lock, MTR_MEMO_X_LOCK));
+#endif
 
 	if (UNIV_LIKELY(err == DB_SUCCESS)) {
 		err = btr_cur_optimistic_insert(flags,
@@ -2471,6 +2557,7 @@ btr_attach_half_pages(
 	/* Get the level of the split pages */
 	const ulint level = btr_page_get_level(block->page.frame);
 	ut_ad(level == btr_page_get_level(new_block->page.frame));
+	page_id_t id{block->page.id()};
 
 	/* Get the previous and next pages of page */
 	const uint32_t prev_page_no = btr_page_get_prev(block->page.frame);
@@ -2478,12 +2565,32 @@ btr_attach_half_pages(
 
 	/* for consistency, both blocks should be locked, before change */
 	if (prev_page_no != FIL_NULL && direction == FSP_DOWN) {
-		prev_block = btr_block_get(*index, prev_page_no, RW_X_LATCH,
+		id.set_page_no(prev_page_no);
-					   !level, mtr);
+		prev_block = mtr->get_already_latched(id, MTR_MEMO_PAGE_X_FIX);
+#if 1 /* MDEV-29835 FIXME: acquire page latches upfront */
+		if (!prev_block) {
+# if 0 /* MDEV-29835 FIXME */
+			ut_ad(mtr->memo_contains(index->lock,
+						 MTR_MEMO_X_LOCK));
+# endif
+			prev_block = btr_block_get(*index, prev_page_no,
+						   RW_X_LATCH, !level, mtr);
+		}
+#endif
 	}
 	if (next_page_no != FIL_NULL && direction != FSP_DOWN) {
-		next_block = btr_block_get(*index, next_page_no, RW_X_LATCH,
+		id.set_page_no(next_page_no);
-					   !level, mtr);
+		next_block = mtr->get_already_latched(id, MTR_MEMO_PAGE_X_FIX);
+#if 1 /* MDEV-29835 FIXME: acquire page latches upfront */
+		if (!next_block) {
+# if 0 /* MDEV-29835 FIXME */
+			ut_ad(mtr->memo_contains(index->lock,
+						 MTR_MEMO_X_LOCK));
+# endif
+			next_block = btr_block_get(*index, next_page_no,
+						   RW_X_LATCH, !level, mtr);
+		}
+#endif
 	}
 
 	/* Build the node pointer (= node key and page address) for the upper
@@ -3020,6 +3127,7 @@ insert_empty:
 		return nullptr;
 	}
 
+#ifdef UNIV_DEBUG
 	/* If the split is made on the leaf level and the insert will fit
 	on the appropriate half-page, we may release the tree x-latch.
 	We can then move the records after releasing the tree latch,
@@ -3027,21 +3135,21 @@ insert_empty:
 	const bool insert_will_fit = !new_page_zip
 		&& btr_page_insert_fits(cursor, split_rec, offsets, tuple,
 					n_ext, heap);
+#endif
 	if (!split_rec && !insert_left) {
 		UT_DELETE_ARRAY(buf);
 		buf = NULL;
 	}
 
-	if (!srv_read_only_mode
+#if 0 // FIXME: this used to be a no-op, and may cause trouble if enabled
-	    && insert_will_fit
+	if (insert_will_fit
 	    && page_is_leaf(page)
 	    && !dict_index_is_online_ddl(cursor->index())) {
-#if 0 // FIXME: this used to be a no-op, and may cause trouble if enabled
 		mtr->release(cursor->index()->lock);
-#endif
 		/* NOTE: We cannot release root block latch here, because it
 		has segment header and already modified in most of cases.*/
 	}
+#endif
 
 	/* 5. Move then the records to the new page */
 	if (direction == FSP_DOWN) {
@@ -3273,52 +3381,58 @@ func_exit:
 dberr_t btr_level_list_remove(const buf_block_t& block,
                               const dict_index_t& index, mtr_t* mtr)
 {
-	ut_ad(mtr->memo_contains_flagged(&block, MTR_MEMO_PAGE_X_FIX));
+  ut_ad(mtr->memo_contains_flagged(&block, MTR_MEMO_PAGE_X_FIX));
-	ut_ad(block.zip_size() == index.table->space->zip_size());
+  ut_ad(block.zip_size() == index.table->space->zip_size());
-	ut_ad(index.table->space->id == block.page.id().space());
+  ut_ad(index.table->space->id == block.page.id().space());
-	/* Get the previous and next page numbers of page */
+  /* Get the previous and next page numbers of page */
+  const uint32_t prev_page_no= btr_page_get_prev(block.page.frame);
+  const uint32_t next_page_no= btr_page_get_next(block.page.frame);
+  page_id_t id{block.page.id()};
+  buf_block_t *prev= nullptr, *next;
+  dberr_t err;
 
-	const page_t* page = block.page.frame;
+  /* Update page links of the level */
-	const uint32_t	prev_page_no = btr_page_get_prev(page);
+  if (prev_page_no != FIL_NULL)
-	const uint32_t	next_page_no = btr_page_get_next(page);
+  {
+    id.set_page_no(prev_page_no);
+    prev= mtr->get_already_latched(id, MTR_MEMO_PAGE_X_FIX);
+#if 1 /* MDEV-29835 FIXME: acquire page latches upfront */
+    if (!prev)
+    {
+# if 0 /* MDEV-29835 FIXME */
+      ut_ad(mtr->memo_contains(index.lock, MTR_MEMO_X_LOCK));
+# endif
+      prev= btr_block_get(index, id.page_no(), RW_X_LATCH,
+                          page_is_leaf(block.page.frame), mtr, &err);
+      if (UNIV_UNLIKELY(!prev))
+        return err;
+    }
+#endif
+  }
 
-	/* Update page links of the level */
+  if (next_page_no != FIL_NULL)
-	dberr_t err;
+  {
+    id.set_page_no(next_page_no);
+    next= mtr->get_already_latched(id, MTR_MEMO_PAGE_X_FIX);
+#if 1 /* MDEV-29835 FIXME: acquire page latches upfront */
+    if (!next)
+    {
+# if 0 /* MDEV-29835 FIXME */
+      ut_ad(mtr->memo_contains(index.lock, MTR_MEMO_X_LOCK));
+# endif
+      next= btr_block_get(index, id.page_no(), RW_X_LATCH,
+                          page_is_leaf(block.page.frame), mtr, &err);
+      if (UNIV_UNLIKELY(!next))
+        return err;
+    }
+#endif
+    btr_page_set_prev(next, prev_page_no, mtr);
+  }
 
-	if (prev_page_no != FIL_NULL) {
+  if (prev)
-		buf_block_t*	prev_block = btr_block_get(
+    btr_page_set_next(prev, next_page_no, mtr);
-			index, prev_page_no, RW_X_LATCH, page_is_leaf(page),
-			mtr, &err);
-		if (UNIV_UNLIKELY(!prev_block)) {
-			return err;
-		}
-		if (UNIV_UNLIKELY(memcmp_aligned<4>(prev_block->page.frame
-						    + FIL_PAGE_NEXT,
-						    page + FIL_PAGE_OFFSET,
-						    4))) {
-			return DB_CORRUPTION;
-		}
-		btr_page_set_next(prev_block, next_page_no, mtr);
-	}
 
-	if (next_page_no != FIL_NULL) {
+  return DB_SUCCESS;
-		buf_block_t*	next_block = btr_block_get(
-			index, next_page_no, RW_X_LATCH, page_is_leaf(page),
-			mtr, &err);
-
-		if (UNIV_UNLIKELY(!next_block)) {
-			return err;
-		}
-		if (UNIV_UNLIKELY(memcmp_aligned<4>(next_block->page.frame
-						    + FIL_PAGE_PREV,
-						    page + FIL_PAGE_OFFSET,
-						    4))) {
-			return DB_CORRUPTION;
-		}
-		btr_page_set_prev(next_block, prev_page_no, mtr);
-	}
-
-	return DB_SUCCESS;
 }
 
 /*************************************************************//**
@@ -4168,23 +4282,30 @@ btr_discard_page(
 
 	const uint32_t left_page_no = btr_page_get_prev(block->page.frame);
 	const uint32_t right_page_no = btr_page_get_next(block->page.frame);
+	page_id_t merge_page_id{block->page.id()};
 
 	ut_d(bool parent_is_different = false);
+	dberr_t err;
 	if (left_page_no != FIL_NULL) {
-		dberr_t err;
+		merge_page_id.set_page_no(left_page_no);
-		merge_block = btr_block_get(*index, left_page_no, RW_X_LATCH,
+		merge_block = btr_block_reget(mtr, *index, merge_page_id,
-					    true, mtr, &err);
+					      RW_X_LATCH, &err);
 		if (UNIV_UNLIKELY(!merge_block)) {
 			return err;
 		}
-
+#if 0 /* MDEV-29385 FIXME: Acquire the page latch upfront. */
+		ut_ad(!memcmp_aligned<4>(merge_block->page.frame
+					 + FIL_PAGE_NEXT,
+					 block->page.frame + FIL_PAGE_OFFSET,
+					 4));
+#else
 		if (UNIV_UNLIKELY(memcmp_aligned<4>(merge_block->page.frame
 						    + FIL_PAGE_NEXT,
 						    block->page.frame
 						    + FIL_PAGE_OFFSET, 4))) {
 			return DB_CORRUPTION;
 		}
-
+#endif
 		ut_d(parent_is_different =
 			(page_rec_get_next(
 				page_get_infimum_rec(
@@ -4192,19 +4313,25 @@ btr_discard_page(
 						&parent_cursor)))
 			 == btr_cur_get_rec(&parent_cursor)));
 	} else if (right_page_no != FIL_NULL) {
-		dberr_t err;
+		merge_page_id.set_page_no(right_page_no);
-		merge_block = btr_block_get(*index, right_page_no, RW_X_LATCH,
+		merge_block = btr_block_reget(mtr, *index, merge_page_id,
-					    true, mtr, &err);
+                                              RW_X_LATCH, &err);
 		if (UNIV_UNLIKELY(!merge_block)) {
 			return err;
 		}
+#if 0 /* MDEV-29385 FIXME: Acquire the page latch upfront. */
+		ut_ad(!memcmp_aligned<4>(merge_block->page.frame
+					 + FIL_PAGE_PREV,
+					 block->page.frame + FIL_PAGE_OFFSET,
+					 4));
+#else
 		if (UNIV_UNLIKELY(memcmp_aligned<4>(merge_block->page.frame
 						    + FIL_PAGE_PREV,
 						    block->page.frame
 						    + FIL_PAGE_OFFSET, 4))) {
 			return DB_CORRUPTION;
 		}
-
+#endif
 		ut_d(parent_is_different = page_rec_is_supremum(
 			page_rec_get_next(btr_cur_get_rec(&parent_cursor))));
 		if (page_is_leaf(merge_block->page.frame)) {
@@ -4246,13 +4373,10 @@ btr_discard_page(
 	}
 
 #ifdef UNIV_ZIP_DEBUG
-	{
+	if (page_zip_des_t* merge_page_zip
-		page_zip_des_t*	merge_page_zip
+	    = buf_block_get_page_zip(merge_block));
-			= buf_block_get_page_zip(merge_block);
+		ut_a(page_zip_validate(merge_page_zip,
-		ut_a(!merge_page_zip
+				       merge_block->page.frame, index));
-		     || page_zip_validate(merge_page_zip,
-					  merge_block->page.frame, index));
-	}
 #endif /* UNIV_ZIP_DEBUG */
 
 	if (index->has_locking()) {
@@ -4271,7 +4395,7 @@ btr_discard_page(
 	}
 
 	/* Free the file page */
-	dberr_t err = btr_page_free(index, block, mtr);
+	err = btr_page_free(index, block, mtr);
 
 	if (err == DB_SUCCESS) {
 		/* btr_check_node_ptr() needs parent block latched.
@@ -4464,6 +4588,8 @@ btr_check_node_ptr(
 		offsets = btr_page_get_father_block(NULL, heap, mtr, &cursor);
 	}
 
+	ut_ad(offsets);
+
 	if (page_is_leaf(page)) {
 
 		goto func_exit;
@@ -4796,19 +4922,16 @@ btr_validate_level(
 	page_zip_des_t*	page_zip;
 #endif /* UNIV_ZIP_DEBUG */
 	ulint		savepoint = 0;
-	ulint		savepoint2 = 0;
 	uint32_t	parent_page_no = FIL_NULL;
 	uint32_t	parent_right_page_no = FIL_NULL;
 	bool		rightmost_child = false;
 
 	mtr.start();
 
-	if (!srv_read_only_mode) {
+	if (lockout) {
-		if (lockout) {
+		mtr_x_lock_index(index, &mtr);
-			mtr_x_lock_index(index, &mtr);
+	} else {
-		} else {
+		mtr_sx_lock_index(index, &mtr);
-			mtr_sx_lock_index(index, &mtr);
-		}
 	}
 
 	dberr_t err;
@@ -4856,7 +4979,6 @@ corrupted:
 		offsets = rec_get_offsets(node_ptr, index, offsets, 0,
 					  ULINT_UNDEFINED, &heap);
 
-		savepoint2 = mtr_set_savepoint(&mtr);
 		block = btr_node_ptr_get_child(node_ptr, index, offsets, &mtr,
 					       &err);
 		if (!block) {
@@ -4877,10 +4999,8 @@ corrupted:
 				/* To obey latch order of tree blocks,
 				we should release the right_block once to
 				obtain lock of the uncle block. */
-				mtr_release_block_at_savepoint(
+				mtr.release_last_page();
-					&mtr, savepoint2, block);
 
-				savepoint2 = mtr_set_savepoint(&mtr);
 				block = btr_block_get(*index, left_page_no,
 						      RW_SX_LATCH, false,
 						      &mtr, &err);
@@ -4908,12 +5028,10 @@ func_exit:
 	mem_heap_empty(heap);
 	offsets = offsets2 = NULL;
 
-	if (!srv_read_only_mode) {
+	if (lockout) {
-		if (lockout) {
+		mtr_x_lock_index(index, &mtr);
-			mtr_x_lock_index(index, &mtr);
+	} else {
-		} else {
+		mtr_sx_lock_index(index, &mtr);
-			mtr_sx_lock_index(index, &mtr);
-		}
 	}
 
 	page = block->page.frame;
@@ -4958,7 +5076,7 @@ func_exit:
 
 	if (right_page_no != FIL_NULL) {
 		const rec_t*	right_rec;
-		savepoint = mtr_set_savepoint(&mtr);
+		savepoint = mtr.get_savepoint();
 
 		right_block = btr_block_get(*index, right_page_no, RW_SX_LATCH,
 					    !level, &mtr, &err);
@@ -5152,8 +5270,10 @@ broken_links:
 				/* To obey latch order of tree blocks,
 				we should release the right_block once to
 				obtain lock of the uncle block. */
-				mtr_release_block_at_savepoint(
+				ut_ad(right_block
-					&mtr, savepoint, right_block);
+				      == mtr.at_savepoint(savepoint));
+				mtr.rollback_to_savepoint(savepoint,
+							  savepoint + 1);
 
 				if (parent_right_page_no != FIL_NULL) {
 					btr_block_get(*index,

storage/innobase/btr/btr0defragment.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (C) 2012, 2014 Facebook, Inc. All Rights Reserved.
-Copyright (C) 2014, 2022, MariaDB Corporation.
+Copyright (C) 2014, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -280,6 +280,70 @@ btr_defragment_calc_n_recs_for_size(
 	return n_recs;
 }
 
+MY_ATTRIBUTE((nonnull(2,3,4), warn_unused_result))
+/************************************************************//**
+Returns the upper level node pointer to a page. It is assumed that mtr holds
+an sx-latch on the tree.
+@return rec_get_offsets() of the node pointer record */
+static
+rec_offs*
+btr_page_search_father_node_ptr(
+	rec_offs*	offsets,/*!< in: work area for the return value */
+	mem_heap_t*	heap,	/*!< in: memory heap to use */
+	btr_cur_t*	cursor,	/*!< in: cursor pointing to user record,
+				out: cursor on node pointer record,
+				its page x-latched */
+	mtr_t*		mtr)	/*!< in: mtr */
+{
+	const uint32_t page_no = btr_cur_get_block(cursor)->page.id().page_no();
+	dict_index_t* index = btr_cur_get_index(cursor);
+	ut_ad(!index->is_spatial());
+
+	ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
+					 | MTR_MEMO_SX_LOCK));
+	ut_ad(dict_index_get_page(index) != page_no);
+
+	const auto level = btr_page_get_level(btr_cur_get_page(cursor));
+
+	const rec_t* user_rec = btr_cur_get_rec(cursor);
+	ut_a(page_rec_is_user_rec(user_rec));
+
+	if (btr_cur_search_to_nth_level(level + 1,
+					dict_index_build_node_ptr(index,
+								  user_rec, 0,
+								  heap, level),
+					RW_X_LATCH,
+					cursor, mtr) != DB_SUCCESS) {
+		return nullptr;
+	}
+
+	const rec_t* node_ptr = btr_cur_get_rec(cursor);
+	ut_ad(!btr_cur_get_block(cursor)->page.lock.not_recursive()
+	      || mtr->memo_contains(index->lock, MTR_MEMO_X_LOCK));
+
+	offsets = rec_get_offsets(node_ptr, index, offsets, 0,
+				  ULINT_UNDEFINED, &heap);
+
+	if (btr_node_ptr_get_child_page_no(node_ptr, offsets) != page_no) {
+		offsets = nullptr;
+	}
+
+	return(offsets);
+}
+
+static bool btr_page_search_father(mtr_t *mtr, btr_cur_t *cursor)
+{
+  rec_t *rec=
+    page_rec_get_next(page_get_infimum_rec(cursor->block()->page.frame));
+  if (UNIV_UNLIKELY(!rec))
+    return false;
+  cursor->page_cur.rec= rec;
+  mem_heap_t *heap= mem_heap_create(100);
+  const bool got= btr_page_search_father_node_ptr(nullptr, heap, cursor, mtr);
+  mem_heap_free(heap);
+  return got;
+}
+
 /*************************************************************//**
 Merge as many records from the from_block to the to_block. Delete
 the from_block if all records are successfully merged to to_block.
@@ -408,7 +472,7 @@ btr_defragment_merge_pages(
 	parent.page_cur.index = index;
 	parent.page_cur.block = from_block;
 
-	if (!btr_page_get_father(mtr, &parent)) {
+	if (!btr_page_search_father(mtr, &parent)) {
 		to_block = nullptr;
 	} else if (n_recs_to_move == n_recs) {
 		/* The whole page is merged with the previous page,
@@ -699,10 +763,9 @@ processed:
 		acquire index->lock X-latch.  This entitles us to
 		acquire page latches in any order for the index. */
 		mtr_x_lock_index(index, &mtr);
-		/* This will acquire index->lock U latch, which is allowed
-		when we are already holding the X-latch. */
 		if (buf_block_t *last_block =
-		    item->pcur->restore_position(BTR_MODIFY_TREE, &mtr)
+		    item->pcur->restore_position(
+			    BTR_PURGE_TREE_ALREADY_LATCHED, &mtr)
 		    == btr_pcur_t::CORRUPTED
 		    ? nullptr
 		    : btr_defragment_n_pages(btr_pcur_get_block(item->pcur),

storage/innobase/btr/btr0pcur.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, 2022, MariaDB Corporation.
+Copyright (c) 2016, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -212,24 +212,98 @@ btr_pcur_copy_stored_position(
 	pcur_receive->old_n_fields = pcur_donate->old_n_fields;
 }
 
+/** Optimistically latches the leaf page or pages requested.
+@param[in]	block		guessed buffer block
+@param[in,out]	pcur		cursor
+@param[in,out]	latch_mode	BTR_SEARCH_LEAF, ...
+@param[in,out]	mtr		mini-transaction
+@return true if success */
+TRANSACTIONAL_TARGET
+static bool btr_pcur_optimistic_latch_leaves(buf_block_t *block,
+                                             btr_pcur_t *pcur,
+                                             btr_latch_mode *latch_mode,
+                                             mtr_t *mtr)
+{
+  ut_ad(block->page.buf_fix_count());
+  ut_ad(block->page.in_file());
+  ut_ad(block->page.frame);
+
+  static_assert(BTR_SEARCH_PREV & BTR_SEARCH_LEAF, "");
+  static_assert(BTR_MODIFY_PREV & BTR_MODIFY_LEAF, "");
+  static_assert((BTR_SEARCH_PREV ^ BTR_MODIFY_PREV) ==
+                (RW_S_LATCH ^ RW_X_LATCH), "");
+
+  const rw_lock_type_t mode=
+    rw_lock_type_t(*latch_mode & (RW_X_LATCH | RW_S_LATCH));
+
+  switch (*latch_mode) {
+  default:
+    ut_ad(*latch_mode == BTR_SEARCH_LEAF || *latch_mode == BTR_MODIFY_LEAF);
+    return buf_page_optimistic_get(mode, block, pcur->modify_clock, mtr);
+  case BTR_SEARCH_PREV:
+  case BTR_MODIFY_PREV:
+    page_id_t id{0};
+    uint32_t left_page_no;
+    ulint zip_size;
+    buf_block_t *left_block= nullptr;
+    {
+      transactional_shared_lock_guard<block_lock> g{block->page.lock};
+      if (block->modify_clock != pcur->modify_clock)
+        return false;
+      id= block->page.id();
+      zip_size= block->zip_size();
+      left_page_no= btr_page_get_prev(block->page.frame);
+    }
+
+    if (left_page_no != FIL_NULL)
+    {
+      left_block=
+        buf_page_get_gen(page_id_t(id.space(), left_page_no), zip_size,
+                         mode, nullptr, BUF_GET_POSSIBLY_FREED, mtr);
+
+      if (left_block &&
+          btr_page_get_next(left_block->page.frame) != id.page_no())
+      {
+release_left_block:
+        mtr->release_last_page();
+        return false;
+      }
+    }
+
+    if (buf_page_optimistic_get(mode, block, pcur->modify_clock, mtr))
+    {
+      if (btr_page_get_prev(block->page.frame) == left_page_no)
+      {
+        /* block was already buffer-fixed while entering the function and
+        buf_page_optimistic_get() buffer-fixes it again. */
+        ut_ad(2 <= block->page.buf_fix_count());
+        *latch_mode= btr_latch_mode(mode);
+        return true;
+      }
+
+      mtr->release_last_page();
+    }
+
+    ut_ad(block->page.buf_fix_count());
+    if (left_block)
+      goto release_left_block;
+    return false;
+  }
+}
+
 /** Structure acts as functor to do the latching of leaf pages.
 It returns true if latching of leaf pages succeeded and false
 otherwise. */
 struct optimistic_latch_leaves
 {
   btr_pcur_t *const cursor;
-  btr_latch_mode *latch_mode;
+  btr_latch_mode *const latch_mode;
   mtr_t *const mtr;
 
-  optimistic_latch_leaves(btr_pcur_t *cursor, btr_latch_mode *latch_mode,
+  bool operator()(buf_block_t *hint) const
-                          mtr_t *mtr)
-    : cursor(cursor), latch_mode(latch_mode), mtr(mtr) {}
-
-  bool operator() (buf_block_t *hint) const
   {
-    return hint && btr_cur_optimistic_latch_leaves(
+    return hint &&
-             hint, cursor->modify_clock, latch_mode,
+      btr_pcur_optimistic_latch_leaves(hint, cursor, latch_mode, mtr);
-             btr_pcur_get_btr_cur(cursor), mtr);
   }
 };
 
@@ -246,8 +320,8 @@ record GREATER than the user record which was the predecessor of the
 supremum.
 (4) cursor was positioned before the first or after the last in an
 empty tree: restores to before first or after the last in the tree.
-@param restore_latch_mode BTR_SEARCH_LEAF, ...
+@param latch_mode  BTR_SEARCH_LEAF, ...
-@param mtr mtr
+@param mtr         mini-transaction
 @return btr_pcur_t::SAME_ALL cursor position on user rec and points on
 the record with the same field values as in the stored record,
 btr_pcur_t::SAME_UNIQ cursor position is on user rec and points on the
@@ -301,10 +375,9 @@ btr_pcur_t::restore_position(btr_latch_mode restore_latch_mode, mtr_t *mtr)
 	case BTR_SEARCH_PREV:
 	case BTR_MODIFY_PREV:
 		/* Try optimistic restoration. */
-
 		if (block_when_stored.run_with_hint(
-			optimistic_latch_leaves(this, &restore_latch_mode,
+			optimistic_latch_leaves{this, &restore_latch_mode,
-						mtr))) {
+						mtr})) {
 			pos_state = BTR_PCUR_IS_POSITIONED;
 			latch_mode = restore_latch_mode;
 
@@ -465,18 +538,9 @@ btr_pcur_move_to_next_page(
 		return DB_CORRUPTION;
 	}
 
-	ulint mode = cursor->latch_mode;
-	switch (mode) {
-	case BTR_SEARCH_TREE:
-		mode = BTR_SEARCH_LEAF;
-		break;
-	case BTR_MODIFY_TREE:
-		mode = BTR_MODIFY_LEAF;
-	}
-
 	dberr_t err;
 	buf_block_t* next_block = btr_block_get(
-		*cursor->index(), next_page_no, mode,
+		*cursor->index(), next_page_no, cursor->latch_mode & ~12,
 		page_is_leaf(page), mtr, &err);
 
 	if (UNIV_UNLIKELY(!next_block)) {
@@ -538,26 +602,42 @@ btr_pcur_move_backward_from_page(
 		return true;
 	}
 
-	buf_block_t* release_block = nullptr;
+	buf_block_t* block = btr_pcur_get_block(cursor);
 
