agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v31 08/11] Add aggregates support in IVM
573+ messages / 2 participants
[nested] [flat]

* [PATCH v31 08/11] Add aggregates support in IVM
@ 2023-05-31 11:46 Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:46 UTC (permalink / raw)

count, sum, adn avg are supported.

As a restriction, expressions specified in GROUP BY must appear in
the target list because tuples to be updated in IMMV are identified
by using this group key. However, in the case of aggregates without
GROUP BY, there is only one tuple in the view, so keys are not uses
to identify tuples.

When creating a IMMV, in addition to __ivm_count column, some hidden
columns for each aggregate are added to the target list. For example,
names of these hidden columns are ivm_count_avg and ivm_sum_avg for
the average function, and so on.

When a base table is modified, the aggregated values and related
hidden columns are also updated as well as __ivm_count__. The
way of update depends the kind of aggregate function.=E3=80=80Specifically,
sum and count are updated by simply adding or subtracting delta value
calculated from delta tables. avg is updated by using values of sum
and count stored in views as hidden columns and deltas calculated
from delta tables.

About aggregate functions except "count()" (sum and avg), NULLs in input
values are ignored, and the result of aggegate should be NULL when no
rows are selected.  To support this specification, the numbers of non-NULL
input values are counted and stored in hidden columns. In the case of
count(), count(x) returns zero when no rows are selected, but count(*)
doesn't ignore NULL input.
---
 src/backend/commands/createas.c | 265 +++++++++++++++++--
 src/backend/commands/matview.c  | 433 ++++++++++++++++++++++++++++++--
 src/include/commands/createas.h |   1 +
 3 files changed, 662 insertions(+), 37 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createa=
s.c
index 8f2bd5203e..aa8440b4e1 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -51,13 +51,19 @@
 #include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
+#include "utils/regproc.h"
+#include "utils/fmgroids.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
=20
 typedef struct
 {
@@ -71,6 +77,11 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_intorel;
=20
+typedef struct
+{
+	bool	has_agg;
+} check_ivm_restriction_context;
+
 /* utility functions for CTAS definition creation */
 static ObjectAddress create_ctas_internal(List *attrList, IntoClause *into=
);
 static ObjectAddress create_ctas_nodata(List *tlist, IntoClause *into);
@@ -85,8 +96,9 @@ static void CreateIvmTriggersOnBaseTablesRecurse(Query *q=
ry, Node *node, Oid mat
 									 Relids *relids, bool ex_lock);
 static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 ti=
ming, bool ex_lock);
 static void check_ivm_restriction(Node *node);
-static bool check_ivm_restriction_walker(Node *node, void *context);
+static bool check_ivm_restriction_walker(Node *node, check_ivm_restriction=
_context *context);
 static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **c=
onstraintList);
+static bool check_aggregate_supports_ivm(Oid aggfnoid);
=20
 /*
  * create_ctas_internal
@@ -417,6 +429,7 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt=
 *stmt,
  * rewriteQueryForIMMV -- rewrite view definition query for IMMV
  *
  * count(*) is added for counting distinct tuples in views.
+ * Also, additional hidden columns are added for aggregate values.
  */
 Query *
 rewriteQueryForIMMV(Query *query, List *colNames)
@@ -430,16 +443,49 @@ rewriteQueryForIMMV(Query *query, List *colNames)
 	rewritten =3D copyObject(query);
 	pstate->p_expr_kind =3D EXPR_KIND_SELECT_TARGET;
=20
-	/*
-	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
-	 * tuples in views.
-	 */
-	if (rewritten->distinctClause)
+	/* group keys must be in targetlist */
+	if (rewritten->groupClause)
 	{
-		TargetEntry *tle;
+		ListCell *lc;
+		foreach(lc, rewritten->groupClause)
+		{
+			SortGroupClause *scl =3D (SortGroupClause *) lfirst(lc);
+			TargetEntry *tle =3D get_sortgroupclause_tle(scl, rewritten->targetList=
);
=20
+			if (tle->resjunk)
+				ereport(ERROR,
+						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+						 errmsg("GROUP BY expression not appearing in select list is not sup=
ported on incrementally maintainable materialized view")));
+		}
+	}
+	/* Convert DISTINCT to GROUP BY.  count(*) will be added afterward. */
+	else if (!rewritten->hasAggs && rewritten->distinctClause)
 		rewritten->groupClause =3D transformDistinctClause(NULL, &rewritten->tar=
getList, rewritten->sortClause, false);
=20
+	/* Add additional columns for aggregate values */
+	if (rewritten->hasAggs)
+	{
+		ListCell *lc;
+		List *aggs =3D NIL;
+		AttrNumber next_resno =3D list_length(rewritten->targetList) + 1;
+
+		foreach(lc, rewritten->targetList)
+		{
+			TargetEntry *tle =3D (TargetEntry *) lfirst(lc);
+			char *resname =3D (colNames =3D=3D NIL || foreach_current_index(lc) >=
=3D list_length(colNames) ?
+								tle->resname : strVal(list_nth(colNames, tle->resno - 1)));
+
+			if (IsA(tle->expr, Aggref))
+				makeIvmAggColumn(pstate, (Aggref *) tle->expr, resname, &next_resno, &=
aggs);
+		}
+		rewritten->targetList =3D list_concat(rewritten->targetList, aggs);
+	}
+
+	/* Add count(*) for counting distinct tuples in views */
+	if (rewritten->distinctClause || rewritten->hasAggs)
+	{
+		TargetEntry *tle;
+
 		fn =3D makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, =
-1);
 		fn->agg_star =3D true;
=20
@@ -456,6 +502,91 @@ rewriteQueryForIMMV(Query *query, List *colNames)
 	return rewritten;
 }
=20
+/*
+ * makeIvmAggColumn -- make additional aggregate columns for IVM
+ *
+ * For an aggregate column specified by aggref, additional aggregate colum=
ns
+ * are added, which are used to calculate the new aggregate value in IMMV.
+ * An additional aggregate columns has a name based on resname
+ * (ex. ivm_count_resname), and resno specified by next_resno. The created
