Backport of WL#5953 from MySQL 5.6

The patch differs from the original MySQL patch as follows:
- All test case differences have been reviewed one by one, and
  care has been taken to restore the original plan so that each
  test case executes the code path it was designed for.
- A bug was found and fixed in MariaDB 5.3 in
  Item_allany_subselect::cleanup().
- ORDER BY is not removed because we are unsure of all effects,
  and it would prevent enabling ORDER BY ... LIMIT subqueries.
- ref_pointer_array.m_size is not adjusted because we don't do
  array bounds checking, and because it looks risky.

Original comment by Jorgen Loland:
-------------------------------------------------------------
WL#5953 - Optimize away useless subquery clauses
      
For IN/ALL/ANY/SOME/EXISTS subqueries, the following clauses are 
meaningless:
      
* ORDER BY (since we don't support LIMIT in these subqueries)
* DISTINCT
* GROUP BY if there is no HAVING clause and no aggregate 
  functions
      
This WL detects and optimizes away these useless parts of the
query during JOIN::prepare()

1 files changed, 17 insertions, 17 deletions

diff --git a/mysql-test/r/subselect_mat.result b/mysql-test/r/subselect_mat.result
index f368f787407..7225cf7c825 100644
--- a/mysql-test/r/subselect_mat.result
+++ b/mysql-test/r/subselect_mat.result
@@ -59,9 +59,9 @@ explain extended
 select * from t1 where a1 in (select b1 from t2 where b1 > '0' group by b1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
-2	MATERIALIZED	t2	ALL	NULL	NULL	NULL	NULL	5	100.00	Using where; Using temporary
+2	MATERIALIZED	t2	ALL	NULL	NULL	NULL	NULL	5	100.00	Using where
 Warnings:
-Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where <expr_cache><`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t1`.`a1`,`test`.`t1`.`a1` in ( <materialize> (select `test`.`t2`.`b1` from `test`.`t2` where (`test`.`t2`.`b1` > '0') group by `test`.`t2`.`b1` ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`))))))
+Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where <expr_cache><`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t1`.`a1`,`test`.`t1`.`a1` in ( <materialize> (select `test`.`t2`.`b1` from `test`.`t2` where (`test`.`t2`.`b1` > '0') ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`))))))
 select * from t1 where a1 in (select b1 from t2 where b1 > '0' group by b1);
 a1	a2
 1 - 01	2 - 01
@@ -70,9 +70,9 @@ explain extended
 select * from t1 where (a1, a2) in (select b1, b2 from t2 where b1 > '0' group by b1, b2);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
-2	MATERIALIZED	t2	ALL	NULL	NULL	NULL	NULL	5	100.00	Using where; Using temporary
+2	MATERIALIZED	t2	ALL	NULL	NULL	NULL	NULL	5	100.00	Using where
 Warnings:
-Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where <expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t2`.`b1`,`test`.`t2`.`b2` from `test`.`t2` where (`test`.`t2`.`b1` > '0') group by `test`.`t2`.`b1`,`test`.`t2`.`b2` ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1`.`a2` = `<subquery2>`.`b2`))))))
+Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where <expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t2`.`b1`,`test`.`t2`.`b2` from `test`.`t2` where (`test`.`t2`.`b1` > '0') ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1`.`a2` = `<subquery2>`.`b2`))))))
 select * from t1 where (a1, a2) in (select b1, b2 from t2 where b1 > '0' group by b1, b2);
 a1	a2
 1 - 01	2 - 01
@@ -100,13 +100,13 @@ a1	a2
 1 - 01	2 - 01
 1 - 02	2 - 02
 explain extended
-select * from t1i where a1 in (select b1 from t2i where b1 > '0' group by b1);
+select * from t1i where a1 in (select max(b1) from t2i where b1 > '0' group by b1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1i	index	NULL	#	18	#	3	100.00	#
-2	MATERIALIZED	t2i	range	it2i1,it2i3	#	9	#	3	100.00	#
+2	MATERIALIZED	t2i	index	it2i1,it2i3	#	9	#	5	100.00	#
 Warnings:
-Note	1003	select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where <expr_cache><`test`.`t1i`.`a1`>(<in_optimizer>(`test`.`t1i`.`a1`,`test`.`t1i`.`a1` in ( <materialize> (select `test`.`t2i`.`b1` from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') group by `test`.`t2i`.`b1` ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery2>`.`b1`))))))