-	if (!page_has_prev(btr_pcur_get_page(cursor))) {
+	if (page_has_prev(block->page.frame)) {
-	} else if (btr_pcur_is_before_first_on_page(cursor)) {
+		buf_block_t* left_block
-		release_block = btr_pcur_get_block(cursor);
+			= mtr->at_savepoint(mtr->get_savepoint() - 1);
-		page_cur_set_after_last(cursor->btr_cur.left_block,
+		const page_t* const left = left_block->page.frame;
-					btr_pcur_get_page_cur(cursor));
+		if (memcmp_aligned<4>(left + FIL_PAGE_NEXT,
-	} else {
+				      block->page.frame
-		/* The repositioned cursor did not end on an infimum
+				      + FIL_PAGE_OFFSET, 4)) {
-		record on a page. Cursor repositioning acquired a latch
+			/* This should be the right sibling page, or
-		also on the previous page, but we do not need the latch:
+			if there is none, the current block. */
-		release it. */
+			ut_ad(left_block == block
-		release_block = cursor->btr_cur.left_block;
+			      || !memcmp_aligned<4>(left + FIL_PAGE_PREV,
+						    block->page.frame
+						    + FIL_PAGE_OFFSET, 4));
+			/* The previous one must be the left sibling. */
+			left_block
+				= mtr->at_savepoint(mtr->get_savepoint() - 2);
+			ut_ad(!memcmp_aligned<4>(left_block->page.frame
+						 + FIL_PAGE_NEXT,
+						 block->page.frame
+						 + FIL_PAGE_OFFSET, 4));
+		}
+		if (btr_pcur_is_before_first_on_page(cursor)) {
+			page_cur_set_after_last(left_block,
+						&cursor->btr_cur.page_cur);
+			/* Release the right sibling. */
+		} else {
+			/* Release the left sibling. */
+			block = left_block;
+		}
+		mtr->release(*block);
 	}
 
 	cursor->latch_mode = latch_mode;
 	cursor->old_rec = nullptr;
-	if (release_block) {
-		mtr->release(*release_block);
-	}
 	return false;
 }
 

storage/innobase/btr/btr0sea.cc

@@ -1057,26 +1057,24 @@ btr_search_guess_on_hash(
 	index_id_t	index_id;
 
 	ut_ad(mtr->is_active());
-
+	ut_ad(index->is_btree() || index->is_ibuf());
-	if (!btr_search_enabled) {
-		return false;
-	}
-
-	ut_ad(!index->is_ibuf());
-	ut_ad(latch_mode == BTR_SEARCH_LEAF || latch_mode == BTR_MODIFY_LEAF);
-	compile_time_assert(ulint{BTR_SEARCH_LEAF} == ulint{RW_S_LATCH});
-	compile_time_assert(ulint{BTR_MODIFY_LEAF} == ulint{RW_X_LATCH});
-
-	/* Not supported for spatial index */
-	ut_ad(!dict_index_is_spatial(index));
 
 	/* Note that, for efficiency, the struct info may not be protected by
 	any latch here! */
 
-	if (info->n_hash_potential == 0) {
+	if (latch_mode > BTR_MODIFY_LEAF
+	    || !info->last_hash_succ || !info->n_hash_potential
+	    || (tuple->info_bits & REC_INFO_MIN_REC_FLAG)) {
 		return false;
 	}
 
+	ut_ad(index->is_btree());
+        ut_ad(!index->table->is_temporary());
+
+	ut_ad(latch_mode == BTR_SEARCH_LEAF || latch_mode == BTR_MODIFY_LEAF);
+	compile_time_assert(ulint{BTR_SEARCH_LEAF} == ulint{RW_S_LATCH});
+	compile_time_assert(ulint{BTR_MODIFY_LEAF} == ulint{RW_X_LATCH});
+
 	cursor->n_fields = info->n_fields;
 	cursor->n_bytes = info->n_bytes;
 

storage/innobase/buf/buf0buf.cc

@@ -2689,6 +2689,18 @@ re_evict:
 	    && mode != BUF_GET_IF_IN_POOL_OR_WATCH) {
 	} else if (!ibuf_debug || recv_recovery_is_on()) {
 	} else if (fil_space_t* space = fil_space_t::get(page_id.space())) {
+		for (ulint i = 0; i < mtr->get_savepoint(); i++) {
+			if (buf_block_t* b = mtr->block_at_savepoint(i)) {
+				if (b->page.oldest_modification() > 2
+				    && b->page.lock.have_any()) {
+					/* We are holding a dirty page latch
+					that would hang buf_flush_sync(). */
+					space->release();
+					goto re_evict_fail;
+				}
+			}
+		}
+
 		/* Try to evict the block from the buffer pool, to use the
 		insert buffer (change buffer) as much as possible. */
 
@@ -2730,9 +2742,9 @@ re_evict:
 
 		/* Failed to evict the page; change it directly */
 	}
+re_evict_fail:
 #endif /* UNIV_DEBUG || UNIV_IBUF_DEBUG */
 
-	ut_ad(state > buf_page_t::FREED);
 	if (UNIV_UNLIKELY(state < buf_page_t::UNFIXED)) {
 		goto ignore_block;
 	}
@@ -2788,8 +2800,7 @@ ibuf_merge_corrupted:
 		}
 
 		if (rw_latch == RW_X_LATCH) {
-			mtr->memo_push(block, MTR_MEMO_PAGE_X_FIX);
+			goto get_latch_valid;
-			goto got_latch;
 		} else {
 			block->page.lock.x_unlock();
 			goto get_latch;
@@ -2797,12 +2808,10 @@ ibuf_merge_corrupted:
 	} else {
 get_latch:
 		switch (rw_latch) {
-			mtr_memo_type_t fix_type;
 		case RW_NO_LATCH:
 			mtr->memo_push(block, MTR_MEMO_BUF_FIX);
 			return block;
 		case RW_S_LATCH:
-			fix_type = MTR_MEMO_PAGE_S_FIX;
 			block->page.lock.s_lock();
 			ut_ad(!block->page.is_read_fixed());
 			if (UNIV_UNLIKELY(block->page.id() != page_id)) {
@@ -2811,13 +2820,12 @@ get_latch:
 				goto page_id_mismatch;
 			}
 get_latch_valid:
-			mtr->memo_push(block, fix_type);
+			mtr->memo_push(block, mtr_memo_type_t(rw_latch));
 #ifdef BTR_CUR_HASH_ADAPT
 			btr_search_drop_page_hash_index(block, true);
 #endif /* BTR_CUR_HASH_ADAPT */
 			break;
 		case RW_SX_LATCH:
-			fix_type = MTR_MEMO_PAGE_SX_FIX;
 			block->page.lock.u_lock();
 			ut_ad(!block->page.is_io_fixed());
 			if (UNIV_UNLIKELY(block->page.id() != page_id)) {
@@ -2827,7 +2835,6 @@ get_latch_valid:
 			goto get_latch_valid;
 		default:
 			ut_ad(rw_latch == RW_X_LATCH);
-			fix_type = MTR_MEMO_PAGE_X_FIX;
 			if (block->page.lock.x_lock_upgraded()) {
 				ut_ad(block->page.id() == page_id);
 				block->unfix();
@@ -2840,7 +2847,6 @@ get_latch_valid:
 			goto get_latch_valid;
 		}
 
-got_latch:
 		ut_ad(page_id_t(page_get_space_id(block->page.frame),
 				page_get_page_no(block->page.frame))
 		      == page_id);
@@ -3029,8 +3035,7 @@ bool buf_page_optimistic_get(ulint rw_latch, buf_block_t *block,
     ut_ad(!block->page.is_read_fixed());
     block->page.set_accessed();
     buf_page_make_young_if_needed(&block->page);
-    mtr->memo_push(block, rw_latch == RW_S_LATCH
+    mtr->memo_push(block, mtr_memo_type_t(rw_latch));
-                   ? MTR_MEMO_PAGE_S_FIX : MTR_MEMO_PAGE_X_FIX);
   }
 
   ut_d(if (!(++buf_dbg_counter % 5771)) buf_pool.validate());

storage/innobase/dict/dict0crea.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -725,7 +725,7 @@ dict_build_field_def_step(
 }
 
 /***************************************************************//**
-Creates an index tree for the index if it is not a member of a cluster.
+Creates an index tree for the index.
 @return DB_SUCCESS or DB_OUT_OF_FILE_SPACE */
 static MY_ATTRIBUTE((nonnull, warn_unused_result))
 dberr_t
@@ -758,9 +758,8 @@ dict_create_index_tree_step(
 	pcur.btr_cur.page_cur.index =
 		UT_LIST_GET_FIRST(dict_sys.sys_indexes->indexes);
 
-	dberr_t err =
+	dberr_t err = btr_pcur_open(search_tuple, PAGE_CUR_L, BTR_MODIFY_LEAF,
-		btr_pcur_open(search_tuple, PAGE_CUR_L, BTR_MODIFY_LEAF,
+				    &pcur, &mtr);
-			      &pcur, 0, &mtr);
 
 	if (err != DB_SUCCESS) {
 func_exit:
@@ -771,10 +770,25 @@ func_exit:
 	btr_pcur_move_to_next_user_rec(&pcur, &mtr);
 
 	if (UNIV_UNLIKELY(btr_pcur_is_after_last_on_page(&pcur))) {
+corrupted:
 		err = DB_CORRUPTION;
 		goto func_exit;
 	}
 
+	ulint	len;
+	byte*	data = rec_get_nth_field_old(btr_pcur_get_rec(&pcur),
+					     DICT_FLD__SYS_INDEXES__ID,
+					     &len);
+	if (UNIV_UNLIKELY(len != 8 || mach_read_from_8(data) != index->id)) {
+		goto corrupted;
+	}
+
+	data = rec_get_nth_field_old(btr_pcur_get_rec(&pcur),
+				     DICT_FLD__SYS_INDEXES__PAGE_NO, &len);
+	if (len != 4) {
+		goto corrupted;
+	}
+
 	if (index->is_readable()) {
 		index->set_modified(mtr);
 
@@ -787,11 +801,6 @@ func_exit:
 				err = DB_OUT_OF_FILE_SPACE; );
 	}
 
-	ulint	len;
-	byte*	data = rec_get_nth_field_old(btr_pcur_get_rec(&pcur),
-					     DICT_FLD__SYS_INDEXES__PAGE_NO,
-					     &len);
-	ut_ad(len == 4);
 	mtr.write<4,mtr_t::MAYBE_NOP>(*btr_pcur_get_block(&pcur), data,
 				      node->page_no);
 	goto func_exit;

storage/innobase/dict/dict0dict.cc

@@ -2,7 +2,7 @@
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
 Copyright (c) 2012, Facebook Inc.
-Copyright (c) 2013, 2022, MariaDB Corporation.
+Copyright (c) 2013, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -4149,8 +4149,7 @@ void dict_set_corrupted(dict_index_t *index, const char *ctx)
 	dict_index_copy_types(tuple, sys_index, 2);
 	cursor.page_cur.index = sys_index;
 
-	if (btr_cur_search_to_nth_level(0, tuple, PAGE_CUR_LE,
+	if (cursor.search_leaf(tuple, PAGE_CUR_LE, BTR_MODIFY_LEAF, &mtr)
-					BTR_MODIFY_LEAF, &cursor, &mtr)
 	    != DB_SUCCESS) {
 		goto fail;
 	}
@@ -4225,8 +4224,7 @@ dict_index_set_merge_threshold(
 	dict_index_copy_types(tuple, sys_index, 2);
 	cursor.page_cur.index = sys_index;
 
-	if (btr_cur_search_to_nth_level(0, tuple, PAGE_CUR_GE,
+	if (cursor.search_leaf(tuple, PAGE_CUR_GE, BTR_MODIFY_LEAF, &mtr)
-					BTR_MODIFY_LEAF, &cursor, &mtr)
 	    != DB_SUCCESS) {
 		goto func_exit;
 	}

storage/innobase/dict/dict0load.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, 2022, MariaDB Corporation.
+Copyright (c) 2016, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1319,7 +1319,7 @@ static dberr_t dict_load_columns(dict_table_t *table, unsigned use_uncommitted,
 	dict_index_copy_types(&tuple, sys_index, 1);
 	pcur.btr_cur.page_cur.index = sys_index;
 
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		goto func_exit;
@@ -1450,7 +1450,7 @@ dict_load_virtual_col(dict_table_t *table, bool uncommitted, ulint nth_v_col)
 	dict_index_copy_types(&tuple, sys_virtual_index, 2);
 	pcur.btr_cur.page_cur.index = sys_virtual_index;
 
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		goto func_exit;
@@ -1690,8 +1690,7 @@ static dberr_t dict_load_fields(dict_index_t *index, bool uncommitted,
 	dict_index_copy_types(&tuple, sys_index, 1);
 	pcur.btr_cur.page_cur.index = sys_index;
 
-	dberr_t error = btr_pcur_open_on_user_rec(&tuple,
+	dberr_t error = btr_pcur_open_on_user_rec(&tuple, BTR_SEARCH_LEAF,
-						  PAGE_CUR_GE, BTR_SEARCH_LEAF,
 						  &pcur, &mtr);
 	if (error != DB_SUCCESS) {
 		goto func_exit;
@@ -1949,8 +1948,7 @@ dberr_t dict_load_indexes(dict_table_t *table, bool uncommitted,
 	dict_index_copy_types(&tuple, sys_index, 1);
 	pcur.btr_cur.page_cur.index = sys_index;
 
-	dberr_t error = btr_pcur_open_on_user_rec(&tuple,
+	dberr_t error = btr_pcur_open_on_user_rec(&tuple, BTR_SEARCH_LEAF,
-						  PAGE_CUR_GE, BTR_SEARCH_LEAF,
 						  &pcur, &mtr);
 	if (error != DB_SUCCESS) {
 		goto func_exit;
@@ -2347,7 +2345,7 @@ static dict_table_t *dict_load_table_one(const span<const char> &name,
 	bool uncommitted = false;
 reload:
 	mtr.start();
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 
 	if (err != DB_SUCCESS || !btr_pcur_is_on_user_rec(&pcur)) {
@@ -2605,8 +2603,7 @@ dict_load_table_on_id(
 
 	dict_table_t* table = nullptr;
 
-	if (btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	if (btr_pcur_open_on_user_rec(&tuple, BTR_SEARCH_LEAF, &pcur, &mtr)
-				      BTR_SEARCH_LEAF, &pcur, &mtr)
 	    == DB_SUCCESS
 	    && btr_pcur_is_on_user_rec(&pcur)) {
 		/*---------------------------------------------------*/
@@ -2712,7 +2709,7 @@ static dberr_t dict_load_foreign_cols(dict_foreign_t *foreign, trx_id_t trx_id)
 	pcur.btr_cur.page_cur.index = sys_index;
 
 	mem_heap_t* heap = nullptr;
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		goto func_exit;
@@ -2889,7 +2886,7 @@ dict_load_foreign(
 	mtr.start();
 
 	mem_heap_t* heap = nullptr;
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		goto err_exit;
@@ -3100,7 +3097,7 @@ start_load:
 	dict_index_copy_types(&tuple, sec_index, 1);
 	pcur.btr_cur.page_cur.index = sec_index;
 
-	dberr_t err = btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open_on_user_rec(&tuple,
 						BTR_SEARCH_LEAF, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		DBUG_RETURN(err);

storage/innobase/dict/dict0stats.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2009, 2019, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2015, 2022, MariaDB Corporation.
+Copyright (c) 2015, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1697,7 +1697,7 @@ static dberr_t page_cur_open_level(page_cur_t *page_cur, ulint level,
 static dberr_t btr_pcur_open_level(btr_pcur_t *pcur, ulint level, mtr_t *mtr,
                                    dict_index_t *index)
 {
-  pcur->latch_mode= BTR_SEARCH_TREE;
+  pcur->latch_mode= BTR_SEARCH_LEAF;
   pcur->search_mode= PAGE_CUR_G;
   pcur->pos_state= BTR_PCUR_IS_POSITIONED;
   pcur->btr_cur.page_cur.index= index;

storage/innobase/fil/fil0fil.cc

@@ -1429,7 +1429,7 @@ inline void mtr_t::log_file_op(mfile_type_t type, uint32_t space_id,
   ut_ad(strchr(path, '/'));
   ut_ad(!strcmp(&path[strlen(path) - strlen(DOT_IBD)], DOT_IBD));
 
-  flag_modified();
+  m_modifications= true;
   if (!is_logged())
     return;
   m_last= nullptr;

storage/innobase/fsp/fsp0fsp.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1995, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -122,15 +122,22 @@ MY_ATTRIBUTE((nonnull, warn_unused_result))
 static buf_block_t *fsp_get_header(const fil_space_t *space, mtr_t *mtr,
                                    dberr_t *err)
 {
-  buf_block_t *block= buf_page_get_gen(page_id_t(space->id, 0),
+  const page_id_t id{space->id, 0};
-                                       space->zip_size(), RW_SX_LATCH,
+  buf_block_t *block= mtr->get_already_latched(id, MTR_MEMO_PAGE_SX_FIX);
-                                       nullptr, BUF_GET_POSSIBLY_FREED,
+  if (block)
-                                       mtr, err);
+    *err= DB_SUCCESS;
-  if (block && space->id != mach_read_from_4(FSP_HEADER_OFFSET + FSP_SPACE_ID +
+  else
-                                             block->page.frame))
   {
-    *err= DB_CORRUPTION;
+    block= buf_page_get_gen(id, space->zip_size(), RW_SX_LATCH,
-    block= nullptr;
+                            nullptr, BUF_GET_POSSIBLY_FREED,
+                            mtr, err);
+    if (block &&
+        space->id != mach_read_from_4(FSP_HEADER_OFFSET + FSP_SPACE_ID +
+                                      block->page.frame))
+    {
+      *err= DB_CORRUPTION;
+      block= nullptr;
+    }
   }
   return block;
 }

storage/innobase/gis/gis0sea.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2016, 2018, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -44,7 +44,6 @@ Created 2014/01/16 Jimmy Yang
 static
 bool
 rtr_cur_restore_position(
-	ulint		latch_mode,	/*!< in: BTR_SEARCH_LEAF, ... */
 	btr_cur_t*	cursor,		/*!< in: detached persistent cursor */
 	ulint		level,		/*!< in: index level */
 	mtr_t*		mtr);		/*!< in: mtr */
@@ -74,6 +73,70 @@ rtr_adjust_parent_path(
 	}
 }
 
+/** Latches the leaf page or pages requested.
+@param[in]	block_savepoint	leaf page where the search converged
+@param[in]	latch_mode	BTR_SEARCH_LEAF, ...
+@param[in]	cursor		cursor
+@param[in]	mtr		mini-transaction */
+static void
+rtr_latch_leaves(
+	ulint			block_savepoint,
+	btr_latch_mode		latch_mode,
+	btr_cur_t*		cursor,
+	mtr_t*			mtr)
+{
+	compile_time_assert(int(MTR_MEMO_PAGE_S_FIX) == int(RW_S_LATCH));
+	compile_time_assert(int(MTR_MEMO_PAGE_X_FIX) == int(RW_X_LATCH));
+	compile_time_assert(int(MTR_MEMO_PAGE_SX_FIX) == int(RW_SX_LATCH));
+
+	buf_block_t* block = mtr->at_savepoint(block_savepoint);
+
+	ut_ad(block->page.id().space() == cursor->index()->table->space->id);
+	ut_ad(block->page.in_file());
+	ut_ad(mtr->memo_contains_flagged(&cursor->index()->lock,
+					 MTR_MEMO_S_LOCK
+					 | MTR_MEMO_X_LOCK
+					 | MTR_MEMO_SX_LOCK));
+
+	switch (latch_mode) {
+		uint32_t	left_page_no;
+		uint32_t	right_page_no;
+	default:
+		ut_ad(latch_mode == BTR_CONT_MODIFY_TREE);
+		break;
+	case BTR_MODIFY_TREE:
+		/* It is exclusive for other operations which calls
+		btr_page_set_prev() */
+		ut_ad(mtr->memo_contains_flagged(&cursor->index()->lock,
+						 MTR_MEMO_X_LOCK
+						 | MTR_MEMO_SX_LOCK));
+		/* x-latch also siblings from left to right */
+		left_page_no = btr_page_get_prev(block->page.frame);
+
+		if (left_page_no != FIL_NULL) {
+			btr_block_get(*cursor->index(), left_page_no, RW_X_LATCH,
+				      true, mtr);
+		}
+
+		mtr->upgrade_buffer_fix(block_savepoint, RW_X_LATCH);
+
+		right_page_no = btr_page_get_next(block->page.frame);
+
+		if (right_page_no != FIL_NULL) {
+			btr_block_get(*cursor->index(), right_page_no,
+				      RW_X_LATCH, true, mtr);
+		}
+		break;
+	case BTR_SEARCH_LEAF:
+	case BTR_MODIFY_LEAF:
+		rw_lock_type_t mode =
+			rw_lock_type_t(latch_mode & (RW_X_LATCH | RW_S_LATCH));
+		static_assert(int{RW_S_LATCH} == int{BTR_SEARCH_LEAF}, "");
+		static_assert(int{RW_X_LATCH} == int{BTR_MODIFY_LEAF}, "");
+		mtr->upgrade_buffer_fix(block_savepoint, mode);
+	}
+}
+
 /*************************************************************//**
 Find the next matching record. This function is used by search
 or record locating during index delete/update.
@@ -135,6 +198,7 @@ rtr_pcur_getnext_from_path(
 		&& (my_latch_mode | 4) == BTR_CONT_MODIFY_TREE;
 
 	if (!index_locked) {
+		ut_ad(mtr->is_empty());
 		mtr_s_lock_index(index, mtr);
 	} else {
 		ut_ad(mtr->memo_contains_flagged(&index->lock,
@@ -154,14 +218,12 @@ rtr_pcur_getnext_from_path(
 		node_seq_t	path_ssn;
 		const page_t*	page;
 		rw_lock_type_t	rw_latch;
-		ulint		tree_idx;
 
 		mysql_mutex_lock(&rtr_info->rtr_path_mutex);
 		next_rec = rtr_info->path->back();
 		rtr_info->path->pop_back();
 		level = next_rec.level;
 		path_ssn = next_rec.seq_no;
-		tree_idx = btr_cur->tree_height - level - 1;
 
 		/* Maintain the parent path info as well, if needed */
 		if (need_parent && !skip_parent && !new_split) {
@@ -223,37 +285,15 @@ rtr_pcur_getnext_from_path(
 			rw_latch = RW_X_LATCH;
 		}
 
-		/* Release previous locked blocks */
+		if (my_latch_mode == BTR_MODIFY_LEAF) {
-		if (my_latch_mode != BTR_SEARCH_LEAF) {
+			mtr->rollback_to_savepoint(1);
-			for (ulint idx = 0; idx < btr_cur->tree_height;
-			     idx++) {
-				if (rtr_info->tree_blocks[idx]) {
-					mtr_release_block_at_savepoint(
-						mtr,
-						rtr_info->tree_savepoints[idx],
-						rtr_info->tree_blocks[idx]);
-					rtr_info->tree_blocks[idx] = NULL;
-				}
-			}
-			for (ulint idx = RTR_MAX_LEVELS; idx < RTR_MAX_LEVELS + 3;
-			     idx++) {
-				if (rtr_info->tree_blocks[idx]) {
-					mtr_release_block_at_savepoint(
-						mtr,
-						rtr_info->tree_savepoints[idx],
-						rtr_info->tree_blocks[idx]);
-					rtr_info->tree_blocks[idx] = NULL;
-				}
-			}
 		}
 
-		/* set up savepoint to record any locks to be taken */
-		rtr_info->tree_savepoints[tree_idx] = mtr_set_savepoint(mtr);
-
 		ut_ad((my_latch_mode | 4) == BTR_CONT_MODIFY_TREE
 		      || !page_is_leaf(btr_cur_get_page(btr_cur))
 		      || !btr_cur->page_cur.block->page.lock.have_any());
 
+		const auto block_savepoint = mtr->get_savepoint();
 		block = buf_page_get_gen(
 			page_id_t(index->table->space_id,
 				  next_rec.page_no), zip_size,
@@ -264,8 +304,6 @@ rtr_pcur_getnext_from_path(
 			break;
 		}
 
-		rtr_info->tree_blocks[tree_idx] = block;
-
 		page = buf_block_get_frame(block);
 		page_ssn = page_get_ssn_id(page);
 
@@ -396,24 +434,23 @@ rtr_pcur_getnext_from_path(
 
 		if (found) {
 			if (level == target_level) {
-				page_cur_t*	r_cur;;
+				ut_ad(block
+				      == mtr->at_savepoint(block_savepoint));
 
 				if (my_latch_mode == BTR_MODIFY_TREE
 				    && level == 0) {
 					ut_ad(rw_latch == RW_NO_LATCH);
 
-					btr_cur_latch_leaves(
+					rtr_latch_leaves(
-						block,
+						block_savepoint,
 						BTR_MODIFY_TREE,
 						btr_cur, mtr);
 				}
 
-				r_cur = btr_cur_get_page_cur(btr_cur);
-
 				page_cur_position(
 					page_cur_get_rec(page_cursor),
 					page_cur_get_block(page_cursor),
-					r_cur);
+					btr_cur_get_page_cur(btr_cur));
 
 				btr_cur->low_match = level != 0 ?
 					DICT_INDEX_SPATIAL_NODEPTR_SIZE + 1
@@ -425,13 +462,7 @@ rtr_pcur_getnext_from_path(
 			last node just located */
 			skip_parent = true;
 		} else {
-			/* Release latch on the current page */
+			mtr->release_last_page();
-			ut_ad(rtr_info->tree_blocks[tree_idx]);
-
-			mtr_release_block_at_savepoint(
-				mtr, rtr_info->tree_savepoints[tree_idx],
-				rtr_info->tree_blocks[tree_idx]);
-			rtr_info->tree_blocks[tree_idx] = NULL;
 		}
 
 	} while (!rtr_info->path->empty());
@@ -509,50 +540,524 @@ static void rtr_compare_cursor_rec(const rec_t *rec, dict_index_t *index,
 }
 #endif
 