+ * columns are returned to aggs, and the resno for the next column is also
+ * returned to next_resno.
+ *
+ * Currently, an additional count() is created for aggref other than count.
+ * In addition, sum() is created for avg aggregate column.
+ */
+void
+makeIvmAggColumn(ParseState *pstate, Aggref *aggref, char *resname, AttrNu=
mber *next_resno, List **aggs)
+{
+	TargetEntry *tle_count;
+	Node *node;
+	FuncCall *fn;
+	Const	*dmy_arg =3D makeConst(INT4OID,
+								 -1,
+								 InvalidOid,
+								 sizeof(int32),
+								 Int32GetDatum(1),
+								 false,
+								 true); /* pass by value */
+	const char *aggname =3D get_func_name(aggref->aggfnoid);
+
+	/*
+	 * For aggregate functions except count, add count() func with the same a=
rg parameters.
+	 * This count result is used for determining if the aggregate value shoul=
d be NULL or not.
+	 * Also, add sum() func for avg because we need to calculate an average v=
alue as sum/count.
+	 *
+	 * XXX: If there are same expressions explicitly in the target list, we c=
an use this instead
+	 * of adding new duplicated one.
+	 */
+	if (strcmp(aggname, "count") !=3D 0)
+	{
+		fn =3D makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, =
-1);
+
+		/* Make a Func with a dummy arg, and then override this by the original =
agg's args. */
+		node =3D ParseFuncOrColumn(pstate, fn->funcname, list_make1(dmy_arg), NU=
LL, fn, false, -1);
+		((Aggref *)node)->args =3D aggref->args;
+
+		tle_count =3D makeTargetEntry((Expr *) node,
+									*next_resno,
+									pstrdup(makeObjectName("__ivm_count",resname, "_")),
+									false);
+		*aggs =3D lappend(*aggs, tle_count);
+		(*next_resno)++;
+	}
+	if (strcmp(aggname, "avg") =3D=3D 0)
+	{
+		List *dmy_args =3D NIL;
+		ListCell *lc;
+		foreach(lc, aggref->aggargtypes)
+		{
+			Oid		typeid =3D lfirst_oid(lc);
+			Type	type =3D typeidType(typeid);
+
+			Const *con =3D makeConst(typeid,
+								   -1,
+								   typeTypeCollation(type),
+								   typeLen(type),
+								   (Datum) 0,
+								   true,
+								   typeByVal(type));
+			dmy_args =3D lappend(dmy_args, con);
+			ReleaseSysCache(type);
+		}
+		fn =3D makeFuncCall(SystemFuncName("sum"), NIL, COERCE_EXPLICIT_CALL, -1=
);
+
+		/* Make a Func with dummy args, and then override this by the original a=
gg's args. */
+		node =3D ParseFuncOrColumn(pstate, fn->funcname, dmy_args, NULL, fn, fal=
se, -1);
+		((Aggref *)node)->args =3D aggref->args;
+
+		tle_count =3D makeTargetEntry((Expr *) node,
+									*next_resno,
+									pstrdup(makeObjectName("__ivm_sum",resname, "_")),
+									false);
+		*aggs =3D lappend(*aggs, tle_count);
+		(*next_resno)++;
+	}
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -939,11 +1070,13 @@ CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type=
, int16 timing, bool ex_lock
 static void
 check_ivm_restriction(Node *node)
 {
-	check_ivm_restriction_walker(node, NULL);
+	check_ivm_restriction_context context =3D {false};
+
+	check_ivm_restriction_walker(node, &context);
 }
=20
 static bool
-check_ivm_restriction_walker(Node *node, void *context)
+check_ivm_restriction_walker(Node *node, check_ivm_restriction_context *co=
ntext)
 {
 	if (node =3D=3D NULL)
 		return false;
@@ -972,6 +1105,10 @@ check_ivm_restriction_walker(Node *node, void *contex=
t)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 							 errmsg("CTE is not supported on incrementally maintainable materia=
lized view")));
+				if (qry->groupClause !=3D NIL && !qry->hasAggs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUP BY clause without aggregate is not supported on incr=
ementally maintainable materialized view")));
 				if (qry->havingQual !=3D NULL)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -1024,6 +1161,8 @@ check_ivm_restriction_walker(Node *node, void *contex=
t)
 					}
 				}
=20
+				context->has_agg |=3D qry->hasAggs;
+
 				/* restrictions for rtable */
 				foreach(lc, qry->rtable)
 				{
@@ -1072,7 +1211,7 @@ check_ivm_restriction_walker(Node *node, void *contex=
t)
=20
 				}
=20
-				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_=
RANGE_TABLE);
+				query_tree_walker(qry, check_ivm_restriction_walker, (void *) context,=
 QTW_IGNORE_RANGE_TABLE);
=20
 				break;
 			}
@@ -1083,8 +1222,12 @@ check_ivm_restriction_walker(Node *node, void *conte=
xt)
 						ereport(ERROR,
 								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 								 errmsg("column name %s is not supported on incrementally maintain=
able materialized view", tle->resname)));
+				if (context->has_agg && !IsA(tle->expr, Aggref) && contain_aggs_of_lev=
el((Node *) tle->expr, 0))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("expression containing an aggregate in it is not supported =
on incrementally maintainable materialized view")));
=20
-				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				expression_tree_walker(node, check_ivm_restriction_walker, (void *) co=
ntext);
 				break;
 			}
 		case T_JoinExpr:
@@ -1096,14 +1239,36 @@ check_ivm_restriction_walker(Node *node, void *cont=
ext)
 								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 								 errmsg("OUTER JOIN is not supported on incrementally maintainable=
 materialized view")));
=20
-				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				expression_tree_walker(node, check_ivm_restriction_walker, (void *) co=
ntext);
+				break;
 			}
-			break;
 		case T_Aggref:
-			ereport(ERROR,
-					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("aggregate function is not supported on incrementally maintai=
nable materialized view")));
-			break;
+			{
+				/* Check if this supports IVM */
+				Aggref *aggref =3D (Aggref *) node;
+				const char *aggname =3D format_procedure(aggref->aggfnoid);
+
+				if (aggref->aggfilter !=3D NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("aggregate function with FILTER clause is not supported on =
incrementally maintainable materialized view")));
+
+				if (aggref->aggdistinct !=3D NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("aggregate function with DISTINCT arguments is not supporte=
