From b349bf669f0ecd699b59358323d5529487f2a855 Mon Sep 17 00:00:00 2001 From: Peter Geoghegan Date: Tue, 6 Oct 2026 13:32:38 -0400 Subject: [PATCH v2_master] Rescind unsafe deduplication support. bpchar equality ignores trailing spaces, so equal values in a column with no length can have different images. Similarly, oidvector equality intentionally pays no attention to the array lower bound field. We nevertheless allowed nbtree deduplication to be used with indexes built with one of these opclass. This could lead to an index-only scan that returns the wrong value following a posting list split. To fix, drop support function 4 from all three affected opclasses on master and 19. It isn't possible to change catalog contents on earlier branches, so handle the problem there by explicitly teaching the relevant support functions to reject the two bpchar opclasses only. We deliberately avoid changing anything about the oidvector opclass on these earlier back branches, though. The oidvector issue is benign in practice, and it doesn't seem worth the trouble that it'd cause users who routinely run pg_amcheck. amcheck would otherwise flag affected system catalog indexes (such as pg_proc_proname_args_nsp_index) as containing a corrupt metapage, even though the underlying issue can't cause any harm with idiomatic usage within system catalogs. Author: Shihao Zhong Co-authored-by: Peter Geoghegan Reported-by: Ke Reported-by: Tom Lane Bug: #19749 Discussion: https://postgr.es/m/19749-d46adf7c7d910b07@postgresql.org Backpatch-through: 14 --- src/include/catalog/pg_amproc.dat | 7 ----- contrib/amcheck/verify_nbtree.c | 16 +--------- doc/src/sgml/btree.sgml | 14 ++++++--- src/test/regress/expected/opr_sanity.out | 40 +++++++++++++----------- 4 files changed, 32 insertions(+), 45 deletions(-) diff --git a/src/include/catalog/pg_amproc.dat b/src/include/catalog/pg_amproc.dat index 4a1efdbc8..27fb8cd2d 100644 --- a/src/include/catalog/pg_amproc.dat +++ b/src/include/catalog/pg_amproc.dat @@ -30,9 +30,6 @@ { amprocfamily => 'btree/bpchar_ops', amproclefttype => 'bpchar', amprocrighttype => 'bpchar', amprocnum => '2', amproc => 'bpchar_sortsupport' }, -{ amprocfamily => 'btree/bpchar_ops', amproclefttype => 'bpchar', - amprocrighttype => 'bpchar', amprocnum => '4', - amproc => 'btvarstrequalimage' }, { amprocfamily => 'btree/bytea_ops', amproclefttype => 'bytea', amprocrighttype => 'bytea', amprocnum => '1', amproc => 'byteacmp' }, { amprocfamily => 'btree/bytea_ops', amproclefttype => 'bytea', @@ -224,8 +221,6 @@ { amprocfamily => 'btree/oidvector_ops', amproclefttype => 'oidvector', amprocrighttype => 'oidvector', amprocnum => '1', amproc => 'btoidvectorcmp' }, -{ amprocfamily => 'btree/oidvector_ops', amproclefttype => 'oidvector', - amprocrighttype => 'oidvector', amprocnum => '4', amproc => 'btequalimage' }, { amprocfamily => 'btree/text_ops', amproclefttype => 'text', amprocrighttype => 'text', amprocnum => '1', amproc => 'bttextcmp' }, { amprocfamily => 'btree/text_ops', amproclefttype => 'text', @@ -273,8 +268,6 @@ { amprocfamily => 'btree/bpchar_pattern_ops', amproclefttype => 'bpchar', amprocrighttype => 'bpchar', amprocnum => '2', amproc => 'btbpchar_pattern_sortsupport' }, -{ amprocfamily => 'btree/bpchar_pattern_ops', amproclefttype => 'bpchar', - amprocrighttype => 'bpchar', amprocnum => '4', amproc => 'btequalimage' }, { amprocfamily => 'btree/money_ops', amproclefttype => 'money', amprocrighttype => 'money', amprocnum => '1', amproc => 'cash_cmp' }, { amprocfamily => 'btree/money_ops', amproclefttype => 'money', diff --git a/contrib/amcheck/verify_nbtree.c b/contrib/amcheck/verify_nbtree.c index c5e1f9010..b2ae22fc9 100644 --- a/contrib/amcheck/verify_nbtree.c +++ b/contrib/amcheck/verify_nbtree.c @@ -329,24 +329,10 @@ bt_index_check_callback(Relation indrel, Relation heaprel, void *state, bool rea errmsg("index \"%s\" metapage has equalimage field set on unsupported nbtree version", RelationGetRelationName(indrel)))); if (allequalimage && !