+TRANSACTIONAL_TARGET
+dberr_t rtr_search_to_nth_level(ulint level, const dtuple_t *tuple,
+                                page_cur_mode_t mode,
+                                btr_latch_mode latch_mode,
+                                btr_cur_t *cur, mtr_t *mtr)
+{
+  page_cur_mode_t page_mode;
+  page_cur_mode_t search_mode= PAGE_CUR_UNSUPP;
+
+  bool mbr_adj= false;
+  bool found= false;
+  dict_index_t *const index= cur->index();
+
+  mem_heap_t *heap= nullptr;
+  rec_offs offsets_[REC_OFFS_NORMAL_SIZE];
+  rec_offs *offsets= offsets_;
+  rec_offs_init(offsets_);
+  ut_ad(level == 0 || mode == PAGE_CUR_LE || RTREE_SEARCH_MODE(mode));
+  ut_ad(dict_index_check_search_tuple(index, tuple));
+  ut_ad(dtuple_check_typed(tuple));
+  ut_ad(index->is_spatial());
+  ut_ad(index->page != FIL_NULL);
+
+  MEM_UNDEFINED(&cur->up_match, sizeof cur->up_match);
+  MEM_UNDEFINED(&cur->up_bytes, sizeof cur->up_bytes);
+  MEM_UNDEFINED(&cur->low_match, sizeof cur->low_match);
+  MEM_UNDEFINED(&cur->low_bytes, sizeof cur->low_bytes);
+  ut_d(cur->up_match= ULINT_UNDEFINED);
+  ut_d(cur->low_match= ULINT_UNDEFINED);
+
+  const bool latch_by_caller= latch_mode & BTR_ALREADY_S_LATCHED;
+
+  ut_ad(!latch_by_caller
+        || mtr->memo_contains_flagged(&index->lock, MTR_MEMO_S_LOCK
+                                      | MTR_MEMO_SX_LOCK));
+  latch_mode= BTR_LATCH_MODE_WITHOUT_FLAGS(latch_mode);
+
+  ut_ad(!latch_by_caller || latch_mode == BTR_SEARCH_LEAF ||
+        latch_mode == BTR_MODIFY_LEAF);
+
+  cur->flag= BTR_CUR_BINARY;
+
+#ifndef BTR_CUR_ADAPT
+  buf_block_t *guess= nullptr;
+#else
+  btr_search_t *const info= btr_search_get_info(index);
+  buf_block_t *guess= info->root_guess;
+#endif
+
+  /* Store the position of the tree latch we push to mtr so that we
+     know how to release it when we have latched leaf node(s) */
+
+  const ulint savepoint= mtr->get_savepoint();
+
+  rw_lock_type_t upper_rw_latch, root_leaf_rw_latch= RW_NO_LATCH;
+
+  switch (latch_mode) {
+  case BTR_MODIFY_TREE:
+    mtr_x_lock_index(index, mtr);
+    upper_rw_latch= root_leaf_rw_latch= RW_X_LATCH;
+    break;
+  case BTR_CONT_MODIFY_TREE:
+    ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK |
+                                     MTR_MEMO_SX_LOCK));
+    upper_rw_latch= RW_X_LATCH;
+    break;
+  default:
+    ut_ad(latch_mode != BTR_MODIFY_PREV);
+    ut_ad(latch_mode != BTR_SEARCH_PREV);
+    if (!latch_by_caller)
+      mtr_s_lock_index(index, mtr);
+    upper_rw_latch= root_leaf_rw_latch= RW_S_LATCH;
+    if (latch_mode == BTR_MODIFY_LEAF)
+      root_leaf_rw_latch= RW_X_LATCH;
+  }
+
+  auto root_savepoint= mtr->get_savepoint();
+  const ulint zip_size= index->table->space->zip_size();
+
+  /* Start with the root page. */
+  page_id_t page_id(index->table->space_id, index->page);
+
+  ulint up_match= 0, up_bytes= 0, low_match= 0, low_bytes= 0;
+  ulint height= ULINT_UNDEFINED;
+
+  /* We use these modified search modes on non-leaf levels of the
+     B-tree. These let us end up in the right B-tree leaf. In that leaf
+     we use the original search mode. */
+
+  switch (mode) {
+  case PAGE_CUR_GE:
+    page_mode= PAGE_CUR_L;
+    break;
+  case PAGE_CUR_G:
+    page_mode= PAGE_CUR_LE;
+    break;
+  default:
+#ifdef PAGE_CUR_LE_OR_EXTENDS
+    ut_ad(mode == PAGE_CUR_L || mode == PAGE_CUR_LE
+          || RTREE_SEARCH_MODE(mode)
+          || mode == PAGE_CUR_LE_OR_EXTENDS);
+#else /* PAGE_CUR_LE_OR_EXTENDS */
+    ut_ad(mode == PAGE_CUR_L || mode == PAGE_CUR_LE
+          || RTREE_SEARCH_MODE(mode));
+#endif /* PAGE_CUR_LE_OR_EXTENDS */
+    page_mode= mode;
+    break;
+  }
+
+ search_loop:
+  auto buf_mode= BUF_GET;
+  ulint rw_latch= RW_NO_LATCH;
+
+  if (height)
+  {
+    /* We are about to fetch the root or a non-leaf page. */
+    if (latch_mode != BTR_MODIFY_TREE || height == level)
+      /* If doesn't have SX or X latch of index,
+         each page should be latched before reading. */
+      rw_latch= upper_rw_latch;
+  }
+  else if (latch_mode <= BTR_MODIFY_LEAF)
+    rw_latch= latch_mode;
+
+  dberr_t err;
+  auto block_savepoint= mtr->get_savepoint();
+  buf_block_t *block= buf_page_get_gen(page_id, zip_size, rw_latch, guess,
+                                       buf_mode, mtr, &err, false);
+  if (!block)
+  {
+    if (err == DB_DECRYPTION_FAILED)
+      btr_decryption_failed(*index);
+  func_exit:
+    if (UNIV_LIKELY_NULL(heap))
+      mem_heap_free(heap);
+
+    if (mbr_adj)
+      /* remember that we will need to adjust parent MBR */
+      cur->rtr_info->mbr_adj= true;
+
+    return err;
+  }
+
+  const page_t *page= buf_block_get_frame(block);
+#ifdef UNIV_ZIP_DEBUG
+  if (rw_latch != RW_NO_LATCH) {
+    const page_zip_des_t *page_zip= buf_block_get_page_zip(block);
+    ut_a(!page_zip || page_zip_validate(page_zip, page, index));
+  }
+#endif /* UNIV_ZIP_DEBUG */
+
+  ut_ad(fil_page_index_page_check(page));
+  ut_ad(index->id == btr_page_get_index_id(page));
+
+  if (height != ULINT_UNDEFINED);
+  else if (page_is_leaf(page) &&
+           rw_latch != RW_NO_LATCH && rw_latch != root_leaf_rw_latch)
+  {
+    /* The root page is also a leaf page (root_leaf).
+    We should reacquire the page, because the root page
+    is latched differently from leaf pages. */
+    ut_ad(root_leaf_rw_latch != RW_NO_LATCH);
+    ut_ad(rw_latch == RW_S_LATCH || rw_latch == RW_SX_LATCH);
+
+    ut_ad(block == mtr->at_savepoint(block_savepoint));
+    mtr->rollback_to_savepoint(block_savepoint);
+
+    upper_rw_latch= root_leaf_rw_latch;
+    goto search_loop;
+  }
+  else
+  {
+    /* We are in the root node */
+
+    height= btr_page_get_level(page);
+    cur->tree_height= height + 1;
+
+    ut_ad(cur->rtr_info);
+
+    /* If SSN in memory is not initialized, fetch it from root page */
+    if (!rtr_get_current_ssn_id(index))
+      /* FIXME: do this in dict_load_table_one() */
+      index->set_ssn(page_get_ssn_id(page) + 1);
+
+    /* Save the MBR */
+    cur->rtr_info->thr= cur->thr;
+    rtr_get_mbr_from_tuple(tuple, &cur->rtr_info->mbr);
+
+#ifdef BTR_CUR_ADAPT
+    info->root_guess= block;
+#endif
+  }
+
+  if (height == 0) {
+    if (rw_latch == RW_NO_LATCH)
+    {
+      ut_ad(block == mtr->at_savepoint(block_savepoint));
+      rtr_latch_leaves(block_savepoint, latch_mode, cur, mtr);
+    }
+
+    switch (latch_mode) {
+    case BTR_MODIFY_TREE:
+    case BTR_CONT_MODIFY_TREE:
+      break;
+    default:
+      if (!latch_by_caller)
+      {
+        /* Release the tree s-latch */
+        mtr->rollback_to_savepoint(savepoint,
+                                   savepoint + 1);
+        block_savepoint--;
+        root_savepoint--;
+      }
+      /* release upper blocks */
+      if (savepoint < block_savepoint)
+        mtr->rollback_to_savepoint(savepoint, block_savepoint);
+    }
+
+    page_mode= mode;
+  }
+
+  /* Remember the page search mode */
+  search_mode= page_mode;
+
+  /* Some adjustment on search mode, when the page search mode is
+  PAGE_CUR_RTREE_LOCATE or PAGE_CUR_RTREE_INSERT, as we are searching
+  with MBRs. When it is not the target level, we should search all
+  sub-trees that "CONTAIN" the search range/MBR. When it is at the
+  target level, the search becomes PAGE_CUR_LE */
+
+  if (page_mode == PAGE_CUR_RTREE_INSERT)
+  {
+    page_mode= (level == height)
+      ? PAGE_CUR_LE
+      : PAGE_CUR_RTREE_INSERT;
+
+    ut_ad(!page_is_leaf(page) || page_mode == PAGE_CUR_LE);
+  }
+  else if (page_mode == PAGE_CUR_RTREE_LOCATE && level == height)
+    page_mode= level == 0 ? PAGE_CUR_LE : PAGE_CUR_RTREE_GET_FATHER;
+
+  up_match= 0;
+  low_match= 0;
+
+  if (latch_mode == BTR_MODIFY_TREE || latch_mode == BTR_CONT_MODIFY_TREE)
+    /* Tree are locked, no need for Page Lock to protect the "path" */
+    cur->rtr_info->need_page_lock= false;
+
+  cur->page_cur.block= block;
+
+  if (page_mode >= PAGE_CUR_CONTAIN)
+  {
+    found= rtr_cur_search_with_match(block, index, tuple, page_mode,
+                                     &cur->page_cur, cur->rtr_info);
+
+    /* Need to use BTR_MODIFY_TREE to do the MBR adjustment */
+    if (search_mode == PAGE_CUR_RTREE_INSERT && cur->rtr_info->mbr_adj) {
+      static_assert(BTR_MODIFY_TREE == (8 | BTR_MODIFY_LEAF), "");
+
+      if (!(latch_mode & 8))
+        /* Parent MBR needs updated, should retry with BTR_MODIFY_TREE */
+        goto func_exit;
+
+      cur->rtr_info->mbr_adj= false;
+      mbr_adj= true;
+    }
+
+    if (found && page_mode == PAGE_CUR_RTREE_GET_FATHER)
+      cur->low_match= DICT_INDEX_SPATIAL_NODEPTR_SIZE + 1;
+  }
+  else
+  {
+    /* Search for complete index fields. */
+    up_bytes= low_bytes= 0;
+    if (page_cur_search_with_match(tuple, page_mode, &up_match,
+                                   &low_match, &cur->page_cur, nullptr)) {
+      err= DB_CORRUPTION;
+      goto func_exit;
+    }
+  }
+
+  /* If this is the desired level, leave the loop */
+
+  ut_ad(height == btr_page_get_level(btr_cur_get_page(cur)));
+
+  /* Add Predicate lock if it is serializable isolation
+     and only if it is in the search case */
+  if (mode >= PAGE_CUR_CONTAIN && mode != PAGE_CUR_RTREE_INSERT &&
+      mode != PAGE_CUR_RTREE_LOCATE && cur->rtr_info->need_prdt_lock)
+  {
+    lock_prdt_t prdt;
+
+    {
+      trx_t* trx= thr_get_trx(cur->thr);
+      TMLockTrxGuard g{TMLockTrxArgs(*trx)};
+      lock_init_prdt_from_mbr(&prdt, &cur->rtr_info->mbr, mode,
+                              trx->lock.lock_heap);
+    }
+
+    if (rw_latch == RW_NO_LATCH && height != 0)
+      block->page.lock.s_lock();
+
+    lock_prdt_lock(block, &prdt, index, LOCK_S, LOCK_PREDICATE, cur->thr);
+
+    if (rw_latch == RW_NO_LATCH && height != 0)
+      block->page.lock.s_unlock();
+  }
+
+  if (level != height)
+  {
+    ut_ad(height > 0);
+
+    height--;
+    guess= nullptr;
+
+    const rec_t *node_ptr= btr_cur_get_rec(cur);
+
+    offsets= rec_get_offsets(node_ptr, index, offsets, 0,
+                             ULINT_UNDEFINED, &heap);
+
+    if (page_rec_is_supremum(node_ptr))
+    {
+      cur->low_match= 0;
+      cur->up_match= 0;
+      goto func_exit;
+    }
+
+    /* If we are doing insertion or record locating,
+       remember the tree nodes we visited */
+    if (page_mode == PAGE_CUR_RTREE_INSERT ||
+        (search_mode == PAGE_CUR_RTREE_LOCATE &&
+         latch_mode != BTR_MODIFY_LEAF))
+    {
+      const bool add_latch= latch_mode == BTR_MODIFY_TREE &&
+        rw_latch == RW_NO_LATCH;
+
+      if (add_latch)
+      {
+        ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK |
+                                         MTR_MEMO_SX_LOCK));
+        block->page.lock.s_lock();
+      }
+
+      /* Store the parent cursor location */
+      ut_d(auto num_stored=)
+      rtr_store_parent_path(block, cur, latch_mode, height + 1, mtr);
+
+      if (page_mode == PAGE_CUR_RTREE_INSERT)
+      {
+        btr_pcur_t *r_cursor= rtr_get_parent_cursor(cur, height + 1, true);
+        /* If it is insertion, there should be only one parent for
+        each level traverse */
+        ut_ad(num_stored == 1);
+        node_ptr= btr_pcur_get_rec(r_cursor);
+      }
+
+      if (add_latch)
+        block->page.lock.s_unlock();
+
+      ut_ad(!page_rec_is_supremum(node_ptr));
+    }
+
+    ut_ad(page_mode == search_mode ||
+          (page_mode == PAGE_CUR_WITHIN &&
+           search_mode == PAGE_CUR_RTREE_LOCATE));
+    page_mode= search_mode;
+
+    if (height == level && latch_mode == BTR_MODIFY_TREE)
+    {
+      ut_ad(upper_rw_latch == RW_X_LATCH);
+      for (auto i= root_savepoint, n= mtr->get_savepoint(); i < n; i++)
+        mtr->upgrade_buffer_fix(i, RW_X_LATCH);
+    }
+
+    /* Go to the child node */
+    page_id.set_page_no(btr_node_ptr_get_child_page_no(node_ptr, offsets));
+
+    if (page_mode >= PAGE_CUR_CONTAIN && page_mode != PAGE_CUR_RTREE_INSERT)
+    {
+      rtr_node_path_t *path= cur->rtr_info->path;
+
+      if (found && !path->empty())
+      {
+        ut_ad(path->back().page_no == page_id.page_no());
+        path->pop_back();
+#ifdef UNIV_DEBUG
+        if (page_mode == PAGE_CUR_RTREE_LOCATE &&
+            latch_mode != BTR_MODIFY_LEAF)
+        {
+          btr_pcur_t* pcur= cur->rtr_info->parent_path->back().cursor;
+          rec_t *my_node_ptr= btr_pcur_get_rec(pcur);
+
+          offsets= rec_get_offsets(my_node_ptr, index, offsets,
+                                   0, ULINT_UNDEFINED, &heap);
+
+          ut_ad(page_id.page_no() ==
+                btr_node_ptr_get_child_page_no(my_node_ptr, offsets));
+        }
+#endif
+      }
+    }
+
+    goto search_loop;
+  }
+
+  if (level)
+  {
+    if (upper_rw_latch == RW_NO_LATCH)
+    {
+      ut_ad(latch_mode == BTR_CONT_MODIFY_TREE);
+      btr_block_get(*index, page_id.page_no(), RW_X_LATCH, false, mtr, &err);
+    }
+    else
+    {
+      ut_ad(mtr->memo_contains_flagged(block, upper_rw_latch));
+      ut_ad(!latch_by_caller);
+    }
+
+    if (page_mode <= PAGE_CUR_LE)
+    {
+      cur->low_match= low_match;
+      cur->up_match= up_match;
+    }
+  }
+  else
+  {
+    cur->low_match= low_match;
+    cur->low_bytes= low_bytes;
+    cur->up_match= up_match;
+    cur->up_bytes= up_bytes;
+
+    ut_ad(up_match != ULINT_UNDEFINED || mode != PAGE_CUR_GE);
+    ut_ad(up_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE);
+    ut_ad(low_match != ULINT_UNDEFINED || mode != PAGE_CUR_LE);
+  }
+
+  goto func_exit;
+}
+
+dberr_t rtr_search_leaf(btr_cur_t *cur, const dtuple_t *tuple,
+                        btr_latch_mode latch_mode,
+                        mtr_t *mtr, page_cur_mode_t mode)
+{
+  return rtr_search_to_nth_level(0, tuple, mode, latch_mode, cur, mtr);
+}
+
+/** Search for a spatial index leaf page record.
+@param pcur         cursor
+@param tuple       search tuple
+@param mode        search mode
+@param mtr         mini-transaction */
+dberr_t rtr_search_leaf(btr_pcur_t *pcur, const dtuple_t *tuple,
+                        page_cur_mode_t mode, mtr_t *mtr)
+{
+#ifdef UNIV_DEBUG
+  switch (mode) {
+  case PAGE_CUR_CONTAIN:
+  case PAGE_CUR_INTERSECT:
+  case PAGE_CUR_WITHIN:
+  case PAGE_CUR_DISJOINT:
+  case PAGE_CUR_MBR_EQUAL:
+    break;
+  default:
+    ut_ad("invalid mode" == 0);
+  }
+#endif
+  pcur->latch_mode= BTR_SEARCH_LEAF;
+  pcur->search_mode= mode;
+  pcur->pos_state= BTR_PCUR_IS_POSITIONED;
+  pcur->trx_if_known= nullptr;
+  return rtr_search_leaf(&pcur->btr_cur, tuple, BTR_SEARCH_LEAF, mtr, mode);
+}
+
 /**************************************************************//**
 Initializes and opens a persistent cursor to an index tree. It should be
-closed with btr_pcur_close. Mainly called by row_search_index_entry() */
+closed with btr_pcur_close. */
-bool
+bool rtr_search(
-rtr_pcur_open(
-	dict_index_t*	index,	/*!< in: index */
 	const dtuple_t*	tuple,	/*!< in: tuple on which search done */
-	btr_latch_mode	latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */
+	btr_latch_mode	latch_mode,/*!< in: BTR_MODIFY_LEAF, ... */
 	btr_pcur_t*	cursor, /*!< in: memory buffer for persistent cursor */
 	mtr_t*		mtr)	/*!< in: mtr */
 {
 	static_assert(BTR_MODIFY_TREE == (8 | BTR_MODIFY_LEAF), "");
 	ut_ad(latch_mode & BTR_MODIFY_LEAF);
+	ut_ad(!(latch_mode & BTR_ALREADY_S_LATCHED));
+	ut_ad(mtr->is_empty());
 
 	/* Initialize the cursor */
 
 	btr_pcur_init(cursor);
 
 	cursor->latch_mode = BTR_LATCH_MODE_WITHOUT_FLAGS(latch_mode);
-	cursor->search_mode =  PAGE_CUR_RTREE_LOCATE;
+	cursor->search_mode = PAGE_CUR_RTREE_LOCATE;
-	cursor->trx_if_known = NULL;
+	cursor->trx_if_known = nullptr;
+
+	if (latch_mode & 8) {
+		mtr_x_lock_index(cursor->index(), mtr);
+	} else {
+		latch_mode
+			= btr_latch_mode(latch_mode | BTR_ALREADY_S_LATCHED);
+		mtr_sx_lock_index(cursor->index(), mtr);
+	}
 
 	/* Search with the tree cursor */
 
 	btr_cur_t* btr_cursor = btr_pcur_get_btr_cur(cursor);
-	btr_cursor->page_cur.index = index;
 
-	btr_cursor->rtr_info = rtr_create_rtr_info(false, false,
+	btr_cursor->rtr_info
-						   btr_cursor, index);
+		= rtr_create_rtr_info(false, false,
+				      btr_cursor, cursor->index());
 
-	/* Purge will SX lock the tree instead of take Page Locks */
 	if (btr_cursor->thr) {
 		btr_cursor->rtr_info->need_page_lock = true;
 		btr_cursor->rtr_info->thr = btr_cursor->thr;
 	}
 
-	if ((latch_mode & 8) && index->lock.have_u_not_x()) {
+	if (rtr_search_leaf(btr_cursor, tuple, latch_mode, mtr)
-		index->lock.u_x_upgrade(SRW_LOCK_CALL);
+	    != DB_SUCCESS) {
-		mtr->lock_upgrade(index->lock);
-	}
-
-	if (btr_cur_search_to_nth_level(0, tuple, PAGE_CUR_RTREE_LOCATE,
-                                        latch_mode,
-					btr_cursor, mtr) != DB_SUCCESS) {
 		return true;
 	}
 
@@ -560,7 +1065,8 @@ rtr_pcur_open(
 
 	const rec_t* rec = btr_pcur_get_rec(cursor);
 
-	const bool d= rec_get_deleted_flag(rec, index->table->not_redundant());
+	const bool d= rec_get_deleted_flag(
+		rec, cursor->index()->table->not_redundant());
 
 	if (page_rec_is_infimum(rec)
 	    || btr_pcur_get_low_match(cursor) != dtuple_get_n_fields(tuple)
@@ -571,26 +1077,12 @@ rtr_pcur_open(
 			btr_cursor->rtr_info->fd_del = true;
 			btr_cursor->low_match = 0;
 		}
-		/* Did not find matched row in first dive. Release
-		latched block if any before search more pages */
-		if (!(latch_mode & 8)) {
-			ulint		tree_idx = btr_cursor->tree_height - 1;
-			rtr_info_t*	rtr_info = btr_cursor->rtr_info;
 
-			if (rtr_info->tree_blocks[tree_idx]) {
+		mtr->rollback_to_savepoint(1);
-				mtr_release_block_at_savepoint(
-					mtr,
-					rtr_info->tree_savepoints[tree_idx],
-					rtr_info->tree_blocks[tree_idx]);
-				rtr_info->tree_blocks[tree_idx] = NULL;
-			}
-		}
 
 		if (!rtr_pcur_getnext_from_path(tuple, PAGE_CUR_RTREE_LOCATE,
 						btr_cursor, 0, latch_mode,
-						latch_mode
+						true, mtr)) {
-						& (8 | BTR_ALREADY_S_LATCHED),
-						mtr)) {
 			return true;
 		}
 
@@ -598,6 +1090,10 @@ rtr_pcur_open(
 		      == dtuple_get_n_fields(tuple));
 	}
 
+	if (!(latch_mode & 8)) {
+		mtr->rollback_to_savepoint(0, 1);
+	}
+
 	return false;
 }
 
@@ -641,8 +1137,7 @@ static const rec_t* rtr_get_father_node(
 	if (sea_cur && sea_cur->tree_height > level) {
 		ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
 						 | MTR_MEMO_SX_LOCK));
-		if (rtr_cur_restore_position(BTR_CONT_MODIFY_TREE, sea_cur,
+		if (rtr_cur_restore_position(sea_cur, level, mtr)) {
-					     level, mtr)) {
 			btr_pcur_t*	r_cursor = rtr_get_parent_cursor(
 				sea_cur, level, false);
 
@@ -668,9 +1163,8 @@ static const rec_t* rtr_get_father_node(
 
 	btr_cur->rtr_info = rtr_create_rtr_info(false, false, btr_cur, index);
 
-	if (btr_cur_search_to_nth_level(level, tuple,
+	if (rtr_search_to_nth_level(level, tuple, PAGE_CUR_RTREE_LOCATE,
-					PAGE_CUR_RTREE_LOCATE,
+				    BTR_CONT_MODIFY_TREE, btr_cur, mtr)
-					BTR_CONT_MODIFY_TREE, btr_cur, mtr)
 	    != DB_SUCCESS) {
 	} else if (sea_cur && sea_cur->tree_height == level) {
 		rec = btr_cur_get_rec(btr_cur);
@@ -729,9 +1223,8 @@ rtr_page_get_father_node_ptr(
 	page_no = btr_cur_get_block(cursor)->page.id().page_no();
 	index = btr_cur_get_index(cursor);
 
-	ut_ad(srv_read_only_mode
+	ut_ad(mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
-	      || mtr->memo_contains_flagged(&index->lock, MTR_MEMO_X_LOCK
+					 | MTR_MEMO_SX_LOCK));
-					    | MTR_MEMO_SX_LOCK));
 
 	ut_ad(dict_index_get_page(index) != page_no);
 
@@ -879,32 +1372,10 @@ rtr_init_rtr_info(
 
 	if (!reinit) {
 		/* Reset all members. */
-		rtr_info->path = NULL;
+		memset(rtr_info, 0, sizeof *rtr_info);
-		rtr_info->parent_path = NULL;
+		static_assert(PAGE_CUR_UNSUPP == 0, "compatibility");
-		rtr_info->matches = NULL;
-
 		mysql_mutex_init(rtr_path_mutex_key, &rtr_info->rtr_path_mutex,
 				 nullptr);
-
-		memset(rtr_info->tree_blocks, 0x0,
-		       sizeof(rtr_info->tree_blocks));
-		memset(rtr_info->tree_savepoints, 0x0,
-		       sizeof(rtr_info->tree_savepoints));
-		rtr_info->mbr.xmin = 0.0;
-		rtr_info->mbr.xmax = 0.0;
-		rtr_info->mbr.ymin = 0.0;
-		rtr_info->mbr.ymax = 0.0;
-		rtr_info->thr = NULL;
-		rtr_info->heap = NULL;
-		rtr_info->cursor = NULL;
-		rtr_info->index = NULL;
-		rtr_info->need_prdt_lock = false;
-		rtr_info->need_page_lock = false;
-		rtr_info->allocated = false;
-		rtr_info->mbr_adj = false;
-		rtr_info->fd_del = false;
-		rtr_info->search_tuple = NULL;
-		rtr_info->search_mode = PAGE_CUR_UNSUPP;
 	}
 
 	ut_ad(!rtr_info->matches || rtr_info->matches->matched_recs->empty());
@@ -1130,7 +1601,6 @@ struct optimistic_get
 static
 bool
 rtr_cur_restore_position(
-	ulint		latch_mode,	/*!< in: BTR_SEARCH_LEAF, ... */
 	btr_cur_t*	btr_cur,	/*!< in: detached persistent cursor */
 	ulint		level,		/*!< in: index level */
 	mtr_t*		mtr)		/*!< in: mtr */
@@ -1158,8 +1628,6 @@ rtr_cur_restore_position(
 		r_cursor->modify_clock = 100;
 	);
 