d on incrementally maintainable materialized view")));
+
+				if (aggref->aggorder !=3D NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("aggregate function with ORDER clause is not supported on i=
ncrementally maintainable materialized view")));
+
+				if (!check_aggregate_supports_ivm(aggref->aggfnoid))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("aggregate function %s is not supported on incrementally ma=
intainable materialized view", aggname)));
+				break;
+			}
 		default:
 			expression_tree_walker(node, check_ivm_restriction_walker, (void *) con=
text);
 			break;
@@ -1111,6 +1276,46 @@ check_ivm_restriction_walker(Node *node, void *conte=
xt)
 	return false;
 }
=20
+/*
+ * check_aggregate_supports_ivm
+ *
+ * Check if the given aggregate function is supporting IVM
+ */
+static bool
+check_aggregate_supports_ivm(Oid aggfnoid)
+{
+	switch (aggfnoid)
+	{
+		/* count */
+		case F_COUNT_ANY:
+		case F_COUNT_:
+
+		/* sum */
+		case F_SUM_INT8:
+		case F_SUM_INT4:
+		case F_SUM_INT2:
+		case F_SUM_FLOAT4:
+		case F_SUM_FLOAT8:
+		case F_SUM_MONEY:
+		case F_SUM_INTERVAL:
+		case F_SUM_NUMERIC:
+
+		/* avg */
+		case F_AVG_INT8:
+		case F_AVG_INT4:
+		case F_AVG_INT2:
+		case F_AVG_NUMERIC:
+		case F_AVG_FLOAT4:
+		case F_AVG_FLOAT8:
+		case F_AVG_INTERVAL:
+
+			return true;
+
+		default:
+			return false;
+	}
+}
+
 /*
  * CreateIndexOnIMMV
  *
@@ -1168,7 +1373,29 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	index->concurrent =3D false;
 	index->if_not_exists =3D false;
=20
-	if (query->distinctClause)
+	if (query->groupClause)
+	{
+		/* create unique constraint on GROUP BY expression columns */
+		foreach(lc, query->groupClause)
+		{
+			SortGroupClause *scl =3D (SortGroupClause *) lfirst(lc);
+			TargetEntry *tle =3D get_sortgroupclause_tle(scl, query->targetList);
+			Form_pg_attribute attr =3D TupleDescAttr(matviewRel->rd_att, tle->resno=
 - 1);
+			IndexElem  *iparam;
+
+			iparam =3D makeNode(IndexElem);
+			iparam->name =3D pstrdup(NameStr(attr->attname));
+			iparam->expr =3D NULL;
+			iparam->indexcolname =3D NULL;
+			iparam->collation =3D NIL;
+			iparam->opclass =3D NIL;
+			iparam->opclassopts =3D NIL;
+			iparam->ordering =3D SORTBY_DEFAULT;
+			iparam->nulls_ordering =3D SORTBY_NULLS_DEFAULT;
+			index->indexParams =3D lappend(index->indexParams, iparam);
+		}
+	}
+	else if (query->distinctClause)
 	{
 		/* create unique constraint on all columns */
 		foreach(lc, query->targetList)
@@ -1226,7 +1453,7 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 					(errmsg("could not create an index on materialized view \"%s\" automa=
tically",
 							RelationGetRelationName(matviewRel)),
 					 errdetail("This target list does not have all the primary key column=
s, "
-							   "or this view does not contain DISTINCT clause."),
+							   "or this view does not contain GROUP BY or DISTINCT clause."),
 					 errhint("Create an index on the materialized view for efficient incr=
emental maintenance.")));
 			return;
 		}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f2e8aa02a3..97406b28c9 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -27,6 +27,7 @@
 #include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -36,6 +37,7 @@
 #include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
 #include "nodes/makefuncs.h"
+#include "optimizer/optimizer.h"
 #include "parser/analyze.h"
 #include "parser/parse_clause.h"
 #include "parser/parse_func.h"
@@ -107,6 +109,13 @@ static HTAB *mv_trigger_info =3D NULL;
=20
 static bool in_delta_calculation =3D false;
=20
+/* kind of IVM operation for the view */
+typedef enum
+{
+	IVM_ADD,
+	IVM_SUB
+} IvmOp;
+
 /* ENR name for materialized view delta */
 #define NEW_DELTA_ENRNAME "new_delta"
 #define OLD_DELTA_ENRNAME "old_delta"
@@ -138,7 +147,7 @@ static RangeTblEntry *get_prestate_rte(RangeTblEntry *r=
te, MV_TriggerTable *tabl
 				 QueryEnvironment *queryEnv, Oid matviewid);
 static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_Trigge=
rTable *table, bool is_new,
 		   QueryEnvironment *queryEnv);
-static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+static Query *rewrite_query_for_counting_and_aggregates(Query *query, Pars=
eState *pstate);
=20
 static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
 			DestReceiver *dest_old, DestReceiver *dest_new,
@@ -149,14 +158,27 @@ static Query *rewrite_query_for_postupdate_state(Quer=
y *query, MV_TriggerTable *
 static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, =
Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
 			Query *query, bool use_count, char *count_colname);
+static void append_set_clause_for_count(const char *resname, StringInfo bu=
f_old,
+							StringInfo buf_new,StringInfo aggs_list);
+static void append_set_clause_for_sum(const char *resname, StringInfo buf_=
old,
+						  StringInfo buf_new, StringInfo aggs_list);
+static void append_set_clause_for_avg(const char *resname, StringInfo buf_=
old,
+						  StringInfo buf_new, StringInfo aggs_list,
+						  const char *aggtype);
+static char *get_operation_string(IvmOp op, const char *col, const char *a=
rg1, const char *arg2,
+					 const char* count_col, const char *castType);
+static char *get_null_condition_string(IvmOp op, const char *arg1, const c=
har *arg2,
+						  const char* count_col);
 static void apply_old_delta(const char *matviewname, const char *deltaname=
_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char=
 *deltaname_old,
-				List *keys, const char *count_colname);
+				List *keys, StringInfo aggs_list, StringInfo aggs_set,
+				const char *count_colname);
 static void apply_new_delta(const char *matviewname, const char *deltaname=
_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char=
* deltaname_new,
-				List *keys, StringInfo target_list, const char* count_colname);
+				List *keys, StringInfo target_list, StringInfo aggs_set,
+				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