-select * from t1i where a1 in (select b1 from t2i where b1 > '0' group by b1);
+Note	1003	select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where <expr_cache><`test`.`t1i`.`a1`>(<in_optimizer>(`test`.`t1i`.`a1`,`test`.`t1i`.`a1` in ( <materialize> (select max(`test`.`t2i`.`b1`) from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') group by `test`.`t2i`.`b1` ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery2>`.`max(b1)`))))))
+select * from t1i where a1 in (select max(b1) from t2i where b1 > '0' group by b1);
 a1	a2
 1 - 01	2 - 01
 1 - 02	2 - 02
@@ -122,13 +122,13 @@ a1	a2
 1 - 01	2 - 01
 1 - 02	2 - 02
 explain extended
-select * from t1i where (a1, a2) in (select b1, b2 from t2i where b1 > '0' group by b1, b2);
+select * from t1i where (a1, a2) in (select b1, max(b2) from t2i where b1 > '0' group by b1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1i	index	NULL	#	#	#	3	100.00	#
 2	MATERIALIZED	t2i	range	it2i1,it2i3	#	#	#	3	100.00	#
 Warnings:
-Note	1003	select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where <expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') group by `test`.`t2i`.`b1`,`test`.`t2i`.`b2` ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1i`.`a2` = `<subquery2>`.`b2`))))))
-select * from t1i where (a1, a2) in (select b1, b2 from t2i where b1 > '0' group by b1, b2);
+Note	1003	select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where <expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t2i`.`b1`,max(`test`.`t2i`.`b2`) from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') group by `test`.`t2i`.`b1` ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1i`.`a2` = `<subquery2>`.`max(b2)`))))))
+select * from t1i where (a1, a2) in (select b1, max(b2) from t2i where b1 > '0' group by b1);
 a1	a2
 1 - 01	2 - 01
 1 - 02	2 - 02
@@ -394,7 +394,7 @@ id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 8	MATERIALIZED	t2i	index	it2i1,it2i3	#	#	#	5	100.00	#
 NULL	UNION RESULT	<union1,7>	ALL	NULL	#	#	#	NULL	NULL	#
 Warnings:
-Note	1003	(select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where (<expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t2`.`b1`,`test`.`t2`.`b2` from `test`.`t2` where (<expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3`.`c2` from `test`.`t3` where (`test`.`t3`.`c2` like '%02') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery3>`.`c2`)))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3`.`c2` from `test`.`t3` where (`test`.`t3`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))) group by `test`.`t2`.`b1`,`test`.`t2`.`b2` ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1`.`a2` = `<subquery2>`.`b2`)))))) and <expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t3`.`c1`,`test`.`t3`.`c2` from `test`.`t3` where <expr_cache><`test`.`t3`.`c1`,`test`.`t3`.`c2`>(<in_optimizer>((`test`.`t3`.`c1`,`test`.`t3`.`c2`),(`test`.`t3`.`c1`,`test`.`t3`.`c2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b2` > '0') ), <primary_index_lookup>(`test`.`t3`.`c1` in <temporary table> on distinct_key where ((`test`.`t3`.`c1` = `<subquery6>`.`b1`) and (`test`.`t3`.`c2` = `<subquery6>`.`b2`)))))) ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery5>`.`c1`) and (`test`.`t1`.`a2` = `<subquery5>`.`c2`)))))))) union (select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where (<expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery8>`.`b1`) and (`test`.`t1i`.`a2` = `<subquery8>`.`b2`)))))) and <expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t3i`.`c1`,`test`.`t3i`.`c2` from `test`.`t3i` where <expr_cache><`test`.`t3i`.`c1`,`test`.`t3i`.`c2`>(<in_optimizer>((`test`.`t3i`.`c1`,`test`.`t3i`.`c2`),(`test`.`t3i`.`c1`,`test`.`t3i`.`c2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b2` > '0') ), <primary_index_lookup>(`test`.`t3i`.`c1` in <temporary table> on distinct_key where ((`test`.`t3i`.`c1` = `<subquery10>`.`b1`) and (`test`.`t3i`.`c2` = `<subquery10>`.`b2`)))))) ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery9>`.`c1`) and (`test`.`t1i`.`a2` = `<subquery9>`.`c2`))))))))