-	ut_ad(latch_mode == BTR_CONT_MODIFY_TREE);
-
 	if (r_cursor->block_when_stored.run_with_hint(
 		optimistic_get(r_cursor, mtr))) {
 		ut_ad(r_cursor->pos_state == BTR_PCUR_IS_POSITIONED);

storage/innobase/handler/ha_innodb.cc

@@ -1525,8 +1525,7 @@ static void innodb_drop_database(handlerton*, char *path)
     mtr_t mtr;
     mtr.start();
     pcur.btr_cur.page_cur.index = sys_index;
-    err= btr_pcur_open_on_user_rec(&tuple, PAGE_CUR_GE,
+    err= btr_pcur_open_on_user_rec(&tuple, BTR_SEARCH_LEAF, &pcur, &mtr);
-                                   BTR_SEARCH_LEAF, &pcur, &mtr);
     if (err != DB_SUCCESS)
       goto err_exit;
 
@@ -7959,6 +7958,7 @@ report_error:
 
 #ifdef WITH_WSREP
 	if (!error_result && trx->is_wsrep()
+	    && !trx->is_bulk_insert()
 	    && wsrep_thd_is_local(m_user_thd)
 	    && !wsrep_thd_ignore_table(m_user_thd)
 	    && !wsrep_consistency_check(m_user_thd)
@@ -10048,6 +10048,8 @@ wsrep_append_key(
 					(shared, exclusive, semi...) */
 )
 {
+	ut_ad(!trx->is_bulk_insert());
+
 	DBUG_ENTER("wsrep_append_key");
 	DBUG_PRINT("enter",
 		    ("thd: %lu trx: %lld", thd_get_thread_id(thd),

storage/innobase/handler/handler0alter.cc

@@ -6097,7 +6097,8 @@ func_exit:
 
 	que_thr_t* thr = pars_complete_graph_for_exec(
 		NULL, trx, ctx->heap, NULL);
-	const bool is_root = block->page.id().page_no() == index->page;
+	page_id_t id{block->page.id()};
+	const bool is_root = id.page_no() == index->page;
 
 	if (rec_is_metadata(rec, *index)) {
 		ut_ad(page_rec_is_user_rec(rec));
@@ -6114,8 +6115,10 @@ func_exit:
 		}
 
 		/* Ensure that the root page is in the correct format. */
-		buf_block_t* root = btr_root_block_get(index, RW_X_LATCH,
+		id.set_page_no(index->page);
-						       &mtr, &err);
+		buf_block_t* root = mtr.get_already_latched(
+			id, MTR_MEMO_PAGE_SX_FIX);
+
 		if (UNIV_UNLIKELY(!root)) {
 			goto func_exit;
 		}
@@ -11293,7 +11296,8 @@ err_index:
 	}
 
 	DBUG_EXECUTE_IF("stats_lock_fail",
-			error = DB_LOCK_WAIT_TIMEOUT;);
+			error = DB_LOCK_WAIT_TIMEOUT;
+			trx_rollback_for_mysql(trx););
 
 	if (error == DB_SUCCESS) {
 		error = lock_sys_tables(trx);
@@ -11311,6 +11315,18 @@ err_index:
 		if (fts_exist) {
 			purge_sys.resume_FTS();
 		}
+
+		if (trx->state == TRX_STATE_NOT_STARTED) {
+			/* Transaction may have been rolled back
+			due to a lock wait timeout, deadlock,
+			or a KILL statement. So restart the
+			transaction to remove the newly created
+			table or index stubs from data dictionary
+			and table cache in
+			rollback_inplace_alter_table() */
+			trx_start_for_ddl(trx);
+		}
+
 		DBUG_RETURN(true);
 	}
 

storage/innobase/ibuf/ibuf0ibuf.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1997, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, 2022, MariaDB Corporation.
+Copyright (c) 2016, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -2299,7 +2299,7 @@ loop:
   btr_pcur_t pcur;
   pcur.btr_cur.page_cur.index= ibuf.index;
   ibuf_mtr_start(&mtr);
-  if (btr_pcur_open(&tuple, PAGE_CUR_GE, BTR_MODIFY_LEAF, &pcur, 0, &mtr))
+  if (btr_pcur_open(&tuple, PAGE_CUR_GE, BTR_MODIFY_LEAF, &pcur, &mtr))
     goto func_exit;
   if (!btr_pcur_is_on_user_rec(&pcur))
   {
@@ -2495,8 +2495,8 @@ ibuf_merge_space(
 	/* Position the cursor on the first matching record. */
 
 	pcur.btr_cur.page_cur.index = ibuf.index;
-	dberr_t err = btr_pcur_open(&tuple, PAGE_CUR_GE,
+	dberr_t err = btr_pcur_open(&tuple, PAGE_CUR_GE, BTR_SEARCH_LEAF,
-				    BTR_SEARCH_LEAF, &pcur, 0, &mtr);
+				    &pcur, &mtr);
 	ut_ad(err != DB_SUCCESS || page_validate(btr_pcur_get_page(&pcur),
 						 ibuf.index));
 
@@ -3240,7 +3240,7 @@ ibuf_insert_low(
 	ibuf_mtr_start(&mtr);
 	pcur.btr_cur.page_cur.index = ibuf.index;
 
-	err = btr_pcur_open(ibuf_entry, PAGE_CUR_LE, mode, &pcur, 0, &mtr);
+	err = btr_pcur_open(ibuf_entry, PAGE_CUR_LE, mode, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 func_exit:
 		ibuf_mtr_commit(&mtr);
@@ -3957,8 +3957,6 @@ ibuf_restore_pos(
 				position is to be restored */
 	mtr_t*		mtr)	/*!< in/out: mini-transaction */
 {
-	ut_ad(mode == BTR_MODIFY_LEAF || mode == BTR_PURGE_TREE);
-
 	if (UNIV_LIKELY(pcur->restore_position(mode, mtr) ==
 	      btr_pcur_t::SAME_ALL)) {
 		return true;
@@ -4039,12 +4037,11 @@ bool ibuf_delete_rec(const page_id_t page_id, btr_pcur_t* pcur,
 
 	ibuf_mtr_start(mtr);
 	mysql_mutex_lock(&ibuf_mutex);
+	mtr_x_lock_index(ibuf.index, mtr);
 
-	if (!ibuf_restore_pos(page_id, search_tuple, BTR_PURGE_TREE,
+	if (!ibuf_restore_pos(page_id, search_tuple,
-			      pcur, mtr)) {
+			      BTR_PURGE_TREE_ALREADY_LATCHED, pcur, mtr)) {
-
 		mysql_mutex_unlock(&ibuf_mutex);
-		ut_ad(mtr->has_committed());
 		goto func_exit;
 	}
 
@@ -4055,13 +4052,10 @@ bool ibuf_delete_rec(const page_id_t page_id, btr_pcur_t* pcur,
 		ut_a(err == DB_SUCCESS);
 
 		ibuf_size_update(ibuf_root->page.frame);
-		mysql_mutex_unlock(&ibuf_mutex);
-
 		ibuf.empty = page_is_empty(ibuf_root->page.frame);
-	} else {
-		mysql_mutex_unlock(&ibuf_mutex);
 	}
 
+	mysql_mutex_unlock(&ibuf_mutex);
 	ibuf_btr_pcur_commit_specify_mtr(pcur, mtr);
 
 func_exit:
@@ -4239,7 +4233,7 @@ loop:
 
 	/* Position pcur in the insert buffer at the first entry for this
 	index page */
-	if (btr_pcur_open_on_user_rec(search_tuple, PAGE_CUR_GE,
+	if (btr_pcur_open_on_user_rec(search_tuple,
 				      BTR_MODIFY_LEAF, &pcur, &mtr)
 	    != DB_SUCCESS) {
 		err = DB_CORRUPTION;
@@ -4456,7 +4450,7 @@ loop:
 
 	/* Position pcur in the insert buffer at the first entry for the
 	space */
-	if (btr_pcur_open_on_user_rec(&search_tuple, PAGE_CUR_GE,
+	if (btr_pcur_open_on_user_rec(&search_tuple,
 				      BTR_MODIFY_LEAF, &pcur, &mtr)
 	    != DB_SUCCESS) {
 		goto leave_loop;

storage/innobase/include/btr0btr.h

@@ -2,7 +2,7 @@
 
 Copyright (c) 1994, 2016, Oracle and/or its affiliates. All Rights Reserved.
 Copyright (c) 2012, Facebook Inc.
-Copyright (c) 2014, 2022, MariaDB Corporation.
+Copyright (c) 2014, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -211,13 +211,12 @@ btr_write_autoinc(dict_index_t* index, ib_uint64_t autoinc, bool reset = false)
 @param[in,out]	mtr	mini-transaction */
 void btr_set_instant(buf_block_t* root, const dict_index_t& index, mtr_t* mtr);
 
-ATTRIBUTE_COLD __attribute__((nonnull, warn_unused_result))
+ATTRIBUTE_COLD __attribute__((nonnull))
 /** Reset the table to the canonical format on ROLLBACK of instant ALTER TABLE.
 @param[in]      index   clustered index with instant ALTER TABLE
 @param[in]      all     whether to reset FIL_PAGE_TYPE as well
-@param[in,out]  mtr     mini-transaction
+@param[in,out]  mtr     mini-transaction */
-@return error code */
+void btr_reset_instant(const dict_index_t &index, bool all, mtr_t *mtr);
-dberr_t btr_reset_instant(const dict_index_t &index, bool all, mtr_t *mtr);
 
 /*************************************************************//**
 Makes tree one level higher by splitting the root, and inserts
@@ -241,7 +240,7 @@ btr_root_raise_and_insert(
 	ulint		n_ext,	/*!< in: number of externally stored columns */
 	mtr_t*		mtr,	/*!< in: mtr */
 	dberr_t*	err)	/*!< out: error code */
-	MY_ATTRIBUTE((warn_unused_result));
+	MY_ATTRIBUTE((nonnull, warn_unused_result));
 /*************************************************************//**
 Reorganizes an index page.
 

storage/innobase/include/btr0cur.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1994, 2019, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -63,12 +63,6 @@ enum {
 	BTR_KEEP_IBUF_BITMAP = 32
 };
 
-/* btr_cur_latch_leaves() returns latched blocks and savepoints. */
-struct btr_latch_leaves_t {
-	buf_block_t*	blocks[3];
-	ulint		savepoints[3];
-};
-
 #include "que0types.h"
 #include "row0types.h"
 
@@ -126,51 +120,28 @@ bool
 btr_cur_instant_root_init(dict_index_t* index, const page_t* page)
 	ATTRIBUTE_COLD __attribute__((nonnull, warn_unused_result));
 
-/** Optimistically latches the leaf page or pages requested.
-@param[in]	block		guessed buffer block
-@param[in]	modify_clock	modify clock value
-@param[in,out]	latch_mode	BTR_SEARCH_LEAF, ...
-@param[in,out]	cursor		cursor
-@param[in]	mtr		mini-transaction
-@return true if success */
-bool
-btr_cur_optimistic_latch_leaves(
-	buf_block_t*	block,
-	ib_uint64_t	modify_clock,
-	btr_latch_mode*	latch_mode,
-	btr_cur_t*	cursor,
-	mtr_t*		mtr);
-
 MY_ATTRIBUTE((warn_unused_result))
-/** Searches an index tree and positions a tree cursor on a given level.
+/********************************************************************//**
+Searches an index tree and positions a tree cursor on a given non-leaf level.
 NOTE: n_fields_cmp in tuple must be set so that it cannot be compared
 to node pointer page number fields on the upper levels of the tree!
-Note that if mode is PAGE_CUR_LE, which is used in inserts, then
 cursor->up_match and cursor->low_match both will have sensible values.
-If mode is PAGE_CUR_GE, then up_match will a have a sensible value.
+Cursor is left at the place where an insert of the
+search tuple should be performed in the B-tree. InnoDB does an insert
+immediately after the cursor. Thus, the cursor may end up on a user record,
+or on a page infimum record.
 @param level      the tree level of search
 @param tuple      data tuple; NOTE: n_fields_cmp in tuple must be set so that
                   it cannot get compared to the node ptr page number field!
-@param mode       PAGE_CUR_L, ...; NOTE that if the search is made using a
+@param latch      RW_S_LATCH or RW_X_LATCH
-                  unique prefix of a record, mode should be PAGE_CUR_LE, not
-                  PAGE_CUR_GE, as the latter may end up on the previous page of
-                  the record! Inserts should always be made using PAGE_CUR_LE
-                  to search the position!
-@param latch_mode BTR_SEARCH_LEAF, ..., ORed with at most one of BTR_INSERT,
-                  BTR_DELETE_MARK, or BTR_DELETE;
-                  cursor->left_block is used to store a pointer to the left
-                  neighbor page
 @param cursor     tree cursor; the cursor page is s- or x-latched, but see also
                   above!
 @param mtr        mini-transaction
-@param autoinc    PAGE_ROOT_AUTO_INC to be written (0 if none)
 @return DB_SUCCESS on success or error code otherwise */
 dberr_t btr_cur_search_to_nth_level(ulint level,
                                     const dtuple_t *tuple,
-                                    page_cur_mode_t mode,
+                                    rw_lock_type_t rw_latch,
-                                    btr_latch_mode latch_mode,
+                                    btr_cur_t *cursor, mtr_t *mtr);
-                                    btr_cur_t *cursor, mtr_t *mtr,
-                                    ib_uint64_t autoinc= 0);
 
 /*************************************************************//**
 Tries to perform an insert to a page in an index tree, next to cursor.
@@ -653,20 +624,6 @@ btr_rec_copy_externally_stored_field(
 	ulint*			len,
 	mem_heap_t*		heap);
 
-/** Latches the leaf page or pages requested.
-@param[in]	block		leaf page where the search converged
-@param[in]	latch_mode	BTR_SEARCH_LEAF, ...
-@param[in]	cursor		cursor
-@param[in,out]	mtr		mini-transaction
-@param[out]	latch_leaves	latched blocks and savepoints */
-void
-btr_cur_latch_leaves(
-	buf_block_t*		block,
-	btr_latch_mode		latch_mode,
-	btr_cur_t*		cursor,
-	mtr_t*			mtr,
-	btr_latch_leaves_t*	latch_leaves = nullptr);
-
 /*######################################################################*/
 
 /** In the pessimistic delete, if the page data size drops below this
@@ -727,21 +684,16 @@ to know struct size! */
 struct btr_cur_t {
 	page_cur_t	page_cur;	/*!< page cursor */
 	purge_node_t*	purge_node;	/*!< purge node, for BTR_DELETE */
-	buf_block_t*	left_block;	/*!< this field is used to store
-					a pointer to the left neighbor
-					page, in the cases
-					BTR_SEARCH_PREV and
-					BTR_MODIFY_PREV */
 	/*------------------------------*/
 	que_thr_t*	thr;		/*!< this field is only used
-					when btr_cur_search_to_nth_level
+					when search_leaf()
 					is called for an index entry
 					insertion: the calling query
 					thread is passed here to be
 					used in the insert buffer */
 	/*------------------------------*/
 	/** The following fields are used in
-	btr_cur_search_to_nth_level to pass information: */
+	search_leaf() to pass information: */
 	/* @{ */
 	enum btr_cur_method	flag;	/*!< Search method used */
 	ulint		tree_height;	/*!< Tree height if the search is done
@@ -750,8 +702,7 @@ struct btr_cur_t {
 	ulint		up_match;	/*!< If the search mode was PAGE_CUR_LE,
 					the number of matched fields to the
 					the first user record to the right of
-					the cursor record after
+					the cursor record after search_leaf();
-					btr_cur_search_to_nth_level;
 					for the mode PAGE_CUR_GE, the matched
 					fields to the first user record AT THE
 					CURSOR or to the right of it;
@@ -768,8 +719,7 @@ struct btr_cur_t {
 	ulint		low_match;	/*!< if search mode was PAGE_CUR_LE,
 					the number of matched fields to the
 					first user record AT THE CURSOR or
-					to the left of it after
+					to the left of it after search_leaf();
-					btr_cur_search_to_nth_level;
 					NOT defined for PAGE_CUR_GE or any
 					other search modes; see also the NOTE
 					in up_match! */
@@ -803,6 +753,24 @@ struct btr_cur_t {
   dberr_t open_leaf(bool first, dict_index_t *index, btr_latch_mode latch_mode,
                     mtr_t *mtr);
 
+  /** Search the leaf page record corresponding to a key.
+  @param tuple      key to search for, with correct n_fields_cmp
+  @param mode       search mode; PAGE_CUR_LE for unique prefix or for inserting
+  @param latch_mode latch mode
+  @param mtr        mini-transaction
+  @return error code */
+  dberr_t search_leaf(const dtuple_t *tuple, page_cur_mode_t mode,
+                      btr_latch_mode latch_mode, mtr_t *mtr);
+
+  /** Search the leaf page record corresponding to a key, exclusively latching
+  all sibling pages on the way.
+  @param tuple      key to search for, with correct n_fields_cmp
+  @param mode       search mode; PAGE_CUR_LE for unique prefix or for inserting
+  @param mtr        mini-transaction
+  @return error code */
+  dberr_t pessimistic_search_leaf(const dtuple_t *tuple, page_cur_mode_t mode,
+                                  mtr_t *mtr);
+
   /** Open the cursor at a random leaf page record.
   @param offsets   temporary memory for rec_get_offsets()
   @param heap      memory heap for rec_get_offsets()
@@ -862,14 +830,14 @@ inherited external field. */
 #define BTR_EXTERN_INHERITED_FLAG	64U
 
 #ifdef BTR_CUR_HASH_ADAPT
-/** Number of searches down the B-tree in btr_cur_search_to_nth_level(). */
+/** Number of searches down the B-tree in btr_cur_t::search_leaf(). */
 extern ib_counter_t<ulint, ib_counter_element_t>	btr_cur_n_non_sea;
 /** Old value of btr_cur_n_non_sea.  Copied by
 srv_refresh_innodb_monitor_stats().  Referenced by
 srv_printf_innodb_monitor(). */
 extern ulint	btr_cur_n_non_sea_old;
 /** Number of successful adaptive hash index lookups in
-btr_cur_search_to_nth_level(). */
+btr_cur_t::search_leaf(). */
 extern ib_counter_t<ulint, ib_counter_element_t>	btr_cur_n_sea;
 /** Old value of btr_cur_n_sea.  Copied by
 srv_refresh_innodb_monitor_stats().  Referenced by

storage/innobase/include/btr0pcur.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -70,24 +70,6 @@ btr_pcur_init(
 /*==========*/
 	btr_pcur_t*	pcur);	/*!< in: persistent cursor */
 
-/**************************************************************//**
-Initializes and opens a persistent cursor to an index tree. */
-inline
-dberr_t
-btr_pcur_open(
-	const dtuple_t*	tuple,	/*!< in: tuple on which search done */
-	page_cur_mode_t	mode,	/*!< in: PAGE_CUR_L, ...;
-				NOTE that if the search is made using a unique
-				prefix of a record, mode should be
-				PAGE_CUR_LE, not PAGE_CUR_GE, as the latter
-				may end up on the previous page from the
-				record! */
-	btr_latch_mode	latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */
-	btr_pcur_t*	cursor, /*!< in: memory buffer for persistent cursor */
-	ib_uint64_t	autoinc,/*!< in: PAGE_ROOT_AUTO_INC to be written
-				(0 if none) */
-	mtr_t*		mtr)	/*!< in: mtr */
-	MY_ATTRIBUTE((nonnull, warn_unused_result));
 /** Opens an persistent cursor to an index tree without initializing the
 cursor.
 @param tuple      tuple on which search done
@@ -100,8 +82,7 @@ cursor.
 @param mtr        mini-transaction
 @return DB_SUCCESS on success or error code otherwise. */
 inline
-dberr_t btr_pcur_open_with_no_init(const dtuple_t *tuple,
+dberr_t btr_pcur_open_with_no_init(const dtuple_t *tuple, page_cur_mode_t mode,
-                                   page_cur_mode_t mode,
                                    btr_latch_mode latch_mode,
                                    btr_pcur_t *cursor, mtr_t *mtr);
 
@@ -356,7 +337,7 @@ struct btr_pcur_t
   /** the modify clock value of the buffer block when the cursor position
   was stored */
   ib_uint64_t modify_clock= 0;
-  /** btr_pcur_store_position() and btr_pcur_restore_position() state. */
+  /** btr_pcur_store_position() and restore_position() state. */
   enum pcur_pos_t pos_state= BTR_PCUR_NOT_POSITIONED;
   page_cur_mode_t search_mode= PAGE_CUR_UNSUPP;
   /** the transaction, if we know it; otherwise this field is not defined;
@@ -383,8 +364,8 @@ struct btr_pcur_t
   supremum.
   (4) cursor was positioned before the first or after the last in an
   empty tree: restores to before first or after the last in the tree.
-  @param restore_latch_mode BTR_SEARCH_LEAF, ...
+  @param latch_mode  BTR_SEARCH_LEAF, ...
-  @param mtr mtr
+  @param mtr         mini-transaction
   @retval SAME_ALL cursor position on user rec and points on
   the record with the same field values as in the stored record,
   @retval SAME_UNIQ cursor position is on user rec and points on the
@@ -409,8 +390,7 @@ struct btr_pcur_t
     pos_state= BTR_PCUR_IS_POSITIONED;
     old_rec= nullptr;
 
-    return btr_cur.open_leaf(first, index,
+    return btr_cur.open_leaf(first, index, this->latch_mode, mtr);
-                             BTR_LATCH_MODE_WITHOUT_FLAGS(latch_mode), mtr);
   }
 };
 
@@ -433,6 +413,24 @@ inline rec_t *btr_pcur_get_rec(const btr_pcur_t *cursor)
   return cursor->btr_cur.page_cur.rec;
 }
 
+/**************************************************************//**
+Initializes and opens a persistent cursor to an index tree. */
+inline
+dberr_t
+btr_pcur_open(
+	const dtuple_t*	tuple,	/*!< in: tuple on which search done */
+        page_cur_mode_t	mode,	/*!< in: PAGE_CUR_LE, ... */
+	btr_latch_mode	latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */
+	btr_pcur_t*	cursor, /*!< in: memory buffer for persistent cursor */
+	mtr_t*		mtr)	/*!< in: mtr */
+{
+  cursor->latch_mode= BTR_LATCH_MODE_WITHOUT_FLAGS(latch_mode);
+  cursor->search_mode= mode;
+  cursor->pos_state= BTR_PCUR_IS_POSITIONED;
+  cursor->trx_if_known= nullptr;
+  return cursor->btr_cur.search_leaf(tuple, mode, latch_mode, mtr);
+}
+
 /** Open a cursor on the first user record satisfying the search condition;
 in case of no match, after the last index record. */
 MY_ATTRIBUTE((nonnull, warn_unused_result))
@@ -440,16 +438,15 @@ inline
 dberr_t
 btr_pcur_open_on_user_rec(
 	const dtuple_t*	tuple,		/*!< in: tuple on which search done */
-	page_cur_mode_t	mode,		/*!< in: PAGE_CUR_L, ... */
 	btr_latch_mode	latch_mode,	/*!< in: BTR_SEARCH_LEAF or
 					BTR_MODIFY_LEAF */
 	btr_pcur_t*	cursor,		/*!< in: memory buffer for persistent
 					cursor */
 	mtr_t*		mtr)		/*!< in: mtr */
 {
-  ut_ad(mode == PAGE_CUR_GE || mode == PAGE_CUR_G);
   ut_ad(latch_mode == BTR_SEARCH_LEAF || latch_mode == BTR_MODIFY_LEAF);
-  if (dberr_t err= btr_pcur_open(tuple, mode, latch_mode, cursor, 0, mtr))
+  if (dberr_t err=
+      btr_pcur_open(tuple, PAGE_CUR_GE, latch_mode, cursor, mtr))
     return err;
   if (!btr_pcur_is_after_last_on_page(cursor) ||
       btr_pcur_is_after_last_in_tree(cursor))

storage/innobase/include/btr0pcur.inl

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2015, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2015, 2022, MariaDB Corporation.
+Copyright (c) 2015, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -299,38 +299,10 @@ btr_pcur_init(
 	pcur->btr_cur.rtr_info = NULL;
 }
 
-/**************************************************************//**
-Initializes and opens a persistent cursor to an index tree. */
-inline
-dberr_t
-btr_pcur_open(
-	const dtuple_t*	tuple,	/*!< in: tuple on which search done */
-	page_cur_mode_t	mode,	/*!< in: PAGE_CUR_L, ...;
-				NOTE that if the search is made using a unique
-				prefix of a record, mode should be
-				PAGE_CUR_LE, not PAGE_CUR_GE, as the latter
-				may end up on the previous page from the
-				record! */
-	btr_latch_mode	latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */
-	btr_pcur_t*	cursor, /*!< in: memory buffer for persistent cursor */
-	ib_uint64_t	autoinc,/*!< in: PAGE_ROOT_AUTO_INC to be written
-				(0 if none) */
-	mtr_t*		mtr)	/*!< in: mtr */
-{
-  ut_ad(!cursor->index()->is_spatial());
-  cursor->latch_mode= BTR_LATCH_MODE_WITHOUT_FLAGS(latch_mode);
-  cursor->search_mode= mode;
-  cursor->pos_state= BTR_PCUR_IS_POSITIONED;
-  cursor->trx_if_known= nullptr;
-  return btr_cur_search_to_nth_level(0, tuple, mode, latch_mode,
-                                     btr_pcur_get_btr_cur(cursor),
-                                     mtr, autoinc);
-}
-
 /** Opens an persistent cursor to an index tree without initializing the
 cursor.
 @param tuple      tuple on which search done
-@param mode       PAGE_CUR_L, ...; NOTE that if the search is made using a
+@param mode       search mode; NOTE that if the search is made using a
                   unique prefix of a record, mode should be PAGE_CUR_LE, not
                   PAGE_CUR_GE, as the latter may end up on the previous page of
                   the record!
@@ -339,8 +311,7 @@ cursor.
 @param mtr        mini-transaction
 @return DB_SUCCESS on success or error code otherwise. */
 inline
-dberr_t btr_pcur_open_with_no_init(const dtuple_t *tuple,
+dberr_t btr_pcur_open_with_no_init(const dtuple_t *tuple, page_cur_mode_t mode,
-                                   page_cur_mode_t mode,
                                    btr_latch_mode latch_mode,
                                    btr_pcur_t *cursor, mtr_t *mtr)
 {
@@ -348,10 +319,7 @@ dberr_t btr_pcur_open_with_no_init(const dtuple_t *tuple,
   cursor->search_mode= mode;
   cursor->pos_state= BTR_PCUR_IS_POSITIONED;
   cursor->trx_if_known= nullptr;
-
+  return cursor->btr_cur.search_leaf(tuple, mode, latch_mode, mtr);
-  /* Search with the tree cursor */
-  return btr_cur_search_to_nth_level(0, tuple, mode, latch_mode,
-                                     btr_pcur_get_btr_cur(cursor), mtr);
 }
 