@@ -1452,11 +1474,44 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 	 * When a base table is truncated, the view content will be empty if the
 	 * view definition query does not contain an aggregate without a GROUP cl=
ause.
 	 * Therefore, such views can be truncated.
+	 *
+	 * Aggregate views without a GROUP clause always have one row. Therefore,
+	 * if a base table is truncated, the view will not be empty and will cont=
ain
+	 * a row with NULL value (or 0 for count()). So, in this case, we refresh=
 the
+	 * view instead of truncating it.
 	 */
 	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
 	{
-		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
-							NIL, DROP_RESTRICT, false, false);
+		if (!(query->hasAggs && query->groupClause =3D=3D NIL))
+			ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+								NIL, DROP_RESTRICT, false, false);
+		else
+		{
+			Oid			OIDNewHeap;
+			DestReceiver *dest;
+			uint64		processed =3D 0;
+			Query	   *dataQuery =3D rewriteQueryForIMMV(query, NIL);
+			char		relpersistence =3D matviewRel->rd_rel->relpersistence;
+
+			/*
+			 * Create the transient table that will receive the regenerated data. L=
ock
+			 * it against access by any other process until commit (by which time it
+			 * will be gone).
+			 */
+			OIDNewHeap =3D make_new_heap(matviewOid, matviewRel->rd_rel->reltablesp=
ace,
+									   matviewRel->rd_rel->relam,
+									   relpersistence,  ExclusiveLock);
+			LockRelationOid(OIDNewHeap, AccessExclusiveLock);
+			dest =3D CreateTransientRelDestReceiver(OIDNewHeap);
+
+			/* Generate the data */
+			processed =3D refresh_matview_datafill(dest, dataQuery, NULL, NULL, "");
+			refresh_by_heap_swap(matviewOid, OIDNewHeap, relpersistence);
+
+			/* Inform cumulative stats system about our activity */
+			pgstat_count_truncate(matviewRel);
+			pgstat_count_heap_insert(matviewRel, processed);
+		}
=20
 		/* Clean up hash entry and delete tuplestores */
 		clean_up_IVM_hash_entry(entry, false);
@@ -1496,8 +1551,8 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 	/* Set all tables in the query to pre-update state */
 	rewritten =3D rewrite_query_for_preupdate_state(rewritten, entry->tables,
 												  pstate, matviewOid);
-	/* Rewrite for counting duplicated tuples */
-	rewritten =3D rewrite_query_for_counting(rewritten, pstate);
+	/* Rewrite for counting duplicated tuples and aggregates functions*/
+	rewritten =3D rewrite_query_for_counting_and_aggregates(rewritten, pstate=
);
=20
 	/* Create tuplestores to store view deltas */
 	if (entry->has_old)
@@ -1548,7 +1603,7 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
=20
 			count_colname =3D pstrdup("__ivm_count__");
=20
-			if (query->distinctClause)
+			if (query->hasAggs || query->distinctClause)
 				use_count =3D true;
=20
 			/* calculate delta tables */
@@ -1944,17 +1999,34 @@ replace_rte_with_delta(RangeTblEntry *rte, MV_Trigg=
erTable *table, bool is_new,
 }
=20
 /*
- * rewrite_query_for_counting
+ * rewrite_query_for_counting_and_aggregates
  *
- * Rewrite query for counting duplicated tuples.
+ * Rewrite query for counting duplicated tuples and aggregate functions.
  */
 static Query *
-rewrite_query_for_counting(Query *query, ParseState *pstate)
+rewrite_query_for_counting_and_aggregates(Query *query, ParseState *pstate)
 {
 	TargetEntry *tle_count;
 	FuncCall *fn;
 	Node *node;
=20
+	/* For aggregate views */
+	if (query->hasAggs)
+	{
+		ListCell *lc;
+		List *aggs =3D NIL;
+		AttrNumber next_resno =3D list_length(query->targetList) + 1;
+
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle =3D (TargetEntry *) lfirst(lc);
+
+			if (IsA(tle->expr, Aggref))
+				makeIvmAggColumn(pstate, (Aggref *)tle->expr, tle->resname, &next_resn=
o, &aggs);
+		}
+		query->targetList =3D list_concat(query->targetList, aggs);
+	}
+
 	/* Add count(*) for counting distinct tuples in views */
 	fn =3D makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -=
1);
 	fn->agg_star =3D true;
@@ -2027,6 +2099,8 @@ rewrite_query_for_postupdate_state(Query *query, MV_T=
riggerTable *table, int rte
 	return query;
 }
=20
+#define IVM_colname(type, col) makeObjectName("__ivm_" type, col, "_")
+
 /*
  * apply_delta
  *
@@ -2040,6 +2114,9 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tupl=
estores, Tuplestorestate *n
 {
 	StringInfoData querybuf;
 	StringInfoData target_list_buf;
+	StringInfo	aggs_list_buf =3D NULL;
+	StringInfo	aggs_set_old =3D NULL;
+	StringInfo	aggs_set_new =3D NULL;
 	Relation	matviewRel;
 	char	   *matviewname;
 	ListCell	*lc;
@@ -2062,6 +2139,15 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tup=
lestores, Tuplestorestate *n
 	initStringInfo(&querybuf);
 	initStringInfo(&target_list_buf);
=20
+	if (query->hasAggs)
+	{
+		if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+			aggs_set_old =3D makeStringInfo();
+		if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+			aggs_set_new =3D makeStringInfo();
+		aggs_list_buf =3D makeStringInfo();
+	}
+
 	/* build string of target list */
 	for (i =3D 0; i < matviewRel->rd_att->natts; i++)
 	{
@@ -2078,13 +2164,61 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tu=
plestores, Tuplestorestate *n
 	{
 		TargetEntry *tle =3D (TargetEntry *) lfirst(lc);
 		Form_pg_attribute attr =3D TupleDescAttr(matviewRel->rd_att, i);
+		char *resname =3D NameStr(attr->attname);
=20
 		i++;
=20
 		if (tle->resjunk)
 			continue;
=20
-		keys =3D lappend(keys, attr);
+		/*
+		 * For views without aggregates, all attributes are used as keys to iden=
tify a
+		 * tuple in a view.
+		 */
+		if (!query->hasAggs)
+			keys =3D lappend(keys, attr);
+
+		/* For views with aggregates, we need to build SET clause for updating a=
ggregate
+		 * values. */
+		if (query->hasAggs && IsA(tle->expr, Aggref))
+		{
+			Aggref *aggref =3D (Aggref *) tle->expr;
+			const char *aggname =3D get_func_name(aggref->aggfnoid);
+
+			/*
+			 * We can use function names here because it is already checked if these
+			 * can be used in IMMV by its OID at the definition time.