+Note	1003	(select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` where (<expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t2`.`b1`,`test`.`t2`.`b2` from `test`.`t2` where (<expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3`.`c2` from `test`.`t3` where (`test`.`t3`.`c2` like '%02') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery3>`.`c2`)))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3`.`c2` from `test`.`t3` where (`test`.`t3`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))) ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery2>`.`b1`) and (`test`.`t1`.`a2` = `<subquery2>`.`b2`)))))) and <expr_cache><`test`.`t1`.`a1`,`test`.`t1`.`a2`>(<in_optimizer>((`test`.`t1`.`a1`,`test`.`t1`.`a2`),(`test`.`t1`.`a1`,`test`.`t1`.`a2`) in ( <materialize> (select `test`.`t3`.`c1`,`test`.`t3`.`c2` from `test`.`t3` where <expr_cache><`test`.`t3`.`c1`,`test`.`t3`.`c2`>(<in_optimizer>((`test`.`t3`.`c1`,`test`.`t3`.`c2`),(`test`.`t3`.`c1`,`test`.`t3`.`c2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b2` > '0') ), <primary_index_lookup>(`test`.`t3`.`c1` in <temporary table> on distinct_key where ((`test`.`t3`.`c1` = `<subquery6>`.`b1`) and (`test`.`t3`.`c2` = `<subquery6>`.`b2`)))))) ), <primary_index_lookup>(`test`.`t1`.`a1` in <temporary table> on distinct_key where ((`test`.`t1`.`a1` = `<subquery5>`.`c1`) and (`test`.`t1`.`a2` = `<subquery5>`.`c2`)))))))) union (select `test`.`t1i`.`a1` AS `a1`,`test`.`t1i`.`a2` AS `a2` from `test`.`t1i` where (<expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b1` > '0') ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery8>`.`b1`) and (`test`.`t1i`.`a2` = `<subquery8>`.`b2`)))))) and <expr_cache><`test`.`t1i`.`a1`,`test`.`t1i`.`a2`>(<in_optimizer>((`test`.`t1i`.`a1`,`test`.`t1i`.`a2`),(`test`.`t1i`.`a1`,`test`.`t1i`.`a2`) in ( <materialize> (select `test`.`t3i`.`c1`,`test`.`t3i`.`c2` from `test`.`t3i` where <expr_cache><`test`.`t3i`.`c1`,`test`.`t3i`.`c2`>(<in_optimizer>((`test`.`t3i`.`c1`,`test`.`t3i`.`c2`),(`test`.`t3i`.`c1`,`test`.`t3i`.`c2`) in ( <materialize> (select `test`.`t2i`.`b1`,`test`.`t2i`.`b2` from `test`.`t2i` where (`test`.`t2i`.`b2` > '0') ), <primary_index_lookup>(`test`.`t3i`.`c1` in <temporary table> on distinct_key where ((`test`.`t3i`.`c1` = `<subquery10>`.`b1`) and (`test`.`t3i`.`c2` = `<subquery10>`.`b2`)))))) ), <primary_index_lookup>(`test`.`t1i`.`a1` in <temporary table> on distinct_key where ((`test`.`t1i`.`a1` = `<subquery9>`.`c1`) and (`test`.`t1i`.`a2` = `<subquery9>`.`c2`))))))))
 (select * from t1
 where (a1, a2) in (select b1, b2 from t2
 where b2 in (select c2 from t3 where c2 LIKE '%02') or
@@ -1150,21 +1150,21 @@ drop table t2;
 create table t1 (a1 int key);
 create table t2 (b1 int);
 insert into t1 values (5);
-explain select min(a1) from t1 where 7 in (select b1 from t2 group by b1);
+explain select min(a1) from t1 where 7 in (select max(b1) from t2 group by b1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	system	NULL	NULL	NULL	NULL	1	
 2	MATERIALIZED	t2	system	NULL	NULL	NULL	NULL	0	const row not found
-select min(a1) from t1 where 7 in (select b1 from t2 group by b1);
+select min(a1) from t1 where 7 in (select max(b1) from t2 group by b1);
 min(a1)
 NULL
 set @save_optimizer_switch=@@optimizer_switch;
 set @@optimizer_switch=@optimizer_switch_local_default;
 set @@optimizer_switch='materialization=off,in_to_exists=on';
-explain select min(a1) from t1 where 7 in (select b1 from t2 group by b1);
+explain select min(a1) from t1 where 7 in (select max(b1) from t2 group by b1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	system	NULL	NULL	NULL	NULL	1	
 2	DEPENDENT SUBQUERY	t2	system	NULL	NULL	NULL	NULL	0	const row not found
-select min(a1) from t1 where 7 in (select b1 from t2 group by b1);
+select min(a1) from t1 where 7 in (select max(b1) from t2 group by b1);
 min(a1)
 NULL
 set @@optimizer_switch=@optimizer_switch_local_default;
@@ -1231,7 +1231,7 @@ WHERE (t1i)  IN (
 SELECT t2i
 FROM t2  
 WHERE (t2i)  IN (  
-SELECT t3i
+SELECT max(t3i)
 FROM t3  
 GROUP BY t3i
 )