 /**************************************************************//**

storage/innobase/include/btr0types.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2015, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2018, 2022, MariaDB Corporation.
+Copyright (c) 2018, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -55,25 +55,26 @@ in the index record. */
 #define BTR_EXTERN_LOCAL_STORED_MAX_SIZE	\
 	(BTR_EXTERN_FIELD_REF_SIZE * 2)
 
-/** Latching modes for btr_cur_search_to_nth_level(). */
+/** Latching modes for btr_cur_t::search_leaf(). */
 enum btr_latch_mode {
 	/** Search a record on a leaf page and S-latch it. */
 	BTR_SEARCH_LEAF = RW_S_LATCH,
 	/** (Prepare to) modify a record on a leaf page and X-latch it. */
 	BTR_MODIFY_LEAF	= RW_X_LATCH,
+	/** U-latch root and X-latch a leaf page */
+	BTR_MODIFY_ROOT_AND_LEAF = RW_SX_LATCH,
 	/** Obtain no latches. */
 	BTR_NO_LATCHES = RW_NO_LATCH,
-	/** Search the previous record. */
+	/** Search the previous record.
+	Used in btr_pcur_move_backward_from_page(). */
 	BTR_SEARCH_PREV = 4 | BTR_SEARCH_LEAF,
-	/** Modify the previous record. */
+	/** Modify the previous record.
+	Used in btr_pcur_move_backward_from_page() and ibuf_insert(). */
 	BTR_MODIFY_PREV = 4 | BTR_MODIFY_LEAF,
-	/** Start searching the entire B-tree. */
+	/** Start modifying the entire B-tree. */
-	BTR_SEARCH_TREE = 8 | BTR_SEARCH_LEAF,
-	/** Start modifying1 the entire B-tree. */
 	BTR_MODIFY_TREE = 8 | BTR_MODIFY_LEAF,
-	/** Continue searching the entire B-tree. */
+	/** Continue modifying the entire R-tree.
-	BTR_CONT_SEARCH_TREE = 4 | BTR_SEARCH_TREE,
+	Only used by rtr_search_to_nth_level(). */
-	/** Continue modifying the entire B-tree. */
 	BTR_CONT_MODIFY_TREE = 4 | BTR_MODIFY_TREE,
 
 	/* BTR_INSERT, BTR_DELETE and BTR_DELETE_MARK are mutually
@@ -98,14 +99,14 @@ enum btr_latch_mode {
 	dict_index_t::lock S-latch is being held. */
 	BTR_SEARCH_LEAF_ALREADY_S_LATCHED = BTR_SEARCH_LEAF
 	| BTR_ALREADY_S_LATCHED,
-	/** Search the entire index tree, assuming that the
-	dict_index_t::lock S-latch is being held. */
-	BTR_SEARCH_TREE_ALREADY_S_LATCHED = BTR_SEARCH_TREE
-	| BTR_ALREADY_S_LATCHED,
 	/** Search and X-latch a leaf page, assuming that the
 	dict_index_t::lock is being held in non-exclusive mode. */
 	BTR_MODIFY_LEAF_ALREADY_LATCHED = BTR_MODIFY_LEAF
 	| BTR_ALREADY_S_LATCHED,
+	/** U-latch root and X-latch a leaf page, assuming that
+	dict_index_t::lock is being held in U mode. */
+	BTR_MODIFY_ROOT_AND_LEAF_ALREADY_LATCHED = BTR_MODIFY_ROOT_AND_LEAF
+	| BTR_ALREADY_S_LATCHED,
 
 	/** Attempt to delete-mark a secondary index record. */
 	BTR_DELETE_MARK_LEAF = BTR_MODIFY_LEAF | BTR_DELETE_MARK,
@@ -132,6 +133,9 @@ enum btr_latch_mode {
 
 	/** Attempt to delete a record in the tree. */
 	BTR_PURGE_TREE = BTR_MODIFY_TREE | BTR_LATCH_FOR_DELETE,
+	/** Attempt to delete a record in an x-latched tree. */
+	BTR_PURGE_TREE_ALREADY_LATCHED = BTR_PURGE_TREE
+	| BTR_ALREADY_S_LATCHED,
 
 	/** Attempt to insert a record into the tree. */
 	BTR_INSERT_TREE = BTR_MODIFY_TREE | BTR_LATCH_FOR_INSERT,

storage/innobase/include/buf0buf.h

@@ -799,7 +799,7 @@ public:
   {
     ut_ad(fsp_is_system_temporary(id().space()));
     ut_ad(in_file());
-    ut_ad(!oldest_modification() || oldest_modification() == 2);
+    ut_ad((oldest_modification() | 2) == 2);
     oldest_modification_= 2;
   }
 

storage/innobase/include/gis0rtree.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2014, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -59,6 +59,44 @@ Created 2013/03/27 Jimmy Yang and Allen Lai
 
 /* Geometry data header */
 #define	GEO_DATA_HEADER_SIZE	4
+
+/** Search for a spatial index leaf page record.
+@param cur         cursor
+@param tuple       search tuple
+@param latch_mode  latching mode
+@param mtr         mini-transaction
+@param mode        search mode */
+dberr_t rtr_search_leaf(btr_cur_t *cur, const dtuple_t *tuple,
+                        btr_latch_mode latch_mode, mtr_t *mtr,
+                        page_cur_mode_t mode= PAGE_CUR_RTREE_LOCATE)
+  MY_ATTRIBUTE((nonnull, warn_unused_result));
+
+/** Search for inserting a spatial index leaf page record.
+@param cur         cursor
+@param tuple       search tuple
+@param latch_mode  latching mode
+@param mtr         mini-transaction */
+inline dberr_t rtr_insert_leaf(btr_cur_t *cur, const dtuple_t *tuple,
+                               btr_latch_mode latch_mode, mtr_t *mtr)
+{
+  return rtr_search_leaf(cur, tuple, latch_mode, mtr, PAGE_CUR_RTREE_INSERT);
+}
+
+/** Search for a spatial index leaf page record.
+@param pcur         cursor
+@param tuple       search tuple
+@param mode        search mode
+@param mtr         mini-transaction */
+dberr_t rtr_search_leaf(btr_pcur_t *pcur, const dtuple_t *tuple,
+                        page_cur_mode_t mode, mtr_t *mtr)
+  MY_ATTRIBUTE((nonnull, warn_unused_result));
+
+dberr_t rtr_search_to_nth_level(ulint level, const dtuple_t *tuple,
+                                page_cur_mode_t mode,
+                                btr_latch_mode latch_mode,
+                                btr_cur_t *cur, mtr_t *mtr)
+  MY_ATTRIBUTE((nonnull, warn_unused_result));
+
 /**********************************************************************//**
 Builds a Rtree node pointer out of a physical record and a page number.
 @return own: node pointer */
@@ -295,11 +333,9 @@ rtr_store_parent_path(
 /**************************************************************//**
 Initializes and opens a persistent cursor to an index tree. It should be
 closed with btr_pcur_close. */
-bool
+bool rtr_search(
-rtr_pcur_open(
-	dict_index_t*	index,	/*!< in: index */
 	const dtuple_t*	tuple,	/*!< in: tuple on which search done */
-	btr_latch_mode	latch_mode,/*!< in: BTR_SEARCH_LEAF, ... */
+	btr_latch_mode	latch_mode,/*!< in: BTR_MODIFY_LEAF, ... */
 	btr_pcur_t*	cursor,	/*!< in: memory buffer for persistent cursor */
 	mtr_t*		mtr)	/*!< in: mtr */
 	MY_ATTRIBUTE((warn_unused_result));

storage/innobase/include/gis0type.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2014, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2018, 2020, MariaDB Corporation.
+Copyright (c) 2018, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -105,12 +105,6 @@ typedef	struct rtr_info{
 	matched_rec_t*	matches;/*!< struct holding matching leaf records */
 	mysql_mutex_t	rtr_path_mutex;
 				/*!< mutex protect the "path" vector */
-	buf_block_t*	tree_blocks[RTR_MAX_LEVELS + RTR_LEAF_LATCH_NUM];
-				/*!< tracking pages that would be locked
-				at leaf level, for future free */
-        ulint		tree_savepoints[RTR_MAX_LEVELS + RTR_LEAF_LATCH_NUM];
-				/*!< savepoint used to release latches/blocks
-				on each level and leaf level */
 	rtr_mbr_t	mbr;	/*!< the search MBR */
 	que_thr_t*      thr;	/*!< the search thread */
 	mem_heap_t*	heap;	/*!< memory heap */

storage/innobase/include/ibuf0ibuf.inl

@@ -100,8 +100,8 @@ ibuf_should_try(
 						a secondary index when we
 						decide */
 {
-  if (!innodb_change_buffering || !ibuf.max_size || index->is_clust() ||
+  if (index->type & (DICT_CLUSTERED | DICT_IBUF | DICT_SPATIAL) ||
-      index->is_spatial())
+      !innodb_change_buffering || !ibuf.max_size)
     return false;
   if (!ignore_sec_unique && index->is_unique())
     return false;

storage/innobase/include/mtr0log.h

@@ -1,6 +1,6 @@
 /*****************************************************************************
 
-Copyright (c) 2019, 2022, MariaDB Corporation.
+Copyright (c) 2019, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -402,7 +402,8 @@ inline byte *mtr_t::log_write(const page_id_t id, const buf_page_t *bpage,
   ut_ad(have_offset || offset == 0);
   ut_ad(offset + len <= srv_page_size);
   static_assert(MIN_4BYTE >= UNIV_PAGE_SIZE_MAX, "consistency");
-
+  ut_ad(type == FREE_PAGE || type == OPTION || (type == EXTENDED && !bpage) ||
+        memo_contains_flagged(bpage, MTR_MEMO_MODIFY));
   size_t max_len;
   if (!have_len)
     max_len= 1 + 5 + 5;
@@ -512,33 +513,6 @@ inline void mtr_t::memcpy(const buf_block_t &b, void *dest, const void *str,
   memcpy(b, ut_align_offset(d, srv_page_size), len);
 }
 
-/** Initialize an entire page.
-@param[in,out]        b       buffer page */
-inline void mtr_t::init(buf_block_t *b)
-{
-  const page_id_t id{b->page.id()};
-  ut_ad(is_named_space(id.space()));
-  ut_ad(!m_freed_pages == !m_freed_space);
-
-  if (UNIV_LIKELY_NULL(m_freed_space) &&
-      m_freed_space->id == id.space() &&
-      m_freed_pages->remove_if_exists(b->page.id().page_no()) &&
-      m_freed_pages->empty())
-  {
-    delete m_freed_pages;
-    m_freed_pages= nullptr;
-    m_freed_space= nullptr;
-  }
-
-  b->page.set_reinit(b->page.state() & buf_page_t::LRU_MASK);
-
-  if (!is_logged())
-    return;
-
-  m_log.close(log_write<INIT_PAGE>(b->page.id(), &b->page));
-  m_last_offset= FIL_PAGE_TYPE;
-}
-
 /** Write an EXTENDED log record.
 @param block  buffer pool page
 @param type   extended record subtype; @see mrec_ext_t */

storage/innobase/include/mtr0mtr.h

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1995, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2013, 2022, MariaDB Corporation.
+Copyright (c) 2013, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -29,7 +29,7 @@ Created 11/26/1995 Heikki Tuuri
 #include "fil0fil.h"
 #include "dyn0buf.h"
 #include "buf0buf.h"
-#include <vector>
+#include "small_vector.h"
 
 /** Start a mini-transaction. */
 #define mtr_start(m)		(m)->start()
@@ -37,15 +37,6 @@ Created 11/26/1995 Heikki Tuuri
 /** Commit a mini-transaction. */
 #define mtr_commit(m)		(m)->commit()
 
-/** Set and return a savepoint in mtr.
-@return	savepoint */
-#define mtr_set_savepoint(m)	(m)->get_savepoint()
-
-/** Release the (index tree) s-latch stored in an mtr memo after a
-savepoint. */
-#define mtr_release_s_latch_at_savepoint(m, s, l)			\
-				(m)->release_s_latch_at_savepoint((s), (l))
-
 /** Change the logging mode of a mini-transaction.
 @return	old mode */
 #define mtr_set_log_mode(m, d)	(m)->set_log_mode((d))
@@ -60,13 +51,10 @@ savepoint. */
 # define mtr_sx_lock_index(i,m)	(m)->u_lock(&(i)->lock)
 #endif
 
-#define mtr_release_block_at_savepoint(m, s, b)				\
-				(m)->release_block_at_savepoint((s), (b))
-
 /** Mini-transaction memo stack slot. */
 struct mtr_memo_slot_t
 {
-  /** pointer to the object, or nullptr if released */
+  /** pointer to the object */
   void *object;
   /** type of the stored object */
   mtr_memo_type_t type;
@@ -77,6 +65,9 @@ struct mtr_memo_slot_t
 
 /** Mini-transaction handle and buffer */
 struct mtr_t {
+  mtr_t();
+  ~mtr_t();
+
   /** Start a mini-transaction. */
   void start();
 
@@ -91,11 +82,11 @@ struct mtr_t {
   /** Release latches of unmodified buffer pages.
   @param begin   first slot to release */
   void rollback_to_savepoint(ulint begin)
-  { rollback_to_savepoint(begin, m_memo->size()); }
+  { rollback_to_savepoint(begin, m_memo.size()); }
 
   /** Release the last acquired buffer page latch. */
   void release_last_page()
-  { auto s= m_memo->size(); rollback_to_savepoint(s - 1, s); }
+  { auto s= m_memo.size(); rollback_to_savepoint(s - 1, s); }
 
   /** Commit a mini-transaction that is shrinking a tablespace.
   @param space   tablespace that is being shrunk */
@@ -120,86 +111,39 @@ struct mtr_t {
   ulint get_savepoint() const
   {
     ut_ad(is_active());
-    return m_memo ? m_memo->size() : 0;
+    return m_memo.size();
   }
 
-  /** Release the (index tree) s-latch stored in an mtr memo after a savepoint.
+  /** Get the block at a savepoint */
-  @param savepoint value returned by get_savepoint()
+  buf_block_t *at_savepoint(ulint savepoint) const
-  @param lock   index latch to release */
-  void release_s_latch_at_savepoint(ulint savepoint, index_lock *lock)
   {
     ut_ad(is_active());
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
+    const mtr_memo_slot_t &slot= m_memo[savepoint];
-    ut_ad(slot.object == lock);
+    ut_ad(slot.type < MTR_MEMO_S_LOCK);
-    ut_ad(slot.type == MTR_MEMO_S_LOCK);
+    ut_ad(slot.object);
-    slot.object= nullptr;
+    return static_cast<buf_block_t*>(slot.object);
-    lock->s_unlock();
   }
-  /** Release the block in an mtr memo after a savepoint. */
+
-  void release_block_at_savepoint(ulint savepoint, buf_block_t *block)
+  /** Try to get a block at a savepoint.
+  @param savepoint the savepoint right before the block was acquired
+  @return the block at the savepoint
+  @retval nullptr  if no buffer block was registered at that savepoint */
+  buf_block_t *block_at_savepoint(ulint savepoint) const
   {
     ut_ad(is_active());
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
+    const mtr_memo_slot_t &slot= m_memo[savepoint];
-    ut_ad(slot.object == block);
+    return slot.type < MTR_MEMO_S_LOCK
-    ut_ad(!(slot.type & MTR_MEMO_MODIFY));
+      ? static_cast<buf_block_t*>(slot.object)
-    slot.object= nullptr;
+      : nullptr;
-    block->page.unfix();
-
-    switch (slot.type) {
-    case MTR_MEMO_PAGE_S_FIX:
-      block->page.lock.s_unlock();
-      break;
-    case MTR_MEMO_PAGE_SX_FIX:
-    case MTR_MEMO_PAGE_X_FIX:
-      block->page.lock.u_or_x_unlock(slot.type == MTR_MEMO_PAGE_SX_FIX);
-      break;
-    default:
-      break;
-    }
   }
 
-  /** @return if we are about to make a clean buffer block dirty */
+  /** Retrieve a page that has already been latched.
-  static bool is_block_dirtied(const buf_page_t &b)
+  @param id    page identifier
-  {
+  @param type  page latch type
-    ut_ad(b.in_file());
+  @return block
-    ut_ad(b.frame);
+  @retval nullptr if the block had not been latched yet */
-    ut_ad(b.buf_fix_count());
+  buf_block_t *get_already_latched(const page_id_t id, mtr_memo_type_t type)
-    return b.oldest_modification() <= 1 && b.id().space() < SRV_TMP_SPACE_ID;
+    const;
-  }
-
-  /** X-latch a not yet latched block after a savepoint. */
-  void x_latch_at_savepoint(ulint savepoint, buf_block_t *block)
-  {
-    ut_ad(is_active());
-    ut_ad(!memo_contains_flagged(block, MTR_MEMO_PAGE_S_FIX |
-                                 MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX));
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
-    ut_ad(slot.object == block);
-    ut_ad(slot.type == MTR_MEMO_BUF_FIX);
-    slot.type= MTR_MEMO_PAGE_X_FIX;
-    block->page.lock.x_lock();
-    ut_ad(!block->page.is_io_fixed());
-
-    if (!m_made_dirty)
-      m_made_dirty= is_block_dirtied(block->page);
-  }
-
-  /** U-latch a not yet latched block after a savepoint. */
-  void sx_latch_at_savepoint(ulint savepoint, buf_block_t *block)
-  {
-    ut_ad(is_active());
-    ut_ad(!memo_contains_flagged(block, MTR_MEMO_PAGE_S_FIX |
-                                 MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX));
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
-    ut_ad(slot.object == block);
-    ut_ad(slot.type == MTR_MEMO_BUF_FIX);
-    slot.type= MTR_MEMO_PAGE_SX_FIX;
-    block->page.lock.u_lock();
-    ut_ad(!block->page.is_io_fixed());
-
-    if (!m_made_dirty)
-      m_made_dirty= is_block_dirtied(block->page);
-  }
 
   /** @return the logging mode */
   mtr_log_t get_log_mode() const
@@ -358,23 +302,17 @@ struct mtr_t {
   void release(const index_lock &lock) { release(&lock); }
   /** Release a latch to an unmodified page. */
   void release(const buf_block_t &block) { release(&block); }
-
-  /** Note that the mini-transaction will modify data. */
-  void flag_modified() { m_modifications = true; }
 private:
   /** Release an unmodified object. */
   void release(const void *object);
+public:
   /** Mark the given latched page as modified.
   @param block   page that will be modified */
-  void modify(const buf_block_t& block);
+  void set_modified(const buf_block_t &block);
-public:
-  /** Note that the mini-transaction will modify a block. */
-  void set_modified(const buf_block_t &block)
-  { flag_modified(); if (m_log_mode != MTR_LOG_NONE) modify(block); }
 
   /** Set the state to not-modified. This will not log the changes.
   This is only used during redo log apply, to avoid logging the changes. */
-  void discard_modifications() { m_modifications = false; }
+  void discard_modifications() { m_modifications= false; }
 
   /** Get the LSN of commit().
   @return the commit LSN
@@ -403,28 +341,17 @@ public:
   @param rw_latch    latch to acquire */
   void upgrade_buffer_fix(ulint savepoint, rw_lock_type_t rw_latch);
 
-  /** Register a page latch on a buffer-fixed block was buffer-fixed.
+  /** Register a change to the page latch state. */
-  @param latch   latch type */
+  void lock_register(ulint savepoint, mtr_memo_type_t type)
-  void u_lock_register(ulint savepoint)
   {
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
+    mtr_memo_slot_t &slot= m_memo[savepoint];
-    ut_ad(slot.type == MTR_MEMO_BUF_FIX);
+    ut_ad(slot.type <= MTR_MEMO_BUF_FIX);
-    slot.type= MTR_MEMO_PAGE_SX_FIX;
+    ut_ad(type <= MTR_MEMO_BUF_FIX);
-  }
+    slot.type= type;
-
-  /** Register a page latch on a buffer-fixed block was buffer-fixed.
-  @param latch   latch type */
-  void s_lock_register(ulint savepoint)
-  {
-    mtr_memo_slot_t &slot= m_memo->at(savepoint);
-    ut_ad(slot.type == MTR_MEMO_BUF_FIX);
-    slot.type= MTR_MEMO_PAGE_S_FIX;
   }
 
   /** Upgrade U locks on a block to X */
   void page_lock_upgrade(const buf_block_t &block);
-  /** Upgrade U lock to X */
-  void lock_upgrade(const index_lock &lock);
 
   /** Check if we are holding tablespace latch
   @param space  tablespace to search for
@@ -454,31 +381,66 @@ public:
   @retval nullptr    if not found */
   buf_block_t *memo_contains_page_flagged(const byte *ptr, ulint flags) const;
 
-  /** @return true if mini-transaction contains modifications. */
+  /** @return whether this mini-transaction modifies persistent data */
   bool has_modifications() const { return m_modifications; }
 #endif /* UNIV_DEBUG */
 
-  /** Push an object to an mtr memo stack.
+  /** Push a buffer page to an the memo.
-  @param object	object
+  @param block  buffer block
+  @param type	object type: MTR_MEMO_S_LOCK, ... */
+  void memo_push(buf_block_t *block, mtr_memo_type_t type)
+    __attribute__((nonnull))
+  {
+    ut_ad(is_active());
+    ut_ad(type <= MTR_MEMO_PAGE_SX_MODIFY);
+    ut_ad(block->page.buf_fix_count());
+    ut_ad(block->page.in_file());
+#ifdef UNIV_DEBUG
+    switch (type) {
+    case MTR_MEMO_PAGE_S_FIX:
+      ut_ad(block->page.lock.have_s());
+      break;
+    case MTR_MEMO_PAGE_X_FIX: case MTR_MEMO_PAGE_X_MODIFY:
+      ut_ad(block->page.lock.have_x());
+      break;
+    case MTR_MEMO_PAGE_SX_FIX: case MTR_MEMO_PAGE_SX_MODIFY:
+      ut_ad(block->page.lock.have_u_or_x());
+      break;
+    case MTR_MEMO_BUF_FIX:
+      break;
+    case MTR_MEMO_MODIFY:
+    case MTR_MEMO_S_LOCK: case MTR_MEMO_X_LOCK: case MTR_MEMO_SX_LOCK:
+    case MTR_MEMO_SPACE_X_LOCK: case MTR_MEMO_SPACE_S_LOCK:
+      ut_ad("invalid type" == 0);
+    }
+#endif
+    if (!(type & MTR_MEMO_MODIFY));
+    else if (block->page.id().space() >= SRV_TMP_SPACE_ID)
+    {
+      block->page.set_temp_modified();
+      type= mtr_memo_type_t(type & ~MTR_MEMO_MODIFY);
+    }
+    else
+    {
+      m_modifications= true;
+      if (!m_made_dirty)
+        /* If we are going to modify a previously clean persistent page,
+        we must set m_made_dirty, so that commit() will acquire
+        log_sys.flush_order_mutex and insert the block into
+        buf_pool.flush_list. */
+        m_made_dirty= block->page.oldest_modification() <= 1;
+    }
+    m_memo.emplace_back(mtr_memo_slot_t{block, type});
+  }
+
+  /** Push an index lock or tablespace latch to the memo.
+  @param object index lock or tablespace latch
   @param type	object type: MTR_MEMO_S_LOCK, ... */
   void memo_push(void *object, mtr_memo_type_t type) __attribute__((nonnull))
   {
     ut_ad(is_active());
-    /* If this mtr has U or X latched a clean page then we set
+    ut_ad(type >= MTR_MEMO_S_LOCK);
-    the m_made_dirty flag. This tells us if we need to
+    m_memo.emplace_back(mtr_memo_slot_t{object, type});
-    grab log_sys.flush_order_mutex at mtr_t::commit() so that we
-    can insert the dirtied page into the buf_pool.flush_list.
-
-    FIXME: Do this only when the MTR_MEMO_MODIFY flag is set! */
-    if (!m_made_dirty &&
-        (type & (MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX)))
-      m_made_dirty=
-        is_block_dirtied(*static_cast<const buf_page_t*>(object));
-
-    if (!m_memo)
-      m_memo= new std::vector<mtr_memo_slot_t>(1, {object, type});
-    else
-      m_memo->emplace_back(mtr_memo_slot_t{object, type});
   }
 
   /** @return the size of the log is empty */
@@ -783,7 +745,7 @@ private:
   /** specifies which operations should be logged; default MTR_LOG_ALL */
   uint16_t m_log_mode:2;
 
-  /** whether at least one buffer pool page was written to */
+  /** whether at least one persistent page was written to */
   uint16_t m_modifications:1;
 
   /** whether at least one previously clean buffer pool page was written to */
@@ -809,7 +771,7 @@ private:
 #endif /* UNIV_DEBUG */
 
   /** acquired dict_index_t::lock, fil_space_t::latch, buf_block_t */
-  std::vector<mtr_memo_slot_t> *m_memo= nullptr;
+  small_vector<mtr_memo_slot_t, 16> m_memo;
 