+			 */
+
+			/* count */
+			if (!strcmp(aggname, "count"))
+				append_set_clause_for_count(resname, aggs_set_old, aggs_set_new, aggs_=
list_buf);
+
+			/* sum */
+			else if (!strcmp(aggname, "sum"))
+				append_set_clause_for_sum(resname, aggs_set_old, aggs_set_new, aggs_li=
st_buf);
+
+			/* avg */
+			else if (!strcmp(aggname, "avg"))
+				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_li=
st_buf,
+										  format_type_be(aggref->aggtype));
+
+			else
+				elog(ERROR, "unsupported aggregate function: %s", aggname);
+		}
+	}
+
+	/* If we have GROUP BY clause, we use its entries as keys. */
+	if (query->hasAggs && query->groupClause)
+	{
+		foreach (lc, query->groupClause)
+		{
+			SortGroupClause *sgcl =3D (SortGroupClause *) lfirst(lc);
+			TargetEntry		*tle =3D get_sortgroupclause_tle(sgcl, query->targetList);
+			Form_pg_attribute attr =3D TupleDescAttr(matviewRel->rd_att, tle->resno=
 - 1);
+
+			keys =3D lappend(keys, attr);
+		}
 	}
=20
 	/* Start maintaining the materialized view. */
@@ -2115,7 +2249,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tupl=
estores, Tuplestorestate *n
 		if (use_count)
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
-									   keys, count_colname);
+									   keys, aggs_list_buf, aggs_set_old,
+									   count_colname);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
=20
@@ -2141,7 +2276,7 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tupl=
estores, Tuplestorestate *n
 		/* apply new delta */
 		if (use_count)
 			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
-								keys, &target_list_buf, count_colname);
+								keys, aggs_set_new, &target_list_buf, count_colname);
 		else
 			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
 	}
@@ -2156,6 +2291,250 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tu=
plestores, Tuplestorestate *n
 		elog(ERROR, "SPI_finish failed");
 }
=20
+/*
+ * append_set_clause_for_count
+ *
+ * Append SET clause string for count aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ */
+static void
+append_set_clause_for_count(const char *resname, StringInfo buf_old,
+							StringInfo buf_new,StringInfo aggs_list)
+{
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/* resname =3D mv.resname - t.resname */
+		appendStringInfo(buf_old,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_SUB, resname, "mv", "t", NULL, NULL));
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/* resname =3D mv.resname + diff.resname */
+		appendStringInfo(buf_new,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_ADD, resname, "mv", "diff", NULL, NULL));
+	}
+
+	appendStringInfo(aggs_list, ", %s",
+		quote_qualified_identifier("diff", resname)
+	);
+}
+
+/*
+ * append_set_clause_for_sum
+ *
+ * Append SET clause string for sum aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ */
+static void
+append_set_clause_for_sum(const char *resname, StringInfo buf_old,
+						  StringInfo buf_new, StringInfo aggs_list)
+{
+	char *count_col =3D IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/* sum =3D mv.sum - t.sum */
+		appendStringInfo(buf_old,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_SUB, resname, "mv", "t", count_col, NULL)
+		);
+		/* count =3D mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/* sum =3D mv.sum + diff.sum */
+		appendStringInfo(buf_new,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_ADD, resname, "mv", "diff", count_col, NULL)
+		);
+		/* count =3D mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
+/*
+ * append_set_clause_for_avg
+ *
+ * Append SET clause string for avg aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ */
+static void
+append_set_clause_for_avg(const char *resname, StringInfo buf_old,
+						  StringInfo buf_new, StringInfo aggs_list,
+						  const char *aggtype)
+{
+	char *sum_col =3D IVM_colname("sum", resname);
+	char *count_col =3D IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/* avg =3D (mv.sum - t.sum)::aggtype / (mv.count - t.count) */
+		appendStringInfo(buf_old,
+			", %s =3D %s OPERATOR(pg_catalog./) %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_SUB, sum_col, "mv", "t", count_col, aggtype),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+		/* sum =3D mv.sum - t.sum */
+		appendStringInfo(buf_old,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, sum_col),
+			get_operation_string(IVM_SUB, sum_col, "mv", "t", count_col, NULL)
+		);
+		/* count =3D mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/* avg =3D (mv.sum + diff.sum)::aggtype / (mv.count + diff.count) */
+		appendStringInfo(buf_new,
+			", %s =3D %s OPERATOR(pg_catalog./) %s",
+			quote_qualified_identifier(NULL, resname),
+			get_operation_string(IVM_ADD, sum_col, "mv", "diff", count_col, aggtype=
),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+		/* sum =3D mv.sum + diff.sum */
+		appendStringInfo(buf_new,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, sum_col),
+			get_operation_string(IVM_ADD, sum_col, "mv", "diff", count_col, NULL)
+		);
+		/* count =3D mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s =3D %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("sum", resname)),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
+/*
+ * get_operation_string
+ *
+ * Build a string to calculate the new aggregate values.
+ */
+static char *
+get_operation_string(IvmOp op, const char *col, const char *arg1, const ch=
ar *arg2,
+					 const char* count_col, const char *castType)
+{
+	StringInfoData buf;
+	StringInfoData castString;
+	char   *col1 =3D quote_qualified_identifier(arg1, col);
+	char   *col2 =3D quote_qualified_identifier(arg2, col);
+	char	op_char =3D (op =3D=3D IVM_SUB ? '-' : '+');
+
+	initStringInfo(&buf);
+	initStringInfo(&castString);
+
+	if (castType)
+		appendStringInfo(&castString, "::%s", castType);
+
+	if (!count_col)
+	{
+		/*
+		 * If the attributes don't have count columns then calc the result
+		 * by using the operator simply.
+		 */
+		appendStringInfo(&buf, "(%s OPERATOR(pg_catalog.%c) %s)%s",