_bt_allequalimage(indrel, false)) - { - bool has_interval_ops = false; - - for (int i = 0; i < IndexRelationGetNumberOfKeyAttributes(indrel); i++) - if (indrel->rd_opfamily[i] == INTERVAL_BTREE_FAM_OID) - { - has_interval_ops = true; - break; - } - ereport(ERROR, (errcode(ERRCODE_INDEX_CORRUPTED), errmsg("index \"%s\" metapage incorrectly indicates that deduplication is safe", - RelationGetRelationName(indrel)), - has_interval_ops - ? errhint("This is known of \"interval\" indexes last built on a version predating 2023-11.") - : 0)); - } + RelationGetRelationName(indrel)))); /* Check index, possibly against table it is an index on */ bt_check_every_level(indrel, heaprel, heapkeyspace, readonly, diff --git a/doc/src/sgml/btree.sgml b/doc/src/sgml/btree.sgml index 027361f20..78ba106bc 100644 --- a/doc/src/sgml/btree.sgml +++ b/doc/src/sgml/btree.sgml @@ -875,10 +875,16 @@ options(relopts local_relopts *) returns - text, varchar, and char - cannot use deduplication when a - nondeterministic collation is used. Case - and accent differences must be preserved among equal datums. + text and varchar cannot use deduplication when + a nondeterministic collation is used. Case and + accent differences must be preserved among equal datums. + + + + + + char cannot use deduplication. Trailing spaces must be + preserved among equal datums. diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 67cae3978..907d63daa 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -2225,25 +2225,27 @@ LEFT JOIN pg_amproc AS amp ON amp.amprocfamily = opf.oid AND WHERE am.amname = 'btree' AND amp.amproc IS DISTINCT FROM 'btequalimage'::regproc ORDER BY 1, 2, 3; - proc | opfamily_name | opclass_name | opcintype ---------------------+------------------+------------------+------------------ - btvarstrequalimage | bpchar_ops | bpchar_ops | character - btvarstrequalimage | text_ops | name_ops | name - btvarstrequalimage | text_ops | text_ops | text - btvarstrequalimage | text_ops | varchar_ops | text - | array_ops | array_ops | anyarray - | float_ops | float4_ops | real - | float_ops | float8_ops | double precision - | interval_ops | interval_ops | interval - | jsonb_ops | jsonb_ops | jsonb - | multirange_ops | multirange_ops | anymultirange - | numeric_ops | numeric_ops | numeric - | range_ops | range_ops | anyrange - | record_image_ops | record_image_ops | record - | record_ops | record_ops | record - | tsquery_ops | tsquery_ops | tsquery - | tsvector_ops | tsvector_ops | tsvector -(16 rows) + proc | opfamily_name | opclass_name | opcintype +--------------------+--------------------+--------------------+------------------ + btvarstrequalimage | text_ops | name_ops | name + btvarstrequalimage | text_ops | text_ops | text + btvarstrequalimage | text_ops | varchar_ops | text + | array_ops | array_ops | anyarray + | bpchar_ops | bpchar_ops | character + | bpchar_pattern_ops | bpchar_pattern_ops | character + | float_ops | float4_ops | real + | float_ops | float8_ops | double precision + | interval_ops | interval_ops | interval + | jsonb_ops | jsonb_ops | jsonb + | multirange_ops | multirange_ops | anymultirange + | numeric_ops | numeric_ops | numeric + | oidvector_ops | oidvector_ops | oidvector + | range_ops | range_ops | anyrange + | record_image_ops | record_image_ops | record + | record_ops | record_ops | record + | tsquery_ops | tsquery_ops | tsquery + | tsvector_ops | tsvector_ops | tsvector +(18 rows) -- **************** pg_index **************** -- Look for illegal values in pg_index fields. -- 2.55.0