   /** mini-transaction log */
   mtr_buf_t m_log;

storage/innobase/include/small_vector.h

@@ -0,0 +1,100 @@
+/*****************************************************************************
+
+Copyright (c) 2023, MariaDB Corporation.
+
+This program is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free Software
+Foundation; version 2 of the License.
+
+This program is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License along with
+this program; if not, write to the Free Software Foundation, Inc.,
+51 Franklin Street, Fifth Floor, Boston, MA 02110-1335 USA
+
+*****************************************************************************/
+
+#pragma once
+/* A normally small vector, inspired by llvm::SmallVector */
+#include "my_global.h"
+#include <iterator>
+#include <memory>
+
+class small_vector_base
+{
+protected:
+  typedef uint32_t Size_T;
+  void *BeginX;
+  Size_T Size= 0, Capacity;
+  small_vector_base()= delete;
+  small_vector_base(void *small, size_t small_size)
+    : BeginX(small), Capacity(Size_T(small_size)) {}
+  ATTRIBUTE_COLD void grow_by_1(void *small, size_t element_size);
+public:
+  size_t size() const { return Size; }
+  size_t capacity() const { return Capacity; }
+  bool empty() const { return !Size; }
+  void clear() { Size= 0; }
+protected:
+  void set_size(size_t N) { Size= Size_T(N); }
+};
+
+template <typename T, unsigned N>
+class small_vector : public small_vector_base
+{
+  /** The fixed storage allocation */
+  T small[N];
+
+  using small_vector_base::set_size;
+
+  void grow_if_needed()
+  {
+    if (unlikely(size() >= capacity()))
+      grow_by_1(small, sizeof *small);
+  }
+
+public:
+  small_vector() : small_vector_base(small, N)
+  {
+    TRASH_ALLOC(small, sizeof small);
+  }
+  ~small_vector()
+  {
+    if (small != begin())
+      my_free(begin());
+    MEM_MAKE_ADDRESSABLE(small, sizeof small);
+  }
+
+  using iterator= T *;
+  using const_iterator= const T *;
+  using reverse_iterator= std::reverse_iterator<iterator>;
+  using reference= T &;
+  using const_reference= const T&;
+
+  iterator begin() { return static_cast<iterator>(BeginX); }
+  const_iterator begin() const { return static_cast<const_iterator>(BeginX); }
+  iterator end() { return begin() + size(); }
+  const_iterator end() const { return begin() + size(); }
+
+  reverse_iterator rbegin() { return reverse_iterator(end()); }
+  reverse_iterator rend() { return reverse_iterator(begin()); }
+
+  reference operator[](size_t i) { assert(i < size()); return begin()[i]; }
+  const_reference operator[](size_t i) const
+  { return const_cast<small_vector&>(*this)[i]; }
+
+  void erase(const_iterator S, const_iterator E)
+  {
+    set_size(std::move(const_cast<iterator>(E), end(),
+                       const_cast<iterator>(S)) - begin());
+  }
+
+  void emplace_back(T &&arg)
+  {
+    grow_if_needed();
+    ::new (end()) T(arg);
+    set_size(size() + 1);
+  }
+};

storage/innobase/mtr/mtr0mtr.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1995, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -37,6 +37,8 @@ Created 11/26/1995 Heikki Tuuri
 
 void mtr_memo_slot_t::release() const
 {
+  ut_ad(object);
+
   switch (type) {
   case MTR_MEMO_S_LOCK:
     static_cast<index_lock*>(object)->s_unlock();
@@ -153,10 +155,13 @@ inline void buf_pool_t::insert_into_flush_list(buf_page_t *prev,
   block->page.set_oldest_modification(lsn);
 }
 
+mtr_t::mtr_t()= default;
+mtr_t::~mtr_t()= default;
+
 /** Start a mini-transaction. */
 void mtr_t::start()
 {
-  ut_ad(!m_memo);
+  ut_ad(m_memo.empty());
   ut_ad(!m_freed_pages);
   ut_ad(!m_freed_space);
   MEM_UNDEFINED(this, sizeof *this);
@@ -188,7 +193,7 @@ void mtr_t::start()
 inline void mtr_t::release_resources()
 {
   ut_ad(is_active());
-  ut_ad(!m_memo);
+  ut_ad(m_memo.empty());
   m_log.erase();
   ut_d(m_commit= true);
 }
@@ -243,15 +248,13 @@ void mtr_t::release_unlogged()
 {
   ut_ad(m_log_mode == MTR_LOG_NO_REDO);
   ut_ad(m_log.size() == 0);
-  ut_ad(m_memo);
 
   process_freed_pages();
 
-  for (auto it= m_memo->rbegin(); it != m_memo->rend(); it++)
+  for (auto it= m_memo.rbegin(); it != m_memo.rend(); it++)
   {
     mtr_memo_slot_t &slot= *it;
-    if (!slot.object)
+    ut_ad(slot.object);
-      continue;
     switch (slot.type) {
     case MTR_MEMO_S_LOCK:
       static_cast<index_lock*>(slot.object)->s_unlock();
@@ -278,10 +281,8 @@ void mtr_t::release_unlogged()
       {
         ut_ad(slot.type == MTR_MEMO_PAGE_X_MODIFY ||
               slot.type == MTR_MEMO_PAGE_SX_MODIFY);
-        if (UNIV_LIKELY(block->page.id() >= end_page_id))
+        ut_ad(block->page.id() < end_page_id);
-          block->page.set_temp_modified();
+        insert_imported(block);
-        else
-          insert_imported(block);
       }
 
       switch (slot.type) {
@@ -300,23 +301,14 @@ void mtr_t::release_unlogged()
     }
   }
 
-  delete m_memo;
+  m_memo.clear();
-  m_memo= nullptr;
 }
 
 void mtr_t::release()
 {
-  if (m_memo)
+  for (auto it= m_memo.rbegin(); it != m_memo.rend(); it++)
-  {
+    it->release();
-    for (auto it= m_memo->rbegin(); it != m_memo->rend(); it++)
+  m_memo.clear();
-    {
-      mtr_memo_slot_t &slot= *it;
-      if (slot.object)
-        slot.release();
-    }
-    delete m_memo;
-    m_memo= nullptr;
-  }
 }
 
 /** Commit a mini-transaction. */
@@ -344,19 +336,18 @@ void mtr_t::commit()
 
     if (m_made_dirty)
     {
-      ut_ad(m_memo);
       size_t modified= 0;
-      auto it= m_memo->rbegin();
+      auto it= m_memo.rbegin();
 
       mysql_mutex_lock(&buf_pool.flush_list_mutex);
 
       buf_page_t *const prev=
         buf_pool.prepare_insert_into_flush_list(lsns.first);
 
-      while (it != m_memo->rend())
+      while (it != m_memo.rend())
       {
         const mtr_memo_slot_t &slot= *it++;
-        if (slot.object && slot.type & MTR_MEMO_MODIFY)
+        if (slot.type & MTR_MEMO_MODIFY)
         {
           ut_ad(slot.type == MTR_MEMO_PAGE_X_MODIFY ||
                 slot.type == MTR_MEMO_PAGE_SX_MODIFY);
@@ -401,72 +392,67 @@ void mtr_t::commit()
       else
         log_sys.latch.rd_unlock();
 
-      if (m_memo)
+      size_t modified= 0;
-      {
-        size_t modified= 0;
 
-        for (auto it= m_memo->rbegin(); it != m_memo->rend(); )
+      for (auto it= m_memo.rbegin(); it != m_memo.rend(); )
-        {
+      {
-          const mtr_memo_slot_t &slot= *it++;
+        const mtr_memo_slot_t &slot= *it++;
-          if (!slot.object)
+        ut_ad(slot.object);
-            continue;
+        switch (slot.type) {
-          switch (slot.type) {
+        case MTR_MEMO_S_LOCK:
-          case MTR_MEMO_S_LOCK:
+          static_cast<index_lock*>(slot.object)->s_unlock();
-            static_cast<index_lock*>(slot.object)->s_unlock();
+          break;
-            break;
+        case MTR_MEMO_SPACE_X_LOCK:
-          case MTR_MEMO_SPACE_X_LOCK:
+          static_cast<fil_space_t*>(slot.object)->set_committed_size();
-            static_cast<fil_space_t*>(slot.object)->set_committed_size();
+          static_cast<fil_space_t*>(slot.object)->x_unlock();
-            static_cast<fil_space_t*>(slot.object)->x_unlock();
+          break;
-            break;
+        case MTR_MEMO_SPACE_S_LOCK:
-          case MTR_MEMO_SPACE_S_LOCK:
+          static_cast<fil_space_t*>(slot.object)->s_unlock();
-            static_cast<fil_space_t*>(slot.object)->s_unlock();
+          break;
-            break;
+        case MTR_MEMO_X_LOCK:
-          case MTR_MEMO_X_LOCK:
+        case MTR_MEMO_SX_LOCK:
-          case MTR_MEMO_SX_LOCK:
+          static_cast<index_lock*>(slot.object)->
-            static_cast<index_lock*>(slot.object)->
+            u_or_x_unlock(slot.type == MTR_MEMO_SX_LOCK);
-              u_or_x_unlock(slot.type == MTR_MEMO_SX_LOCK);
+          break;
-            break;
+        default:
-          default:
+          buf_page_t *bpage= static_cast<buf_page_t*>(slot.object);
-            buf_page_t *bpage= static_cast<buf_page_t*>(slot.object);
+          const auto s= bpage->unfix();
-            const auto s= bpage->unfix();
+          if (slot.type & MTR_MEMO_MODIFY)
-            if (slot.type & MTR_MEMO_MODIFY)
+          {
+            ut_ad(slot.type == MTR_MEMO_PAGE_X_MODIFY ||
+                  slot.type == MTR_MEMO_PAGE_SX_MODIFY);
+            ut_ad(bpage->oldest_modification() > 1);
+            ut_ad(bpage->oldest_modification() < m_commit_lsn);
+            ut_ad(bpage->id() < end_page_id);
+            ut_ad(s >= buf_page_t::FREED);
+            ut_ad(s < buf_page_t::READ_FIX);
+            ut_ad(mach_read_from_8(bpage->frame + FIL_PAGE_LSN) <=
+                  m_commit_lsn);
+            if (s >= buf_page_t::UNFIXED)
             {
-              ut_ad(slot.type == MTR_MEMO_PAGE_X_MODIFY ||
+              mach_write_to_8(bpage->frame + FIL_PAGE_LSN, m_commit_lsn);
-                    slot.type == MTR_MEMO_PAGE_SX_MODIFY);
+              if (UNIV_LIKELY_NULL(bpage->zip.data))
-              ut_ad(bpage->oldest_modification() > 1);
+                memcpy_aligned<8>(FIL_PAGE_LSN + bpage->zip.data,
-              ut_ad(bpage->oldest_modification() < m_commit_lsn);
+                                  FIL_PAGE_LSN + bpage->frame, 8);
-              ut_ad(bpage->id() < end_page_id);
-              ut_ad(s >= buf_page_t::FREED);
-              ut_ad(s < buf_page_t::READ_FIX);
-              ut_ad(mach_read_from_8(bpage->frame + FIL_PAGE_LSN) <=
-                    m_commit_lsn);
-              if (s >= buf_page_t::UNFIXED)
-              {
-                mach_write_to_8(bpage->frame + FIL_PAGE_LSN, m_commit_lsn);
-                if (UNIV_LIKELY_NULL(bpage->zip.data))
-                  memcpy_aligned<8>(FIL_PAGE_LSN + bpage->zip.data,
-                                    FIL_PAGE_LSN + bpage->frame, 8);
-              }
-              modified++;
-            }
-            switch (auto latch= slot.type & ~MTR_MEMO_MODIFY) {
-            case MTR_MEMO_PAGE_S_FIX:
-              bpage->lock.s_unlock();
-              continue;
-            case MTR_MEMO_PAGE_SX_FIX:
-            case MTR_MEMO_PAGE_X_FIX:
-              bpage->lock.u_or_x_unlock(latch == MTR_MEMO_PAGE_SX_FIX);
-              continue;
-            default:
-              ut_ad(latch == MTR_MEMO_BUF_FIX);
             }
+            modified++;
+          }
+          switch (auto latch= slot.type & ~MTR_MEMO_MODIFY) {
+          case MTR_MEMO_PAGE_S_FIX:
+            bpage->lock.s_unlock();
+            continue;
+          case MTR_MEMO_PAGE_SX_FIX:
+          case MTR_MEMO_PAGE_X_FIX:
+            bpage->lock.u_or_x_unlock(latch == MTR_MEMO_PAGE_SX_FIX);
+            continue;
+          default:
+            ut_ad(latch == MTR_MEMO_BUF_FIX);
           }
         }
-
-        buf_pool.add_flush_list_requests(modified);
-        delete m_memo;
-        m_memo= nullptr;
       }
+
+      buf_pool.add_flush_list_requests(modified);
+      m_memo.clear();
     }
 
     if (UNIV_UNLIKELY(lsns.second != PAGE_FLUSH_NO))
@@ -481,16 +467,14 @@ func_exit:
 
 void mtr_t::rollback_to_savepoint(ulint begin, ulint end)
 {
-  ut_ad(m_memo);
+  ut_ad(end <= m_memo.size());
-  ut_ad(end <= m_memo->size());
   ut_ad(begin <= end);
   ulint s= end;
 
   while (s-- > begin)
   {
-    const mtr_memo_slot_t &slot= (*m_memo)[s];
+    const mtr_memo_slot_t &slot= m_memo[s];
-    if (!slot.object)
+    ut_ad(slot.object);
-      continue;
     /* This is intended for releasing latches on indexes or unmodified
     buffer pool pages. */
     ut_ad(slot.type <= MTR_MEMO_SX_LOCK);
@@ -498,7 +482,7 @@ void mtr_t::rollback_to_savepoint(ulint begin, ulint end)
     slot.release();
   }
 
-  m_memo->erase(m_memo->begin() + begin, m_memo->begin() + end);
+  m_memo.erase(m_memo.begin() + begin, m_memo.begin() + end);
 }
 
 /** Commit a mini-transaction that is shrinking a tablespace.
@@ -510,9 +494,10 @@ void mtr_t::commit_shrink(fil_space_t &space)
   ut_ad(!high_level_read_only);
   ut_ad(m_modifications);
   ut_ad(m_made_dirty);
-  ut_ad(m_memo);
+  ut_ad(!m_memo.empty());
   ut_ad(!recv_recovery_is_on());
   ut_ad(m_log_mode == MTR_LOG_ALL);
+  ut_ad(!m_freed_pages);
   ut_ad(UT_LIST_GET_LEN(space.chain) == 1);
 
   log_write_and_flush_prepare();
@@ -531,22 +516,21 @@ void mtr_t::commit_shrink(fil_space_t &space)
   os_file_truncate(space.chain.start->name, space.chain.start->handle,
                    os_offset_t{space.size} << srv_page_size_shift, true);
 
-  ut_ad(!m_freed_pages || m_freed_space == &space);
+  space.clear_freed_ranges();
-  process_freed_pages();
 
   const page_id_t high{space.id, space.size};
   size_t modified= 0;
-  auto it= m_memo->rbegin();
+  auto it= m_memo.rbegin();
   mysql_mutex_lock(&buf_pool.flush_list_mutex);
 
   buf_page_t *const prev= buf_pool.prepare_insert_into_flush_list(start_lsn);
 
-  while (it != m_memo->rend())
+  while (it != m_memo.rend())
   {
     mtr_memo_slot_t &slot= *it++;
 
-    if (!slot.object);
+    ut_ad(slot.object);
-    else if (slot.type == MTR_MEMO_SPACE_X_LOCK)
+    if (slot.type == MTR_MEMO_SPACE_X_LOCK)
       ut_ad(high.space() == static_cast<fil_space_t*>(slot.object)->id);
     else
     {
@@ -727,7 +711,7 @@ lsn_t mtr_t::commit_files(lsn_t checkpoint_lsn)
   ut_ad(!is_inside_ibuf());
   ut_ad(m_log_mode == MTR_LOG_ALL);
   ut_ad(!m_made_dirty);
-  ut_ad(!m_memo);
+  ut_ad(m_memo.empty());
   ut_ad(!srv_read_only_mode);
   ut_ad(!m_freed_space);
   ut_ad(!m_freed_pages);
@@ -837,19 +821,18 @@ void mtr_t::x_lock_space(fil_space_t *space)
 void mtr_t::release(const void *object)
 {
   ut_ad(is_active());
-  ut_ad(m_memo);
 
   auto it=
-    std::find_if(m_memo->begin(), m_memo->end(),
+    std::find_if(m_memo.begin(), m_memo.end(),
                  [object](const mtr_memo_slot_t& slot)
                  { return slot.object == object; });
-  ut_ad(it != m_memo->end());
+  ut_ad(it != m_memo.end());
   ut_ad(!(it->type & MTR_MEMO_MODIFY));
   it->release();
-  m_memo->erase(it);
+  m_memo.erase(it, it + 1);
-  ut_ad(std::find_if(m_memo->begin(), m_memo->end(),
+  ut_ad(std::find_if(m_memo.begin(), m_memo.end(),
                      [object](const mtr_memo_slot_t& slot)
-                     { return slot.object == &object; }) == m_memo->end());
+                     { return slot.object == &object; }) == m_memo.end());
 }
 
 static time_t log_close_warn_time;
@@ -1028,11 +1011,11 @@ std::pair<lsn_t,mtr_t::page_flush_ahead> mtr_t::do_write()
 #ifndef DBUG_OFF
   do
   {
-    if (!m_memo || m_log_mode != MTR_LOG_ALL)
+    if (m_log_mode != MTR_LOG_ALL)
       continue;
     DBUG_EXECUTE_IF("skip_page_checksum", continue;);
 
-    for (const mtr_memo_slot_t& slot : *m_memo)
+    for (const mtr_memo_slot_t& slot : m_memo)
       if (slot.type & MTR_MEMO_MODIFY)
       {
         const buf_page_t &b= *static_cast<const buf_page_t*>(slot.object);
@@ -1284,12 +1267,9 @@ mtr_t::finish_write(size_t len)
 
 bool mtr_t::have_x_latch(const buf_block_t &block) const
 {
-  if (!m_memo)
-    return false;
-
   ut_d(const mtr_memo_slot_t *found= nullptr);
 
-  for (const mtr_memo_slot_t &slot : *m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
   {
     if (slot.object != &block)
       continue;
@@ -1309,16 +1289,13 @@ bool mtr_t::have_x_latch(const buf_block_t &block) const
 
 bool mtr_t::have_u_or_x_latch(const buf_block_t &block) const
 {
-  if (m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
   {
-    for (const mtr_memo_slot_t &slot : *m_memo)
+    if (slot.object == &block &&
+        slot.type & (MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX))
     {
-      if (slot.object == &block &&
+      ut_ad(block.page.lock.have_u_or_x());
-          slot.type & (MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX))
+      return true;
-      {
-        ut_ad(block.page.lock.have_u_or_x());
-        return true;
-      }
     }
   }
   return false;
@@ -1330,18 +1307,15 @@ bool mtr_t::have_u_or_x_latch(const buf_block_t &block) const
 @return whether space.latch is being held */
 bool mtr_t::memo_contains(const fil_space_t& space, bool shared) const
 {
-  if (m_memo)
+  const mtr_memo_type_t type= shared
-  {
+    ? MTR_MEMO_SPACE_S_LOCK : MTR_MEMO_SPACE_X_LOCK;
-    const mtr_memo_type_t type= shared
-      ? MTR_MEMO_SPACE_S_LOCK : MTR_MEMO_SPACE_X_LOCK;
 
-    for (const mtr_memo_slot_t &slot : *m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
+  {
+    if (slot.object == &space && slot.type == type)
     {
-      if (slot.object == &space && slot.type == type)
+      ut_ad(shared || space.is_owner());
-      {
+      return true;
-        ut_ad(shared || space.is_owner());
-        return true;
-      }
     }
   }
 
@@ -1351,9 +1325,8 @@ bool mtr_t::memo_contains(const fil_space_t& space, bool shared) const
 void mtr_t::page_lock_upgrade(const buf_block_t &block)
 {
   ut_ad(block.page.lock.have_x());
-  ut_ad(m_memo);
 
-  for (mtr_memo_slot_t &slot : *m_memo)
+  for (mtr_memo_slot_t &slot : m_memo)
     if (slot.object == &block && slot.type & MTR_MEMO_PAGE_SX_FIX)
       slot.type= mtr_memo_type_t(slot.type ^
                                  (MTR_MEMO_PAGE_SX_FIX | MTR_MEMO_PAGE_X_FIX));
@@ -1363,16 +1336,6 @@ void mtr_t::page_lock_upgrade(const buf_block_t &block)
 #endif /* BTR_CUR_HASH_ADAPT */
 }
 
-void mtr_t::lock_upgrade(const index_lock &lock)
-{
-  ut_ad(lock.have_x());
-  ut_ad(m_memo);
-
-  for (mtr_memo_slot_t &slot : *m_memo)
-    if (slot.object == &lock && slot.type == MTR_MEMO_SX_LOCK)
-      slot.type= MTR_MEMO_X_LOCK;
-}
-
 /** Latch a buffer pool block.
 @param block    block to be latched
 @param rw_latch RW_S_LATCH, RW_SX_LATCH, RW_X_LATCH, RW_NO_LATCH */
@@ -1421,27 +1384,29 @@ done:
 void mtr_t::upgrade_buffer_fix(ulint savepoint, rw_lock_type_t rw_latch)
 {
   ut_ad(is_active());
-  ut_ad(m_memo);
+  mtr_memo_slot_t &slot= m_memo[savepoint];
-  ut_ad(savepoint < m_memo->size());
-
-  mtr_memo_slot_t &slot= (*m_memo)[savepoint];
   ut_ad(slot.type == MTR_MEMO_BUF_FIX);
   buf_block_t *block= static_cast<buf_block_t*>(slot.object);
   ut_d(const auto state= block->page.state());
   ut_ad(state > buf_page_t::UNFIXED);
   ut_ad(state > buf_page_t::WRITE_FIX || state < buf_page_t::READ_FIX);
+  static_assert(int{MTR_MEMO_PAGE_S_FIX} == int{RW_S_LATCH}, "");
+  static_assert(int{MTR_MEMO_PAGE_X_FIX} == int{RW_X_LATCH}, "");
+  static_assert(int{MTR_MEMO_PAGE_SX_FIX} == int{RW_SX_LATCH}, "");
+  slot.type= mtr_memo_type_t(rw_latch);
 
   switch (rw_latch) {
   default:
     ut_ad("invalid state" == 0);
     break;
+  case RW_S_LATCH:
+    block->page.lock.s_lock();
+    break;
   case RW_SX_LATCH:
-    slot.type= MTR_MEMO_PAGE_SX_FIX;
     block->page.lock.u_lock();
     ut_ad(!block->page.is_io_fixed());
     break;
   case RW_X_LATCH:
-    slot.type= MTR_MEMO_PAGE_X_FIX;
     block->page.lock.x_lock();
     ut_ad(!block->page.is_io_fixed());
   }
@@ -1463,27 +1428,24 @@ bool mtr_t::memo_contains(const index_lock &lock, mtr_memo_type_t type) const
   ut_ad(type == MTR_MEMO_X_LOCK || type == MTR_MEMO_S_LOCK ||
         type == MTR_MEMO_SX_LOCK);
 
-  if (m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
   {
-    for (const mtr_memo_slot_t &slot : *m_memo)
+    if (slot.object == &lock && slot.type == type)
     {
-      if (slot.object == &lock && slot.type == type)
+      switch (type) {
-      {
+      case MTR_MEMO_X_LOCK:
-        switch (type) {
+        ut_ad(lock.have_x());
-        case MTR_MEMO_X_LOCK:
+        break;
-          ut_ad(lock.have_x());
+      case MTR_MEMO_SX_LOCK:
-          break;
+        ut_ad(lock.have_u_or_x());
-        case MTR_MEMO_SX_LOCK:
+        break;
-          ut_ad(lock.have_u_or_x());
+      case MTR_MEMO_S_LOCK:
-          break;
+        ut_ad(lock.have_s());
-        case MTR_MEMO_S_LOCK:
+        break;
-          ut_ad(lock.have_s());
+      default:
-          break;
+        break;
-        default:
-          break;
-        }
-        return true;
       }
+      return true;
     }
   }
 
@@ -1511,7 +1473,7 @@ bool mtr_t::memo_contains_flagged(const void *object, ulint flags) const
                    MTR_MEMO_MODIFY)) ==
         !!(flags & (MTR_MEMO_X_LOCK | MTR_MEMO_SX_LOCK | MTR_MEMO_S_LOCK)));
 
-  for (const mtr_memo_slot_t &slot : *m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
   {
     if (object != slot.object)
       continue;
@@ -1546,9 +1508,10 @@ buf_block_t* mtr_t::memo_contains_page_flagged(const byte *ptr, ulint flags)
 {
   ptr= page_align(ptr);
 
-  for (const mtr_memo_slot_t &slot : *m_memo)
+  for (const mtr_memo_slot_t &slot : m_memo)
   {
-    if (!slot.object || !(flags & slot.type))
+    ut_ad(slot.object);
+    if (!(flags & slot.type))
       continue;
 
     buf_page_t *bpage= static_cast<buf_page_t*>(slot.object);
@@ -1569,35 +1532,84 @@ buf_block_t* mtr_t::memo_contains_page_flagged(const byte *ptr, ulint flags)
 
 /** Mark the given latched page as modified.
 @param block   page that will be modified */
-void mtr_t::modify(const buf_block_t &block)
+void mtr_t::set_modified(const buf_block_t &block)
 {
-  if (UNIV_UNLIKELY(!m_memo))
+  if (block.page.id().space() >= SRV_TMP_SPACE_ID)
   {
-    /* This must be PageConverter::update_page() in IMPORT TABLESPACE. */
+    const_cast<buf_block_t&>(block).page.set_temp_modified();
-    ut_ad(!block.page.in_LRU_list);
     return;
   }
 
-  mtr_memo_slot_t *found= nullptr;
+  m_modifications= true;
 
-  for (mtr_memo_slot_t &slot : *m_memo)
+  if (UNIV_UNLIKELY(m_log_mode == MTR_LOG_NONE))
+    return;
+
+  for (mtr_memo_slot_t &slot : m_memo)
   {
     if (slot.object == &block &&
         slot.type & (MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX))
     {
-      found= &slot;
+      if (slot.type & MTR_MEMO_MODIFY)
-      break;
+        ut_ad(m_made_dirty || block.page.oldest_modification() > 1);
+      else
+      {
+        slot.type= static_cast<mtr_memo_type_t>(slot.type | MTR_MEMO_MODIFY);
+        if (!m_made_dirty)
+          m_made_dirty= block.page.oldest_modification() <= 1;
+      }
+      return;
     }
   }
 