+			col1, op_char, col2, castString.data);
+	}
+	else
+	{
+		/*
+		 * If the attributes have count columns then consider the condition
+		 * where the result becomes NULL.
+		 */
+		char *null_cond =3D get_null_condition_string(op, arg1, arg2, count_col);
+
+		appendStringInfo(&buf,
+			"(CASE WHEN %s THEN NULL "
+				"WHEN %s IS NULL THEN %s "
+				"WHEN %s IS NULL THEN %s "
+				"ELSE (%s OPERATOR(pg_catalog.%c) %s)%s END)",
+			null_cond,
+			col1, col2,
+			col2, col1,
+			col1, op_char, col2, castString.data
+		);
+	}
+
+	return buf.data;
+}
+
+/*
+ * get_null_condition_string
+ *
+ * Build a predicate string for CASE clause to check if an aggregate value
+ * will became NULL after the given operation is applied.
+ */
+static char *
+get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
+						  const char* count_col)
+{
+	StringInfoData null_cond;
+	initStringInfo(&null_cond);
+
+	switch (op)
+	{
+		case IVM_ADD:
+			appendStringInfo(&null_cond,
+				"%s OPERATOR(pg_catalog.=3D) 0 AND %s OPERATOR(pg_catalog.=3D) 0",
+				quote_qualified_identifier(arg1, count_col),
+				quote_qualified_identifier(arg2, count_col)
+			);
+			break;
+		case IVM_SUB:
+			appendStringInfo(&null_cond,
+				"%s OPERATOR(pg_catalog.=3D) %s",
+				quote_qualified_identifier(arg1, count_col),
+				quote_qualified_identifier(arg2, count_col)
+			);
+			break;
+		default:
+			elog(ERROR,"unknown operation");
+	}
+
+	return null_cond.data;
+}
+
+
 /*
  * apply_old_delta_with_count
  *
@@ -2163,13 +2542,20 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tu=
plestores, Tuplestorestate *n
  * which contains tuples to be deleted from to a materialized view given by
  * matviewname.  This is used when counting is required, that is, the view
  * has aggregate or distinct.
+ *
+ * If the view desn't have aggregates or has GROUP BY, this requires a keys
+ * list to identify a tuple in the view. If the view has aggregates, this
+ * requires strings representing resnames of aggregates and SET clause for
+ * updating aggregate values.
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_=
old,
-				List *keys, const char *count_colname)
+				List *keys, StringInfo aggs_list, StringInfo aggs_set,
+				const char *count_colname)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	bool	agg_without_groupby =3D (list_length(keys) =3D=3D 0);
=20
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond =3D get_matching_condition_string(keys);
@@ -2179,22 +2565,26 @@ apply_old_delta_with_count(const char *matviewname,=
 const char *deltaname_old,
 	appendStringInfo(&querybuf,
 					"WITH t AS ("			/* collecting tid of target tuples in the view */
 						"SELECT diff.%s, "			/* count column */
-								"(diff.%s OPERATOR(pg_catalog.=3D) mv.%s) AS for_dlt, "
+								"(diff.%s OPERATOR(pg_catalog.=3D) mv.%s AND %s) AS for_dlt, "
 								"mv.ctid "
+								"%s "				/* aggregate columns */
 						"FROM %s AS mv, %s AS diff "
 						"WHERE %s"					/* tuple matching condition */
 					"), updt AS ("			/* update a tuple if this is not to be deleted */
 						"UPDATE %s AS mv SET %s =3D mv.%s OPERATOR(pg_catalog.-) t.%s "
+											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=3D) t.ctid AND NOT for_dl=
t "
 					")"
 					/* delete a tuple if this is to be deleted */
 					"DELETE FROM %s AS mv USING t "
 					"WHERE mv.ctid OPERATOR(pg_catalog.=3D) t.ctid AND for_dlt",
 					count_colname,
-					count_colname, count_colname,
+					count_colname, count_colname, (agg_without_groupby ? "false" : "true"=
),
+					(aggs_list !=3D NULL ? aggs_list->data : ""),
 					matviewname, deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
+					(aggs_set !=3D NULL ? aggs_set->data : ""),
 					matviewname);
=20
 	if (SPI_exec(querybuf.data, 0) !=3D SPI_OK_DELETE)
@@ -2258,10 +2648,15 @@ apply_old_delta(const char *matviewname, const char=
 *deltaname_old,
  * matviewname.  This is used when counting is required, that is, the view
  * has aggregate or distinct. Also, when a table in EXISTS sub queries
  * is modified.
+ *
+ * If the view desn't have aggregates or has GROUP BY, this requires a keys
+ * list to identify a tuple in the view. If the view has aggregates, this
+ * requires strings representing SET clause for updating aggregate values.
  */
 static void
 apply_new_delta_with_count(const char *matviewname, const char* deltaname_=
new,
-				List *keys, StringInfo target_list, const char* count_colname)
+				List *keys, StringInfo aggs_set, StringInfo target_list,
+				const char* count_colname)
 {
 	StringInfoData	querybuf;
 	StringInfoData	returning_keys;
@@ -2292,6 +2687,7 @@ apply_new_delta_with_count(const char *matviewname, c=
onst char* deltaname_new,
 	appendStringInfo(&querybuf,
 					"WITH updt AS ("		/* update a tuple if this exists in the view */
 						"UPDATE %s AS mv SET %s =3D mv.%s OPERATOR(pg_catalog.+) diff.%s "
+											"%s "	/* SET clauses for aggregates */
 						"FROM %s AS diff "
 						"WHERE %s "					/* tuple matching condition */
 						"RETURNING %s"				/* returning keys of updated tuples */
@@ -2299,6 +2695,7 @@ apply_new_delta_with_count(const char *matviewname, c=
onst char* deltaname_new,
 						"SELECT %s FROM %s AS diff "
 						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
 					matviewname, count_colname, count_colname, count_colname,
+					(aggs_set !=3D NULL ? aggs_set->data : ""),
 					deltaname_new,
 					match_cond,
 					returning_keys.data,
diff --git a/src/include/commands/createas.h b/src/include/commands/createa=
s.h
index 6b47e66bfd..af3a5b4b27 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -30,6 +30,7 @@ extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid=
 matviewOid);
 extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
=20
 extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+extern void makeIvmAggColumn(ParseState *pstate, Aggref *aggref, char *res=
name, AttrNumber *next_resno, List **aggs);
=20
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
=20
--=20
2.25.1


--Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1
Content-Type: text/x-diff;
 name="v31-0009-Add-support-for-min-max-aggregates-for-IVM.patch"
Content-Disposition: attachment;
 filename="v31-0009-Add-support-for-min-max-aggregates-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread

* [PATCH v1] Add RoleNameGetOid() with invalidation-based retry loop for DropRole()/GrantRole()
@ 2026-07-04 04:47 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 573+ messages in thread

From: Bertrand Drouvot @ 2026-07-04 04:47 UTC (permalink / raw)

DropRole() and GrantRole() resolve the role name to an OID before acquiring
LockSharedObject() on the role. A concurrent session that commits a DROP ROLE
between the read and the lock acquisition leaves the first session acting on a
stale OID.

This commit fixes the races by using the same approach as RangeVarGetRelidExtended():
It encapsulates name resolution, permission checking (via a caller-supplied callback),
and lock acquisition inside a retry loop driven by SharedInvalidMessageCounter.
If invalidation messages arrive between name resolution and locking, indicating
concurrent DDL, the function retries.

The lock is kept across retries and only released if the name resolves to a
different OID on the next iteration.

Two callbacks are provided:
- RoleNameCallbackForDropRole(): checks current/session user, superuser attribute,
and ADMIN OPTION privilege before locking. This is similar to what DropRole() is
currently doing before LockSharedObject().
- RoleNameCallbackForGrantRole(): calls check_role_membership_authorization() to
verify the current user can grant/revoke membership. This is similar to what GrantRole()
is currently doing before calling AddRoleMems()/DelRoleMems().

DropRole() and GrantRole() now call RoleNameGetOid() with appropriate lock
levels.

AlterRole() does not need the fix because it calls CatalogTupleUpdate() on the
pg_authid tuple before AddRoleMems(), which blocks a concurrent DROP ROLE.

Author: Bertrand Drouvot <[email protected]>
Reviewed-by:
Discussion:
---
 src/backend/commands/user.c | 246 ++++++++++++++++++++++++++----------
 src/include/commands/user.h |   9 ++
 2 files changed, 191 insertions(+), 64 deletions(-)
  95.5% src/backend/commands/
   4.4% src/include/commands/

diff --git a/src/backend/commands/user.c b/src/backend/commands/user.c
index be11c49f919..6d8e2fa8813 100644
--- a/src/backend/commands/user.c
+++ b/src/backend/commands/user.c
@@ -34,6 +34,7 @@
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/catcache.h"
@@ -116,6 +117,10 @@ static void plan_recursive_revoke(CatCList *memlist,
 								  bool revoke_admin_option_only,
 								  DropBehavior behavior);
 static void InitGrantRoleOptions(GrantRoleOptions *popt);
+static void RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+static void RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+										 Oid oldroleid, void *callback_arg);
 
 
 /* Check if current user has createrole privileges */
@@ -126,6 +131,92 @@ have_createrole_privilege(void)
 }
 
 
+/*
+ * RoleNameGetOid
+ *		Given a role name, look up its OID, lock it, and return the OID.
+ *
+ * This follows the same pattern as RangeVarGetRelidExtended():
+ * name resolution, permission check (via callback), and lock acquisition are
+ * performed inside a retry loop. If invalidation messages arrive during the
+ * process (indicating concurrent DDL), we retry to ensure the name still
+ * resolves to the same OID.
+ *
+ * The callback is invoked before locking, giving callers a chance to check
+ * permissions. It receives the current rolename, the resolved OID, the
+ * previous OID (InvalidOid on first iteration), and a caller-supplied arg.
+ * If the callback raises an error, the function aborts without locking.
+ *
+ * If missing_ok is true and the role does not exist, returns InvalidOid.
+ * Otherwise, raises an error.
+ */
+Oid
+RoleNameGetOid(const char *rolename, LOCKMODE lockmode, bool missing_ok,
+			   RoleNameGetOidCallback callback, void *callback_arg)
+{
+	uint64		inval_count;
+	Oid			roleid;
+	Oid			oldroleid = InvalidOid;
+	bool		retry = false;
+
+	for (;;)
+	{
+		/*
+		 * Remember the current invalidation count so we can detect concurrent
+		 * DDL after locking.
+		 */
+		inval_count = SharedInvalidMessageCounter;
+
+		/* Look up the role name */
+		roleid = get_role_oid(rolename, true);
+
+		if (!OidIsValid(roleid))
+		{
+			if (!missing_ok)
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("role \"%s\" does not exist", rolename)));
+			return InvalidOid;
+		}
+
+		/*
+		 * Invoke caller-supplied callback before locking. This is a good
+		 * place to check permissions: we haven't taken the lock yet, but we
+		 * know the OID we intend to lock. If concurrent DDL changes things,
+		 * the callback will be invoked again on the next iteration.
+		 */
+		if (callback)
+			callback(rolename, roleid, oldroleid, callback_arg);
+
+		/*
+		 * If upon retry we get back the same OID, the invalidation messages
+		 * did not change the final answer. So we're done.
+		 *
+		 * If we got a different OID, we've locked the role that used to have
+		 * this name rather than the one that does now. Release the old lock.
+		 */
+		if (retry)
+		{
+			if (roleid == oldroleid)
+				break;
+			UnlockSharedObject(AuthIdRelationId, oldroleid, 0, lockmode);
+		}
+
+		/* Lock the role */
+		LockSharedObject(AuthIdRelationId, roleid, 0, lockmode);
+
+		/* If no invalidation messages were processed, we're done */
+		if (inval_count == SharedInvalidMessageCounter)
+			break;
+
+		/* Something may have changed, retry */
+		retry = true;
+		oldroleid = roleid;
+	}
+
+	return roleid;
+}
+
+
 /*
  * CREATE ROLE
  */
@@ -1090,6 +1181,59 @@ AlterRoleSet(AlterRoleSetStmt *stmt)
 }
 
 
+/*
+ * Before acquiring a role lock for DROP ROLE, check that the role is not the
+ * current/session user and that the caller has sufficient privileges to drop it.
+ */
+static void
+RoleNameCallbackForDropRole(const char *rolename, Oid roleid,
+							Oid oldroleid, void *callback_arg)
+{
+	HeapTuple	tuple;
+	Form_pg_authid roleform;
+
+	if (roleid == GetUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetOuterUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("current user cannot be dropped")));
+	if (roleid == GetSessionUserId())
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_IN_USE),
+				 errmsg("session user cannot be dropped")));
+
+	tuple = SearchSysCache1(AUTHOID, ObjectIdGetDatum(roleid));
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_OBJECT),
+				 errmsg("role \"%s\" does not exist", rolename)));
+
+	roleform = (Form_pg_authid) GETSTRUCT(tuple);
+
+	/*
+	 * For safety's sake, we allow createrole holders to drop ordinary roles
+	 * but not superuser roles, and only if they also have ADMIN OPTION.
+	 */
+	if (roleform->rolsuper && !superuser())
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
+						   "SUPERUSER", "SUPERUSER")));
+	if (!is_admin_of_role(GetUserId(), roleid))
+		ereport(ERROR,
+				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+				 errmsg("permission denied to drop role"),
+				 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
+						   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
+
+	ReleaseSysCache(tuple);
+}
+
+
 /*
  * DROP ROLE
  */
@@ -1119,9 +1263,7 @@ DropRole(DropRoleStmt *stmt)
 	{
 		RoleSpec   *rolspec = lfirst(item);
 		char	   *role;
-		HeapTuple	tuple,
-					tmp_tuple;
-		Form_pg_authid roleform;
+		HeapTuple	tmp_tuple;
 		ScanKeyData scankey;
 		SysScanDesc sscan;
 		Oid			roleid;
@@ -1132,71 +1274,27 @@ DropRole(DropRoleStmt *stmt)
 					 errmsg("cannot use special role specifier in DROP ROLE")));
 		role = rolspec->rolename;
 