-  if (UNIV_UNLIKELY(!found))
+  /* This must be PageConverter::update_page() in IMPORT TABLESPACE. */
+  ut_ad(m_memo.empty());
+  ut_ad(!block.page.in_LRU_list);
+}
+
+void mtr_t::init(buf_block_t *b)
+{
+  const page_id_t id{b->page.id()};
+  ut_ad(is_named_space(id.space()));
+  ut_ad(!m_freed_pages == !m_freed_space);
+  ut_ad(memo_contains_flagged(b, MTR_MEMO_PAGE_X_FIX));
+
+  if (id.space() >= SRV_TMP_SPACE_ID)
+    b->page.set_temp_modified();
+  else
   {
-    ut_ad("modifying an unlatched page" == 0);
+    for (mtr_memo_slot_t &slot : m_memo)
-    return;
+    {
+      if (slot.object == b && slot.type & MTR_MEMO_PAGE_X_FIX)
+      {
+        slot.type= MTR_MEMO_PAGE_X_MODIFY;
+        m_modifications= true;
+        if (!m_made_dirty)
+          m_made_dirty= b->page.oldest_modification() <= 1;
+        goto found;
+      }
+    }
+    ut_ad("block not X-latched" == 0);
   }
-  found->type= static_cast<mtr_memo_type_t>(found->type | MTR_MEMO_MODIFY);
+
-  if (!m_made_dirty)
+ found:
-    m_made_dirty= is_block_dirtied(block.page);
+  if (UNIV_LIKELY_NULL(m_freed_space) &&
+      m_freed_space->id == id.space() &&
+      m_freed_pages->remove_if_exists(id.page_no()) &&
+      m_freed_pages->empty())
+  {
+    delete m_freed_pages;
+    m_freed_pages= nullptr;
+    m_freed_space= nullptr;
+  }
+
+  b->page.set_reinit(b->page.state() & buf_page_t::LRU_MASK);
+
+  if (!is_logged())
+    return;
+
+  m_log.close(log_write<INIT_PAGE>(id, &b->page));
+  m_last_offset= FIL_PAGE_TYPE;
 }
 
 /** Free a page.
@@ -1610,24 +1622,26 @@ void mtr_t::free(const fil_space_t &space, uint32_t offset)
 
   if (is_logged())
   {
-    ut_ad(m_memo);
     buf_block_t *freed= nullptr;
     const page_id_t id{space.id, offset};
 
-    for (auto it= m_memo->rbegin(); it != m_memo->rend(); it++)
+    for (auto it= m_memo.end(); it != m_memo.begin(); )
     {
+      it--;
+    next:
       mtr_memo_slot_t &slot= *it;
       buf_block_t *block= static_cast<buf_block_t*>(slot.object);
-      if (!block);
+      ut_ad(block);
-      else if (block == freed)
+      if (block == freed)
       {
         if (slot.type & (MTR_MEMO_PAGE_SX_FIX | MTR_MEMO_PAGE_X_FIX))
           slot.type= MTR_MEMO_PAGE_X_FIX;
         else
         {
           ut_ad(slot.type == MTR_MEMO_BUF_FIX);
-          slot.object= nullptr;
           block->page.unfix();
+          m_memo.erase(it, it + 1);
+          goto next;
         }
       }
       else if (slot.type & (MTR_MEMO_PAGE_X_FIX | MTR_MEMO_PAGE_SX_FIX) &&
@@ -1641,7 +1655,17 @@ void mtr_t::free(const fil_space_t &space, uint32_t offset)
           ut_d(bool upgraded=) block->page.lock.x_lock_upgraded();
           ut_ad(upgraded);
         }
-        slot.type= MTR_MEMO_PAGE_X_MODIFY;
+        if (id.space() >= SRV_TMP_SPACE_ID)
+        {
+          block->page.set_temp_modified();
+          slot.type= MTR_MEMO_PAGE_X_FIX;
+        }
+        else
+        {
+          slot.type= MTR_MEMO_PAGE_X_MODIFY;
+          if (!m_made_dirty)
+            m_made_dirty= block->page.oldest_modification() <= 1;
+        }
 #ifdef BTR_CUR_HASH_ADAPT
         if (block->index)
           btr_search_drop_page_hash_index(block, false);
@@ -1650,8 +1674,22 @@ void mtr_t::free(const fil_space_t &space, uint32_t offset)
       }
     }
 
-    if (freed && !m_made_dirty)
-      m_made_dirty= is_block_dirtied(freed->page);
     m_log.close(log_write<FREE_PAGE>(id, nullptr));
   }
 }
+
+void small_vector_base::grow_by_1(void *small, size_t element_size)
+{
+  const size_t cap= Capacity*= 2, s= cap * element_size;
+  void *new_begin;
+  if (BeginX == small)
+  {
+    new_begin= my_malloc(PSI_NOT_INSTRUMENTED, s, MYF(0));
+    memcpy(new_begin, BeginX, size() * element_size);
+    TRASH_FREE(small, size() * element_size);
+  }
+  else
+    new_begin= my_realloc(PSI_NOT_INSTRUMENTED, BeginX, s, MYF(0));
+
+  BeginX= new_begin;
+}

storage/innobase/row/row0import.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2012, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2015, 2022, MariaDB Corporation.
+Copyright (c) 2015, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1617,6 +1617,9 @@ inline dberr_t IndexPurge::purge_pessimistic_delete() noexcept
 dberr_t IndexPurge::purge() noexcept
 {
   btr_pcur_store_position(&m_pcur, &m_mtr);
+  m_mtr.commit();
+  m_mtr.start();
+  m_mtr.set_log_mode(MTR_LOG_NO_REDO);
   dberr_t err= purge_pessimistic_delete();
 
   m_mtr.start();

storage/innobase/row/row0ins.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, 2022, MariaDB Corporation.
+Copyright (c) 2016, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -314,8 +314,10 @@ row_ins_clust_index_entry_by_modify(
 	}
 
 	if (mode != BTR_MODIFY_TREE) {
-		ut_ad((mode & ulint(~BTR_ALREADY_S_LATCHED))
+		ut_ad(mode == BTR_MODIFY_LEAF
-		      == BTR_MODIFY_LEAF);
+		      || mode == BTR_MODIFY_LEAF_ALREADY_LATCHED
+		      || mode == BTR_MODIFY_ROOT_AND_LEAF
+		      || mode == BTR_MODIFY_ROOT_AND_LEAF_ALREADY_LATCHED);
 
 		/* Try optimistic updating of the record, keeping changes
 		within the page */
@@ -1621,8 +1623,7 @@ row_ins_check_foreign_constraint(
 
 	dtuple_set_n_fields_cmp(entry, foreign->n_fields);
 	pcur.btr_cur.page_cur.index = check_index;
-	err = btr_pcur_open(entry, PAGE_CUR_GE, BTR_SEARCH_LEAF, &pcur, 0,
+	err = btr_pcur_open(entry, PAGE_CUR_GE, BTR_SEARCH_LEAF, &pcur, &mtr);
-			    &mtr);
 	if (UNIV_UNLIKELY(err != DB_SUCCESS)) {
 		goto end_scan;
 	}
@@ -2119,7 +2120,7 @@ row_ins_scan_sec_index_for_duplicate(
 	pcur.btr_cur.page_cur.index = index;
 	trx_t* const trx = thr_get_trx(thr);
 	dberr_t err = btr_pcur_open(entry, PAGE_CUR_GE, BTR_SEARCH_LEAF,
-				    &pcur, 0, mtr);
+				    &pcur, mtr);
 	if (err != DB_SUCCESS) {
 		goto end_scan;
 	}
@@ -2546,8 +2547,8 @@ row_ins_index_entry_big_rec(
 		index->set_modified(mtr);
 	}
 
-	dberr_t error = btr_pcur_open(entry, PAGE_CUR_LE,
+	dberr_t error = btr_pcur_open(entry, PAGE_CUR_LE, BTR_MODIFY_TREE,
-				      BTR_MODIFY_TREE, &pcur, 0, &mtr);
+				      &pcur, &mtr);
 	if (error != DB_SUCCESS) {
 		return error;
 	}
@@ -2580,6 +2581,42 @@ but GCC 4.8.5 does not support pop_options. */
 # pragma GCC optimize ("O0")
 #endif
 
+#ifdef WITH_WSREP
+/** Start bulk insert operation for Galera by appending
+table-level exclusive key for bulk insert.
+@param trx transaction
+@param index index
+@retval false on success
+@retval true on failure */
+ATTRIBUTE_COLD static bool row_ins_wsrep_start_bulk(trx_t *trx, const dict_index_t &index)
+{
+  char db_buf[NAME_LEN + 1];
+  char tbl_buf[NAME_LEN + 1];
+  ulint	db_buf_len, tbl_buf_len;
+
+  if (!index.table->parse_name(db_buf, tbl_buf, &db_buf_len, &tbl_buf_len))
+  {
+    WSREP_ERROR("Parse_name for bulk insert failed: %s",
+                wsrep_thd_query(trx->mysql_thd));
+    trx->error_state = DB_ROLLBACK;
+    return true;
+  }
+
+  /* Append table-level exclusive key for bulk insert. */
+  const int rcode = wsrep_thd_append_table_key(trx->mysql_thd, db_buf,
+                                               tbl_buf, WSREP_SERVICE_KEY_EXCLUSIVE);
+  if (rcode)
+  {
+    WSREP_ERROR("Appending table key for bulk insert failed: %s, %d",
+                wsrep_thd_query(trx->mysql_thd), rcode);
+    trx->error_state = DB_ROLLBACK;
+    return true;
+  }
+
+  return false;
+}
+#endif
+
 /***************************************************************//**
 Tries to insert an entry into a clustered index, ignoring foreign key
 constraints. If a record with the same unique key is found, the other
@@ -2605,11 +2642,10 @@ row_ins_clust_index_entry_low(
 	que_thr_t*	thr)	/*!< in: query thread */
 {
 	btr_pcur_t	pcur;
-	btr_cur_t*	cursor;
 	dberr_t		err		= DB_SUCCESS;
 	big_rec_t*	big_rec		= NULL;
 	mtr_t		mtr;
-	ib_uint64_t	auto_inc	= 0;
+	uint64_t	auto_inc	= 0;
 	mem_heap_t*	offsets_heap	= NULL;
 	rec_offs	offsets_[REC_OFFS_NORMAL_SIZE];
 	rec_offs*	offsets         = offsets_;
@@ -2625,7 +2661,7 @@ row_ins_clust_index_entry_low(
 	ut_ad(!n_uniq || n_uniq == dict_index_get_n_unique(index));
 	ut_ad(!trx->in_rollback);
 
-	mtr_start(&mtr);
+	mtr.start();
 
 	if (index->table->is_temporary()) {
 		/* Disable REDO logging as the lifetime of temp-tables is
@@ -2665,6 +2701,13 @@ row_ins_clust_index_entry_low(
 						dfield->type.mtype,
 						dfield->type.prtype
 						& DATA_UNSIGNED);
+					if (auto_inc
+					    && mode != BTR_MODIFY_TREE) {
+						mode = btr_latch_mode(
+							BTR_MODIFY_ROOT_AND_LEAF
+							^ BTR_MODIFY_LEAF
+							^ mode);
+					}
 				}
 			}
 		}
@@ -2674,20 +2717,26 @@ row_ins_clust_index_entry_low(
 	the function will return in both low_match and up_match of the
 	cursor sensible values */
 	pcur.btr_cur.page_cur.index = index;
-	err = btr_pcur_open(entry, PAGE_CUR_LE, mode, &pcur, auto_inc, &mtr);
+	err = btr_pcur_open(entry, PAGE_CUR_LE, mode, &pcur, &mtr);
 	if (err != DB_SUCCESS) {
 		index->table->file_unreadable = true;
-commit_exit:
+err_exit:
 		mtr.commit();
 		goto func_exit;
 	}
 
-	cursor = btr_pcur_get_btr_cur(&pcur);
+	if (auto_inc) {
-	cursor->thr = thr;
+		buf_block_t* root
+			= mtr.at_savepoint(mode != BTR_MODIFY_ROOT_AND_LEAF);
+		ut_ad(index->page == root->page.id().page_no());
+		page_set_autoinc(root, auto_inc, &mtr, false);
+	}
+
+	btr_pcur_get_btr_cur(&pcur)->thr = thr;
 
 #ifdef UNIV_DEBUG
 	{
-		page_t*	page = btr_cur_get_page(cursor);
+		page_t*	page = btr_pcur_get_page(&pcur);
 		rec_t*	first_rec = page_rec_get_next(
 			page_get_infimum_rec(page));
 
@@ -2696,7 +2745,7 @@ commit_exit:
 	}
 #endif /* UNIV_DEBUG */
 
-	block = btr_cur_get_block(cursor);
+	block = btr_pcur_get_block(&pcur);
 
 	DBUG_EXECUTE_IF("row_ins_row_level", goto skip_bulk_insert;);
 
@@ -2710,7 +2759,7 @@ commit_exit:
 	    && !index->table->n_rec_locks
 	    && !index->table->is_active_ddl()
 	    && !index->table->has_spatial_index()
-	    && !trx->is_wsrep() /* FIXME: MDEV-24623 */
+	    && !index->table->versioned()
 	    && !thd_is_slave(trx->mysql_thd) /* FIXME: MDEV-24622 */) {
 		DEBUG_SYNC_C("empty_root_page_insert");
 
@@ -2722,7 +2771,7 @@ commit_exit:
 			if (err != DB_SUCCESS) {
 				trx->error_state = err;
 				trx->bulk_insert = false;
-				goto commit_exit;
+				goto err_exit;
 			}
 
 			if (index->table->n_rec_locks) {
@@ -2731,6 +2780,16 @@ avoid_bulk:
 				goto skip_bulk_insert;
 			}
 
+#ifdef WITH_WSREP
+			if (trx->is_wsrep())
+			{
+			    if (!wsrep_thd_is_local_transaction(trx->mysql_thd))
+				    goto skip_bulk_insert;
+			    if (row_ins_wsrep_start_bulk(trx, *index))
+				    goto err_exit;
+			}
+#endif /* WITH_WSREP */
+
 #ifdef BTR_CUR_HASH_ADAPT
 			if (btr_search_enabled) {
 				btr_search_x_lock_all();
@@ -2754,7 +2813,7 @@ avoid_bulk:
 				goto avoid_bulk;
 			}
 
-			goto commit_exit;
+			goto err_exit;
 		}
 	}
 
@@ -2765,7 +2824,7 @@ skip_bulk_insert:
 		ut_ad(index->is_instant());
 		ut_ad(!dict_index_is_online_ddl(index));
 
-		const rec_t* rec = btr_cur_get_rec(cursor);
+		const rec_t* rec = btr_pcur_get_rec(&pcur);
 
 		if (rec_get_info_bits(rec, page_rec_is_comp(rec))
 		    & REC_INFO_MIN_REC_FLAG) {
@@ -2774,16 +2833,17 @@ skip_bulk_insert:
 			goto err_exit;
 		}
 
-		ut_ad(!row_ins_must_modify_rec(cursor));
+		ut_ad(!row_ins_must_modify_rec(&pcur.btr_cur));
 		goto do_insert;
 	}
 
-	if (rec_is_metadata(btr_cur_get_rec(cursor), *index)) {
+	if (rec_is_metadata(btr_pcur_get_rec(&pcur), *index)) {
 		goto do_insert;
 	}
 
 	if (n_uniq
-	    && (cursor->up_match >= n_uniq || cursor->low_match >= n_uniq)) {
+	    && (pcur.btr_cur.up_match >= n_uniq
+		|| pcur.btr_cur.low_match >= n_uniq)) {
 
 		if (flags
 		    == (BTR_CREATE_FLAG | BTR_NO_LOCKING_FLAG
@@ -2791,7 +2851,7 @@ skip_bulk_insert:
 			/* Set no locks when applying log
 			in online table rebuild. Only check for duplicates. */
 			err = row_ins_duplicate_error_in_clust_online(
-				n_uniq, entry, cursor,
+				n_uniq, entry, &pcur.btr_cur,
 				&offsets, &offsets_heap);
 
 			switch (err) {
@@ -2802,26 +2862,24 @@ skip_bulk_insert:
 				/* fall through */
 			case DB_SUCCESS_LOCKED_REC:
 			case DB_DUPLICATE_KEY:
-				trx->error_info = cursor->index();
+				trx->error_info = index;
 			}
 		} else {
 			/* Note that the following may return also
 			DB_LOCK_WAIT */
 
 			err = row_ins_duplicate_error_in_clust(
-				flags, cursor, entry, thr);
+				flags, &pcur.btr_cur, entry, thr);
 		}
 
 		if (err != DB_SUCCESS) {
-err_exit:
+			goto err_exit;
-			mtr_commit(&mtr);
-			goto func_exit;
 		}
 	}
 
 	/* Note: Allowing duplicates would qualify for modification of
 	an existing record as the new entry is exactly same as old entry. */
-	if (row_ins_must_modify_rec(cursor)) {
+	if (row_ins_must_modify_rec(&pcur.btr_cur)) {
 		/* There is already an index entry with a long enough common
 		prefix, we must convert the insert into a modify of an
 		existing record */
@@ -2839,10 +2897,13 @@ do_insert:
 		rec_t*	insert_rec;
 
 		if (mode != BTR_MODIFY_TREE) {
-			ut_ad(mode == BTR_MODIFY_LEAF ||
+			ut_ad(mode == BTR_MODIFY_LEAF
-			      mode == BTR_MODIFY_LEAF_ALREADY_LATCHED);
+			      || mode == BTR_MODIFY_LEAF_ALREADY_LATCHED
+			      || mode == BTR_MODIFY_ROOT_AND_LEAF
+			      || mode
+			      == BTR_MODIFY_ROOT_AND_LEAF_ALREADY_LATCHED);
 			err = btr_cur_optimistic_insert(
-				flags, cursor, &offsets, &offsets_heap,
+				flags, &pcur.btr_cur, &offsets, &offsets_heap,
 				entry, &insert_rec, &big_rec,
 				n_ext, thr, &mtr);
 		} else {
@@ -2851,17 +2912,15 @@ do_insert:
 				goto err_exit;
 			}
 
-			DEBUG_SYNC_C("before_insert_pessimitic_row_ins_clust");
-
 			err = btr_cur_optimistic_insert(
-				flags, cursor,
+				flags, &pcur.btr_cur,
 				&offsets, &offsets_heap,
 				entry, &insert_rec, &big_rec,
 				n_ext, thr, &mtr);
 
 			if (err == DB_FAIL) {
 				err = btr_cur_pessimistic_insert(
-					flags, cursor,
+					flags, &pcur.btr_cur,
 					&offsets, &offsets_heap,
 					entry, &insert_rec, &big_rec,
 					n_ext, thr, &mtr);
@@ -2973,9 +3032,7 @@ row_ins_sec_index_entry_low(
 		rtr_init_rtr_info(&rtr_info, false, &cursor, index, false);
 		rtr_info_update_btr(&cursor, &rtr_info);
 
-		err = btr_cur_search_to_nth_level(0, entry,
+		err = rtr_insert_leaf(&cursor, entry, search_mode, &mtr);
-						  PAGE_CUR_RTREE_INSERT,
-						  search_mode, &cursor, &mtr);
 
 		if (err == DB_SUCCESS && search_mode == BTR_MODIFY_LEAF
 		    && rtr_info.mbr_adj) {
@@ -2991,9 +3048,8 @@ row_ins_sec_index_entry_low(
 			} else {
 				index->set_modified(mtr);
 			}
-			err = btr_cur_search_to_nth_level(
+			err = rtr_insert_leaf(&cursor, entry,
-				0, entry, PAGE_CUR_RTREE_INSERT,
+					      search_mode, &mtr);
-				search_mode, &cursor, &mtr);
 		}
 
 		DBUG_EXECUTE_IF(
@@ -3009,8 +3065,8 @@ row_ins_sec_index_entry_low(
 				   : BTR_INSERT));
 		}
 
-		err = btr_cur_search_to_nth_level(0, entry, PAGE_CUR_LE,
+		err = cursor.search_leaf(entry, PAGE_CUR_LE, search_mode,
-						  search_mode, &cursor, &mtr);
+					 &mtr);
 	}
 
 	if (err != DB_SUCCESS) {
@@ -3086,12 +3142,12 @@ row_ins_sec_index_entry_low(
 		prevent any insertion of a duplicate by another
 		transaction. Let us now reposition the cursor and
 		continue the insertion (bypassing the change buffer). */
-		err = btr_cur_search_to_nth_level(
+		err = cursor.search_leaf(
-			0, entry, PAGE_CUR_LE,
+			entry, PAGE_CUR_LE,
 			btr_latch_mode(search_mode
 				       & ~(BTR_INSERT
 					   | BTR_IGNORE_SEC_UNIQUE)),
-			&cursor, &mtr);
+			&mtr);
 		if (err != DB_SUCCESS) {
 			goto func_exit;
 		}

storage/innobase/row/row0log.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 2011, 2018, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1696,8 +1696,8 @@ err_exit:
 		mtr->start();
 		index->set_modified(*mtr);
 		pcur->btr_cur.page_cur.index = index;
-		error = btr_pcur_open(entry, PAGE_CUR_LE,
+		error = btr_pcur_open(entry, PAGE_CUR_LE, BTR_PURGE_TREE, pcur,
-				      BTR_PURGE_TREE, pcur, 0, mtr);
+				      mtr);
 		if (error) {
 			goto err_exit;
 		}
@@ -1780,8 +1780,8 @@ row_log_table_apply_delete(
 
 	mtr_start(&mtr);
 	index->set_modified(mtr);
-	dberr_t err = btr_pcur_open(old_pk, PAGE_CUR_LE,
+	dberr_t err = btr_pcur_open(old_pk, PAGE_CUR_LE, BTR_PURGE_TREE, &pcur,
-				    BTR_PURGE_TREE, &pcur, 0, &mtr);
+				    &mtr);
 	if (err != DB_SUCCESS) {
 		goto all_done;
 	}
@@ -1917,8 +1917,8 @@ row_log_table_apply_update(
 
 	mtr.start();
 	index->set_modified(mtr);
-	error = btr_pcur_open(old_pk, PAGE_CUR_LE,
+	error = btr_pcur_open(old_pk, PAGE_CUR_LE, BTR_MODIFY_TREE, &pcur,
-			      BTR_MODIFY_TREE, &pcur, 0, &mtr);
+			      &mtr);
 	if (error != DB_SUCCESS) {
 func_exit:
 		mtr.commit();
@@ -3084,11 +3084,8 @@ row_log_apply_op_low(
 	record. The operation may already have been performed,
 	depending on when the row in the clustered index was
 	scanned. */
-	*error = btr_cur_search_to_nth_level(0, entry, PAGE_CUR_LE,
+	*error = cursor.search_leaf(entry, PAGE_CUR_LE, has_index_lock
-					     has_index_lock
+				    ? BTR_MODIFY_TREE : BTR_MODIFY_LEAF, &mtr);
-					     ? BTR_MODIFY_TREE
-					     : BTR_MODIFY_LEAF,
-					     &cursor, &mtr);
 	if (UNIV_UNLIKELY(*error != DB_SUCCESS)) {
 		goto func_exit;
 	}
@@ -3138,9 +3135,9 @@ row_log_apply_op_low(
 				mtr_commit(&mtr);
 				mtr_start(&mtr);
 				index->set_modified(mtr);
-				*error = btr_cur_search_to_nth_level(
+				*error = cursor.search_leaf(entry, PAGE_CUR_LE,
-					0, entry, PAGE_CUR_LE,
+							    BTR_MODIFY_TREE,
-					BTR_MODIFY_TREE, &cursor, &mtr);
+							    &mtr);
 				if (UNIV_UNLIKELY(*error != DB_SUCCESS)) {
 					goto func_exit;
 				}
@@ -3242,9 +3239,9 @@ insert_the_rec:
 				mtr_commit(&mtr);
 				mtr_start(&mtr);
 				index->set_modified(mtr);
-				*error = btr_cur_search_to_nth_level(
+				*error = cursor.search_leaf(entry, PAGE_CUR_LE,
-					0, entry, PAGE_CUR_LE,
+							    BTR_MODIFY_TREE,
-					BTR_MODIFY_TREE, &cursor, &mtr);
+							    &mtr);
 				if (*error != DB_SUCCESS) {
 					break;
 				}

storage/innobase/row/row0merge.cc

@@ -150,9 +150,8 @@ public:
 					  false);
 			rtr_info_update_btr(&ins_cur, &rtr_info);
 
-			error = btr_cur_search_to_nth_level(
+			error = rtr_insert_leaf(&ins_cur, dtuple,
-				0, dtuple, PAGE_CUR_RTREE_INSERT,
+						BTR_MODIFY_LEAF, &mtr);
-				BTR_MODIFY_LEAF, &ins_cur, &mtr);
 
 			/* It need to update MBR in parent entry,
 			so change search mode to BTR_MODIFY_TREE */
@@ -164,10 +163,8 @@ public:
 				rtr_info_update_btr(&ins_cur, &rtr_info);
 				mtr.start();
 				index->set_modified(mtr);
-				error = btr_cur_search_to_nth_level(
+				error = rtr_insert_leaf(&ins_cur, dtuple,
-					0, dtuple,
+							BTR_MODIFY_TREE, &mtr);
-					PAGE_CUR_RTREE_INSERT,
-					BTR_MODIFY_TREE, &ins_cur, &mtr);
 			}
 
 			if (error == DB_SUCCESS) {
@@ -189,11 +186,8 @@ public:
 						  &ins_cur, index, false);
 
 				rtr_info_update_btr(&ins_cur, &rtr_info);
-				error = btr_cur_search_to_nth_level(
+				error = rtr_insert_leaf(&ins_cur, dtuple,
-					0, dtuple,
+							BTR_MODIFY_TREE, &mtr);
-					PAGE_CUR_RTREE_INSERT,
-					BTR_MODIFY_TREE,
-					&ins_cur, &mtr);
 
 				if (error == DB_SUCCESS) {
 					error = btr_cur_pessimistic_insert(

storage/innobase/row/row0purge.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1997, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -104,7 +104,7 @@ bool
 row_purge_remove_clust_if_poss_low(
 /*===============================*/
 	purge_node_t*	node,	/*!< in/out: row purge node */
-	btr_latch_mode	mode)	/*!< in: BTR_MODIFY_LEAF or BTR_MODIFY_TREE */
+	btr_latch_mode	mode)	/*!< in: BTR_MODIFY_LEAF or BTR_PURGE_TREE */
 {
 	dict_index_t* index = dict_table_get_first_index(node->table);
 	table_id_t table_id = 0;
@@ -342,17 +342,20 @@ row_purge_remove_sec_if_poss_tree(
 	ibool			success	= TRUE;
 	dberr_t			err;
 	mtr_t			mtr;
-	enum row_search_result	search_result;
 
 	log_free_check();
 	mtr.start();
 	index->set_modified(mtr);
 	pcur.btr_cur.page_cur.index = index;
 