-		tuple = SearchSysCache1(AUTHNAME, PointerGetDatum(role));
-		if (!HeapTupleIsValid(tuple))
-		{
-			if (!stmt->missing_ok)
-			{
-				ereport(ERROR,
-						(errcode(ERRCODE_UNDEFINED_OBJECT),
-						 errmsg("role \"%s\" does not exist", role)));
-			}
-			else
-			{
-				ereport(NOTICE,
-						(errmsg("role \"%s\" does not exist, skipping",
-								role)));
-			}
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP or ALTER commits between name
+		 * resolution and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(role, AccessExclusiveLock, stmt->missing_ok,
+								RoleNameCallbackForDropRole, NULL);
 
+		if (!OidIsValid(roleid))
+		{
+			/* missing_ok case: role doesn't exist */
+			ereport(NOTICE,
+					(errmsg("role \"%s\" does not exist, skipping",
+							role)));
 			continue;
 		}
 
-		roleform = (Form_pg_authid) GETSTRUCT(tuple);
-		roleid = roleform->oid;
-
-		if (roleid == GetUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetOuterUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("current user cannot be dropped")));
-		if (roleid == GetSessionUserId())
-			ereport(ERROR,
-					(errcode(ERRCODE_OBJECT_IN_USE),
-					 errmsg("session user cannot be dropped")));
-
-		/*
-		 * For safety's sake, we allow createrole holders to drop ordinary
-		 * roles but not superuser roles, and only if they also have ADMIN
-		 * OPTION.
-		 */
-		if (roleform->rolsuper && !superuser())
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute may drop roles with the %s attribute.",
-							   "SUPERUSER", "SUPERUSER")));
-		if (!is_admin_of_role(GetUserId(), roleid))
-			ereport(ERROR,
-					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-					 errmsg("permission denied to drop role"),
-					 errdetail("Only roles with the %s attribute and the %s option on role \"%s\" may drop this role.",
-							   "CREATEROLE", "ADMIN", NameStr(roleform->rolname))));
-
 		/* DROP hook for the role being removed */
 		InvokeObjectDropHook(AuthIdRelationId, roleid, 0);
 
-		/* Don't leak the syscache tuple */
-		ReleaseSysCache(tuple);
-
-		/*
-		 * Lock the role, so nobody can add dependencies to her while we drop
-		 * her.  We keep the lock until the end of transaction.
-		 */
-		LockSharedObject(AuthIdRelationId, roleid, 0, AccessExclusiveLock);
-
 		/*
 		 * If there is a pg_auth_members entry that has one of the roles to be
 		 * dropped as the roleid or member, it should be silently removed, but
@@ -1484,6 +1582,21 @@ RenameRole(const char *oldname, const char *newname)
 	return address;
 }
 
+/*
+ * Before acquiring a role lock for GRANT/REVOKE, check that the current user
+ * has authorization to grant/revoke membership in the specified role.
+ */
+static void
+RoleNameCallbackForGrantRole(const char *rolename, Oid roleid,
+							 Oid oldroleid, void *callback_arg)
+{
+	bool		is_grant = *((bool *) callback_arg);
+	Oid			currentUserId = GetUserId();
+
+	check_role_membership_authorization(currentUserId, roleid, is_grant);
+}
+
+
 /*
  * GrantRoleStmt
  *
@@ -1568,9 +1681,14 @@ GrantRole(ParseState *pstate, GrantRoleStmt *stmt)
 					(errcode(ERRCODE_INVALID_GRANT_OPERATION),
 					 errmsg("column names cannot be included in GRANT/REVOKE ROLE")));
 
-		roleid = get_role_oid(rolename, false);
-		check_role_membership_authorization(currentUserId,
-											roleid, stmt->is_grant);
+		/*
+		 * Use RoleNameGetOid to resolve the name, check permissions, and lock
+		 * the role atomically with a retry loop. This prevents race
+		 * conditions where a concurrent DROP commits between name resolution
+		 * and lock acquisition.
+		 */
+		roleid = RoleNameGetOid(rolename, ShareUpdateExclusiveLock, false,
+								RoleNameCallbackForGrantRole, &stmt->is_grant);
 		if (stmt->is_grant)
 			AddRoleMems(currentUserId, rolename, roleid,
 						stmt->grantee_roles, grantee_ids,
diff --git a/src/include/commands/user.h b/src/include/commands/user.h
index 97dcb93791b..17263452250 100644
--- a/src/include/commands/user.h
+++ b/src/include/commands/user.h
@@ -21,6 +21,15 @@
 extern PGDLLIMPORT int Password_encryption; /* values from enum PasswordType */
 extern PGDLLIMPORT char *createrole_self_grant;
 
+/* Callback for RoleNameGetOid, invoked after name resolution but before locking */
+typedef void (*RoleNameGetOidCallback) (const char *rolename, Oid roleid,
+										Oid oldroleid, void *callback_arg);
+
+extern Oid	RoleNameGetOid(const char *rolename, LOCKMODE lockmode,
+						   bool missing_ok,
+						   RoleNameGetOidCallback callback,
+						   void *callback_arg);
+
 /* Hook to check passwords in CreateRole() and AlterRole() */
 typedef void (*check_password_hook_type) (const char *username, const char *shadow_pass, PasswordType password_type, Datum validuntil_time, bool validuntil_null);
 
-- 
2.34.1


--xlWYagR37YwJXkF8--





^ permalink  raw  reply  [nested|flat] 573+ messages in thread