-	search_result = row_search_index_entry(entry, BTR_PURGE_TREE,
+	if (index->is_spatial()) {
-					       &pcur, &mtr);
+		if (!rtr_search(entry, BTR_PURGE_TREE, &pcur, &mtr)) {
+			goto found;
+		}
+		goto func_exit;
+	}
 
-	switch (search_result) {
+	switch (row_search_index_entry(entry, BTR_PURGE_TREE, &pcur, &mtr)) {
 	case ROW_NOT_FOUND:
 		/* Not found.  This is a legitimate condition.  In a
 		rollback, InnoDB will remove secondary recs that would
@@ -381,6 +384,7 @@ row_purge_remove_sec_if_poss_tree(
 	which cannot be purged yet, requires its existence. If some requires,
 	we should do nothing. */
 
+found:
 	if (row_purge_poss_sec(node, index, entry, &pcur, &mtr, true)) {
 
 		/* Remove the index record, which should have been
@@ -439,8 +443,6 @@ row_purge_remove_sec_if_poss_leaf(
 {
 	mtr_t			mtr;
 	btr_pcur_t		pcur;
-	enum btr_latch_mode	mode;
-	enum row_search_result	search_result;
 	bool			success	= true;
 
 	log_free_check();
@@ -449,31 +451,27 @@ row_purge_remove_sec_if_poss_leaf(
 	mtr.start();
 	index->set_modified(mtr);
 
-	/* Change buffering is disabled for spatial index and
-	virtual index. */
-	mode = (index->type & (DICT_SPATIAL | DICT_VIRTUAL))
-		? BTR_MODIFY_LEAF : BTR_PURGE_LEAF;
 	pcur.btr_cur.page_cur.index = index;
 
 	/* Set the purge node for the call to row_purge_poss_sec(). */
 	pcur.btr_cur.purge_node = node;
 	if (index->is_spatial()) {
 		pcur.btr_cur.thr = NULL;
-		index->lock.u_lock(SRW_LOCK_CALL);
+		if (!rtr_search(entry, BTR_MODIFY_LEAF, &pcur, &mtr)) {
-		search_result = row_search_index_entry(
+			goto found;
-			entry, mode, &pcur, &mtr);
+		}
-		index->lock.u_unlock();
+		goto func_exit;
-	} else {
-		/* Set the query thread, so that ibuf_insert_low() will be
-		able to invoke thd_get_trx(). */
-		pcur.btr_cur.thr = static_cast<que_thr_t*>(
-			que_node_get_parent(node));
-		search_result = row_search_index_entry(
-			entry, mode, &pcur, &mtr);
 	}
 
-	switch (search_result) {
+	/* Set the query thread, so that ibuf_insert_low() will be
+	able to invoke thd_get_trx(). */
+	pcur.btr_cur.thr = static_cast<que_thr_t*>(que_node_get_parent(node));
+
+	switch (row_search_index_entry(entry, index->has_virtual()
+				       ? BTR_MODIFY_LEAF : BTR_PURGE_LEAF,
+				       &pcur, &mtr)) {
 	case ROW_FOUND:
+found:
 		/* Before attempting to purge a record, check
 		if it is safe to do so. */
 		if (row_purge_poss_sec(node, index, entry, &pcur, &mtr, false)) {

storage/innobase/row/row0row.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2018, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2018, 2022, MariaDB Corporation.
+Copyright (c) 2018, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1216,7 +1216,7 @@ row_search_on_row_ref(
 			& REC_INFO_MIN_REC_FLAG;
 	} else {
 		ut_a(ref->n_fields == index->n_uniq);
-		if (btr_pcur_open(ref, PAGE_CUR_LE, mode, pcur, 0, mtr)
+		if (btr_pcur_open(ref, PAGE_CUR_LE, mode, pcur, mtr)
 		    != DB_SUCCESS) {
 			return false;
 		}
@@ -1278,21 +1278,13 @@ row_search_index_entry(
 
 	ut_ad(dtuple_check_typed(entry));
 
-	if (pcur->index()->is_spatial()) {
+	if (btr_pcur_open(entry, PAGE_CUR_LE, mode, pcur, mtr) != DB_SUCCESS) {
-		if (rtr_pcur_open(pcur->index(), entry, mode, pcur, mtr)) {
+		return ROW_NOT_FOUND;
-			return ROW_NOT_FOUND;
-		}
-	} else {
-		if (btr_pcur_open(entry, PAGE_CUR_LE, mode, pcur, 0, mtr)
-		    != DB_SUCCESS) {
-			return ROW_NOT_FOUND;
-		}
 	}
 
 	switch (btr_pcur_get_btr_cur(pcur)->flag) {
 	case BTR_CUR_DELETE_REF:
 		ut_ad(!(~mode & BTR_DELETE));
-		ut_ad(!pcur->index()->is_spatial());
 		return(ROW_NOT_DELETED_REF);
 
 	case BTR_CUR_DEL_MARK_IBUF:

storage/innobase/row/row0sel.cc

@@ -2,7 +2,7 @@
 
 Copyright (c) 1997, 2017, Oracle and/or its affiliates. All Rights Reserved.
 Copyright (c) 2008, Google Inc.
-Copyright (c) 2015, 2022, MariaDB Corporation.
+Copyright (c) 2015, 2023, MariaDB Corporation.
 
 Portions of this file contain modifications contributed and copyrighted by
 Google, Inc. Those modifications are gratefully acknowledged and are described
@@ -4771,7 +4771,7 @@ wait_table_again:
 		pcur->btr_cur.thr = thr;
 		pcur->old_rec = nullptr;
 
-		if (dict_index_is_spatial(index)) {
+		if (index->is_spatial()) {
 			if (!prebuilt->rtr_info) {
 				prebuilt->rtr_info = rtr_create_rtr_info(
 					set_also_gap_locks, true,
@@ -4787,10 +4787,13 @@ wait_table_again:
 				prebuilt->rtr_info->search_tuple = search_tuple;
 				prebuilt->rtr_info->search_mode = mode;
 			}
-		}
 
-		err = btr_pcur_open_with_no_init(search_tuple, mode,
+			err = rtr_search_leaf(pcur, search_tuple, mode, &mtr);
-						 BTR_SEARCH_LEAF, pcur, &mtr);
+		} else {
+			err = btr_pcur_open_with_no_init(search_tuple, mode,
+							 BTR_SEARCH_LEAF,
+							 pcur, &mtr);
+		}
 
 		if (err != DB_SUCCESS) {
 page_corrupted:
@@ -5767,8 +5770,7 @@ next_rec_after_check:
 
 	if (spatial_search) {
 		/* No need to do store restore for R-tree */
-		mtr.commit();
+		mtr.rollback_to_savepoint(0);
-		mtr.start();
 	} else if (mtr_extra_clust_savepoint) {
 		/* We must release any clustered index latches
 		if we are moving to the next non-clustered

storage/innobase/row/row0uins.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1997, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -233,7 +233,7 @@ func_exit:
 	if (err == DB_SUCCESS && node->rec_type == TRX_UNDO_INSERT_METADATA) {
 		/* When rolling back the very first instant ADD COLUMN
 		operation, reset the root page to the basic state. */
-		err = btr_reset_instant(*index, true, &mtr);
+		btr_reset_instant(*index, true, &mtr);
 	}
 
 	btr_pcur_commit_specify_mtr(&node->pcur, &mtr);
@@ -268,21 +268,32 @@ row_undo_ins_remove_sec_low(
 	pcur.btr_cur.page_cur.index = index;
 	row_mtr_start(&mtr, index, !modify_leaf);
 
-	if (modify_leaf) {
-		mode = BTR_MODIFY_LEAF_ALREADY_LATCHED;
-		mtr_s_lock_index(index, &mtr);
-	} else {
-		ut_ad(mode == BTR_PURGE_TREE);
-		mtr_sx_lock_index(index, &mtr);
-	}
-
 	if (index->is_spatial()) {
 		mode = modify_leaf
-			? btr_latch_mode(BTR_MODIFY_LEAF_ALREADY_LATCHED
+			? btr_latch_mode(BTR_MODIFY_LEAF
 					 | BTR_RTREE_DELETE_MARK
 					 | BTR_RTREE_UNDO_INS)
 			: btr_latch_mode(BTR_PURGE_TREE | BTR_RTREE_UNDO_INS);
 		btr_pcur_get_btr_cur(&pcur)->thr = thr;
+		if (rtr_search(entry, mode, &pcur, &mtr)) {
+			goto func_exit;
+		}
+
+		if (rec_get_deleted_flag(
+			    btr_pcur_get_rec(&pcur),
+			    dict_table_is_comp(index->table))) {
+			ib::error() << "Record found in index " << index->name
+				<< " is deleted marked on insert rollback.";
+			ut_ad(0);
+		}
+		goto found;
+	} else if (modify_leaf) {
+		mode = BTR_MODIFY_LEAF_ALREADY_LATCHED;
+		mtr_s_lock_index(index, &mtr);
+	} else {
+		ut_ad(mode == BTR_PURGE_TREE);
+		mode = BTR_PURGE_TREE_ALREADY_LATCHED;
+		mtr_x_lock_index(index, &mtr);
 	}
 
 	switch (row_search_index_entry(entry, mode, &pcur, &mtr)) {
@@ -295,15 +306,7 @@ row_undo_ins_remove_sec_low(
 	case ROW_NOT_FOUND:
 		break;
 	case ROW_FOUND:
-		if (dict_index_is_spatial(index)
+        found:
-		    && rec_get_deleted_flag(
-			    btr_pcur_get_rec(&pcur),
-			    dict_table_is_comp(index->table))) {
-			ib::error() << "Record found in index " << index->name
-				<< " is deleted marked on insert rollback.";
-			ut_ad(0);
-		}
-
 		btr_cur_t* btr_cur = btr_pcur_get_btr_cur(&pcur);
 
 		if (modify_leaf) {
@@ -318,6 +321,7 @@ row_undo_ins_remove_sec_low(
 		}
 	}
 
+func_exit:
 	btr_pcur_close(&pcur);
 	mtr_commit(&mtr);
 

storage/innobase/row/row0umod.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1997, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, 2022, MariaDB Corporation.
+Copyright (c) 2017, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -133,8 +133,7 @@ row_undo_mod_clust_low(
 		    && node->ref == &trx_undo_metadata
 		    && btr_cur_get_index(btr_cur)->table->instant
 		    && node->update->info_bits == REC_INFO_METADATA_ADD) {
-			err = btr_reset_instant(*btr_cur_get_index(btr_cur),
+			btr_reset_instant(*btr_cur->index(), false, mtr);
-						false, mtr);
 		}
 	}
 
@@ -490,7 +489,6 @@ row_undo_mod_del_mark_or_remove_sec_low(
 	dberr_t			err	= DB_SUCCESS;
 	mtr_t			mtr;
 	mtr_t			mtr_vers;
-	row_search_result	search_result;
 	const bool		modify_leaf = mode == BTR_MODIFY_LEAF;
 
 	row_mtr_start(&mtr, index, !modify_leaf);
@@ -505,6 +503,11 @@ row_undo_mod_del_mark_or_remove_sec_low(
 					 | BTR_RTREE_UNDO_INS)
 			: btr_latch_mode(BTR_PURGE_TREE | BTR_RTREE_UNDO_INS);
 		btr_cur->thr = thr;
+		if (UNIV_LIKELY(!rtr_search(entry, mode, &pcur, &mtr))) {
+			goto found;
+		} else {
+			goto func_exit;
+		}
 	} else if (!index->is_committed()) {
 		/* The index->online_status may change if the index is
 		or was being created online, but not committed yet. It
@@ -514,7 +517,8 @@ row_undo_mod_del_mark_or_remove_sec_low(
 			mtr_s_lock_index(index, &mtr);
 		} else {
 			ut_ad(mode == BTR_PURGE_TREE);
-			mtr_sx_lock_index(index, &mtr);
+			mode = BTR_PURGE_TREE_ALREADY_LATCHED;
+			mtr_x_lock_index(index, &mtr);
 		}
 	} else {
 		/* For secondary indexes,
@@ -523,9 +527,8 @@ row_undo_mod_del_mark_or_remove_sec_low(
 		ut_ad(!dict_index_is_online_ddl(index));
 	}
 
-	search_result = row_search_index_entry(entry, mode, &pcur, &mtr);
+	switch (UNIV_EXPECT(row_search_index_entry(entry, mode, &pcur, &mtr),
-
+			    ROW_FOUND)) {
-	switch (UNIV_EXPECT(search_result, ROW_FOUND)) {
 	case ROW_NOT_FOUND:
 		/* In crash recovery, the secondary index record may
 		be missing if the UPDATE did not have time to insert
@@ -547,6 +550,7 @@ row_undo_mod_del_mark_or_remove_sec_low(
 		ut_error;
 	}
 
+found:
 	/* We should remove the index record if no prior version of the row,
 	which cannot be purged yet, requires its existence. If some requires,
 	we should delete mark the record. */
@@ -665,13 +669,12 @@ row_undo_mod_del_unmark_sec_and_undo_update(
 	trx_t*			trx		= thr_get_trx(thr);
 	const ulint		flags
 		= BTR_KEEP_SYS_FLAG | BTR_NO_LOCKING_FLAG;
-	row_search_result	search_result;
 	const auto		orig_mode = mode;
 
 	pcur.btr_cur.page_cur.index = index;
 	ut_ad(trx->id != 0);
 
-	if (dict_index_is_spatial(index)) {
+	if (index->is_spatial()) {
 		/* FIXME: Currently we do a 2-pass search for the undo
 		due to avoid undel-mark a wrong rec in rolling back in
 		partial update.  Later, we could log some info in
@@ -686,9 +689,22 @@ try_again:
 
 	btr_cur->thr = thr;
 
-	search_result = row_search_index_entry(entry, mode, &pcur, &mtr);
+	if (index->is_spatial()) {
+		if (!rtr_search(entry, mode, &pcur, &mtr)) {
+			goto found;
+		}
 
-	switch (search_result) {
+		if (mode != orig_mode && btr_cur->rtr_info->fd_del) {
+			mode = orig_mode;
+			btr_pcur_close(&pcur);
+			mtr.commit();
+			goto try_again;
+		}
+
+		goto not_found;
+	}
+
+	switch (row_search_index_entry(entry, mode, &pcur, &mtr)) {
 		mem_heap_t*	heap;
 		mem_heap_t*	offsets_heap;
 		rec_offs*	offsets;
@@ -699,17 +715,7 @@ try_again:
 		flags BTR_INSERT, BTR_DELETE, or BTR_DELETE_MARK. */
 		ut_error;
 	case ROW_NOT_FOUND:
-		/* For spatial index, if first search didn't find an
+not_found:
-		undel-marked rec, try to find a del-marked rec. */
-		if (dict_index_is_spatial(index) && btr_cur->rtr_info->fd_del) {
-			if (mode != orig_mode) {
-				mode = orig_mode;
-				btr_pcur_close(&pcur);
-				mtr_commit(&mtr);
-				goto try_again;
-			}
-		}
-
 		if (btr_cur->up_match >= dict_index_get_n_unique(index)
 		    || btr_cur->low_match >= dict_index_get_n_unique(index)) {
 			ib::warn() << "Record in index " << index->name
@@ -767,6 +773,7 @@ try_again:
 
 		break;
 	case ROW_FOUND:
+found:
 		btr_rec_set_deleted<false>(btr_cur_get_block(btr_cur),
 					   btr_cur_get_rec(btr_cur), &mtr);
 		heap = mem_heap_create(

storage/innobase/row/row0upd.cc

@@ -1,7 +1,7 @@
 /*****************************************************************************
 
 Copyright (c) 1996, 2017, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2015, 2022, MariaDB Corporation.
+Copyright (c) 2015, 2023, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -1832,12 +1832,10 @@ row_upd_sec_index_entry(
 	que_thr_t*	thr)	/*!< in: query thread */
 {
 	mtr_t			mtr;
-	const rec_t*		rec;
 	btr_pcur_t		pcur;
 	mem_heap_t*		heap;
 	dtuple_t*		entry;
 	dict_index_t*		index;
-	btr_cur_t*		btr_cur;
 	dberr_t			err	= DB_SUCCESS;
 	trx_t*			trx	= thr_get_trx(thr);
 	btr_latch_mode		mode;
@@ -1876,10 +1874,6 @@ row_upd_sec_index_entry(
 	case SRV_TMP_SPACE_ID:
 		mtr.set_log_mode(MTR_LOG_NO_REDO);
 		flags = BTR_NO_LOCKING_FLAG;
-		if (index->is_spatial()) {
-			mode = btr_latch_mode(BTR_MODIFY_LEAF
-					      | BTR_RTREE_DELETE_MARK);
-		}
 		break;
 	default:
 		index->set_modified(mtr);
@@ -1888,26 +1882,35 @@ row_upd_sec_index_entry(
 		flags = index->table->no_rollback() ? BTR_NO_ROLLBACK : 0;
 		/* We can only buffer delete-mark operations if there
 		are no foreign key constraints referring to the index. */
-		mode = index->is_spatial()
+		if (!referenced) {
-			? btr_latch_mode(BTR_MODIFY_LEAF
+			mode = BTR_DELETE_MARK_LEAF;
-					 | BTR_RTREE_DELETE_MARK)
+		}
-			: referenced
-			? BTR_MODIFY_LEAF : BTR_DELETE_MARK_LEAF;
 		break;
 	}
 
 	/* Set the query thread, so that ibuf_insert_low() will be
 	able to invoke thd_get_trx(). */
-	btr_pcur_get_btr_cur(&pcur)->thr = thr;
+	pcur.btr_cur.thr = thr;
 	pcur.btr_cur.page_cur.index = index;
 
+	if (index->is_spatial()) {
+		mode = btr_latch_mode(BTR_MODIFY_LEAF | BTR_RTREE_DELETE_MARK);
+		if (UNIV_LIKELY(!rtr_search(entry, mode, &pcur, &mtr))) {
+			goto found;
+		}
+
+		if (pcur.btr_cur.rtr_info->fd_del) {
+			/* We found the record, but a delete marked */
+			goto close;
+		}
+
+		goto not_found;
+	}
+
 	search_result = row_search_index_entry(entry, mode, &pcur, &mtr);
 
-	btr_cur = btr_pcur_get_btr_cur(&pcur);
-
-	rec = btr_cur_get_rec(btr_cur);
-
 	switch (search_result) {
+	const rec_t* rec;
 	case ROW_NOT_DELETED_REF:	/* should only occur for BTR_DELETE */
 		ut_error;
 		break;
@@ -1916,11 +1919,8 @@ row_upd_sec_index_entry(
 		break;
 
 	case ROW_NOT_FOUND:
-		if (dict_index_is_spatial(index) && btr_cur->rtr_info->fd_del) {
+not_found:
-			/* We found the record, but a delete marked */
+		rec = btr_pcur_get_rec(&pcur);
-			break;
-		}
-
 		ib::error()
 			<< "Record in index " << index->name
 			<< " of table " << index->table->name
@@ -1934,7 +1934,9 @@ row_upd_sec_index_entry(
 #endif /* UNIV_DEBUG */
 		break;
 	case ROW_FOUND:
+found:
 		ut_ad(err == DB_SUCCESS);
+		rec = btr_pcur_get_rec(&pcur);
 
 		/* Delete mark the old index record; it can already be
 		delete marked if we return after a lock wait in
@@ -1943,14 +1945,14 @@ row_upd_sec_index_entry(
 			    rec, dict_table_is_comp(index->table))) {
 			err = lock_sec_rec_modify_check_and_lock(
 				flags,
-				btr_cur_get_block(btr_cur),
+				btr_pcur_get_block(&pcur),
-				btr_cur_get_rec(btr_cur), index, thr, &mtr);
+				btr_pcur_get_rec(&pcur), index, thr, &mtr);
 			if (err != DB_SUCCESS) {
 				break;
 			}
 
-			btr_rec_set_deleted<true>(btr_cur_get_block(btr_cur),
+			btr_rec_set_deleted<true>(btr_pcur_get_block(&pcur),
-						  btr_cur_get_rec(btr_cur),
+						  btr_pcur_get_rec(&pcur),
 						  &mtr);
 #ifdef WITH_WSREP
 			if (!referenced && foreign
@@ -2009,6 +2011,7 @@ row_upd_sec_index_entry(
 		}
 	}
 
+close:
 	btr_pcur_close(&pcur);
 	mtr_commit(&mtr);
 

storage/innobase/trx/trx0purge.cc

@@ -426,7 +426,6 @@ static dberr_t trx_purge_free_segment(trx_rseg_t *rseg, fil_addr_t hdr_addr)
       block->fix();
       mtr.commit();
       mtr.start();
-      mtr.flag_modified();
       rseg->latch.wr_lock(SRW_LOCK_CALL);
       rseg_hdr->page.lock.x_lock();
       block->page.lock.x_lock();

storage/spider/ha_spider.cc

@@ -979,10 +979,8 @@ int ha_spider::reset()
   result_list.snap_direct_aggregate = FALSE;
   result_list.direct_distinct = FALSE;
   store_error_num = 0;
-  if (
+  if (wide_handler)
-    wide_handler &&
+  {
-    wide_handler->sql_command != SQLCOM_END
-  ) {
     wide_handler->sql_command = SQLCOM_END;
     wide_handler->between_flg = FALSE;
     wide_handler->idx_bitmap_is_set = FALSE;

storage/spider/mysql-test/spider/bugfix/r/mdev_30191.result

@@ -0,0 +1,44 @@
+#
+# MDEV-30191 SIGSEGV & heap-use-after-free in spider_db_print_item_type, SIGABRT in __cxa_pure_virtual/spider_db_print_item_type, Got error 128 "Out of memory in engine", 56/112 memory not freed, and Assertion `fixed()' failed in Item_sp_variable::val_str on SP call
+#
+for master_1
+for child2
+child2_1
+child2_2
+child2_3
+for child3
+connection child2_1;
+CREATE DATABASE auto_test_remote;
+USE auto_test_remote;
+CREATE TABLE tbl_a (c INT);
+connection master_1;
+CREATE DATABASE auto_test_local;
+USE auto_test_local;
+CREATE TABLE tbl_a (
+c INT
+) ENGINE=Spider DEFAULT CHARSET=utf8 COMMENT='table "tbl_a", srv "s_2_1"';
+CREATE TABLE tbl_b (c INT);
+CREATE PROCEDURE sp() BEGIN
+DECLARE v1 DATE;
+WHILE EXISTS (SELECT 1 FROM tbl_a WHERE c>v1 AND c<=v1) DO
+SELECT 1;
+END WHILE;
+WHILE EXISTS (SELECT 1
+FROM tbl_a
+WHERE c<v1 AND EXISTS (SELECT 1
+FROM tbl_b
+WHERE tbl_a.c=tbl_b.c)) DO
+SELECT 1;
+END WHILE; 
+END $$
+CALL sp();
+connection master_1;
+DROP DATABASE IF EXISTS auto_test_local;
+connection child2_1;
+DROP DATABASE IF EXISTS auto_test_remote;
+for master_1
+for child2
+child2_1
+child2_2
+child2_3
+for child3

storage/spider/mysql-test/spider/bugfix/t/mdev_30191.cnf

@@ -0,0 +1,3 @@
+!include include/default_mysqld.cnf
+!include ../my_1_1.cnf
+!include ../my_2_1.cnf

storage/spider/mysql-test/spider/bugfix/t/mdev_30191.test

@@ -0,0 +1,51 @@
+--echo #
+--echo # MDEV-30191 SIGSEGV & heap-use-after-free in spider_db_print_item_type, SIGABRT in __cxa_pure_virtual/spider_db_print_item_type, Got error 128 "Out of memory in engine", 56/112 memory not freed, and Assertion `fixed()' failed in Item_sp_variable::val_str on SP call
+--echo #
+ 
+--disable_query_log
+--disable_result_log
+--source ../../t/test_init.inc
+--enable_result_log
+--enable_query_log
+ 
+--connection child2_1
+CREATE DATABASE auto_test_remote;
+USE auto_test_remote;
+CREATE TABLE tbl_a (c INT);
+ 
+--connection master_1
+CREATE DATABASE auto_test_local;
+USE auto_test_local;
+ 
+eval CREATE TABLE tbl_a (
+    c INT
+) $MASTER_1_ENGINE $MASTER_1_CHARSET COMMENT='table "tbl_a", srv "s_2_1"';
+CREATE TABLE tbl_b (c INT);
+ 
+--delimiter $$
+CREATE PROCEDURE sp() BEGIN
+    DECLARE v1 DATE;
+    WHILE EXISTS (SELECT 1 FROM tbl_a WHERE c>v1 AND c<=v1) DO
+        SELECT 1;
+    END WHILE;
+    WHILE EXISTS (SELECT 1
+                 FROM tbl_a
+                 WHERE c<v1 AND EXISTS (SELECT 1
+                                       FROM tbl_b
+                                       WHERE tbl_a.c=tbl_b.c)) DO
+        SELECT 1;
+    END WHILE; 
+END $$
+--delimiter ;
+CALL sp();
+ 
+--connection master_1
+DROP DATABASE IF EXISTS auto_test_local;
+--connection child2_1
+DROP DATABASE IF EXISTS auto_test_remote;
+ 
+--disable_query_log
+--disable_result_log
+--source ../t/test_deinit.inc
+--enable_query_log
+--enable_result_log