Add security checks to selectivity estimation functions

Some selectivity estimation functions run user-supplied operators over
data obtained from pg_statistic without security checks, which allows
those operators to leak pg_statistic data without having privileges on
the underlying tables.  Fix by checking that one of the following is
satisfied: (1) the user has table or column privileges on the table
underlying the pg_statistic data, or (2) the function implementing the
user-supplied operator is leak-proof.  If neither is satisfied, planning
will proceed as if there are no statistics available.

At least one of these is satisfied in most cases in practice.  The only
situations that are negatively impacted are user-defined or
not-leak-proof operators on a security-barrier view.

Reported-by: Robert Haas <robertmhaas@gmail.com>
Author: Peter Eisentraut <peter_e@gmx.net>
Author: Tom Lane <tgl@sss.pgh.pa.us>

Security: CVE-2017-7484

doc/src/sgml/planstats.sgml

@@ -582,4 +582,65 @@ EXPLAIN (ANALYZE, TIMING OFF) SELECT COUNT(*) FROM t GROUP BY a, b;
 
   </sect2>
  </sect1>
+
+ <sect1 id="planner-stats-security">
+  <title>Planner Statistics and Security</title>
+
+  <para>
+   Access to the table <structname>pg_statistic</structname> is restricted to
+   superusers, so that ordinary users cannot learn about the contents of the
+   tables of other users from it.  Some selectivity estimation functions will
+   use a user-provided operator (either the operator appearing in the query or
+   a related operator) to analyze the stored statistics.  For example, in order
+   to determine whether a stored most common value is applicable, the
+   selectivity estimator will have to run the appropriate <literal>=</literal>
+   operator to compare the constant in the query to the stored value.
+   Thus the data in <structname>pg_statistic</structname> is potentially
+   passed to user-defined operators.  An appropriately crafted operator can
+   intentionally leak the passed operands (for example, by logging them
+   or writing them to a different table), or accidentally leak them by showing
+   their values in error messages, in either case possibly exposing data from
+   <structname>pg_statistic</structname> to a user who should not be able to
+   see it.
+  </para>
+
+  <para>
+   In order to prevent this, the following applies to all built-in selectivity
+   estimation functions.  When planning a query, in order to be able to use
+   stored statistics, the current user must either
+   have <literal>SELECT</literal> privilege on the table or the involved
+   columns, or the operator used must be <literal>LEAKPROOF</literal> (more
+   accurately, the function that the operator is based on).  If not, then the
+   selectivity estimator will behave as if no statistics are available, and
+   the planner will proceed with default or fall-back assumptions.
+  </para>
+
+  <para>
+   If a user does not have the required privilege on the table or columns,
+   then in many cases the query will ultimately receive a permission-denied
+   error, in which case this mechanism is invisible in practice.  But if the
+   user is reading from a security-barrier view, then the planner might wish
+   to check the statistics of an underlying table that is otherwise
+   inaccessible to the user.  In that case, the operator should be leak-proof
+   or the statistics will not be used.  There is no direct feedback about
+   that, except that the plan might be suboptimal.  If one suspects that this
+   is the case, one could try running the query as a more privileged user,
+   to see if a different plan results.
+  </para>
+
+  <para>
+   This restriction applies only to cases where the planner would need to
+   execute a user-defined operator on one or more values
+   from <structname>pg_statistic</structname>.  Thus the planner is permitted
+   to use generic statistical information, such as the fraction of null values
+   or the number of distinct values in a column, regardless of access
+   privileges.
+  </para>
+
+  <para>
+   Selectivity estimation functions contained in third-party extensions that
+   potentially operate on statistics with user-defined operators should follow
+   the same security rules.  Consult the PostgreSQL source code for guidance.
+  </para>
+ </sect1>
 </chapter>

src/backend/utils/adt/array_selfuncs.c

@@ -133,7 +133,8 @@ scalararraysel_containment(PlannerInfo *root,
 		useOr = !useOr;
 
 	/* Get array element stats for var, if available */
-	if (HeapTupleIsValid(vardata.statsTuple))
+	if (HeapTupleIsValid(vardata.statsTuple) &&
+		statistic_proc_security_check(&vardata, cmpfunc->fn_oid))
 	{
 		Form_pg_statistic stats;
 		Datum	   *values;
@@ -364,7 +365,8 @@ calc_arraycontsel(VariableStatData *vardata, Datum constval,
 	 */
 	array = DatumGetArrayTypeP(constval);
 
-	if (HeapTupleIsValid(vardata->statsTuple))
+	if (HeapTupleIsValid(vardata->statsTuple) &&
+		statistic_proc_security_check(vardata, cmpfunc->fn_oid))
 	{
 		Form_pg_statistic stats;
 		Datum	   *values;

src/backend/utils/adt/rangetypes_selfuncs.c

@@ -255,6 +255,7 @@ calc_rangesel(TypeCacheEntry *typcache, VariableStatData *vardata,
 			if (nnumbers != 1)
 				elog(ERROR, "invalid empty fraction statistic");		/* shouldn't happen */
 			empty_frac = numbers[0];
+			free_attstatsslot(vardata->atttype, NULL, 0, numbers, nnumbers);
 		}
 		else
 		{
@@ -383,6 +384,15 @@ calc_hist_selectivity(TypeCacheEntry *typcache, VariableStatData *vardata,
 	bool		empty;
 	double		hist_selec;
 
+	/* Can't use the histogram with insecure range support functions */
+	if (!statistic_proc_security_check(vardata,
+									   typcache->rng_cmp_proc_finfo.fn_oid))
+		return -1;
+	if (OidIsValid(typcache->rng_subdiff_finfo.fn_oid) &&
+		!statistic_proc_security_check(vardata,
+									   typcache->rng_subdiff_finfo.fn_oid))
+		return -1;
+
 	/* Try to get histogram of ranges */
 	if (!(HeapTupleIsValid(vardata->statsTuple) &&
 		  get_attstatsslot(vardata->statsTuple,
@@ -420,11 +430,19 @@ calc_hist_selectivity(TypeCacheEntry *typcache, VariableStatData *vardata,
 							   NULL,
 							   &length_hist_values, &length_nhist,
 							   NULL, NULL)))
+		{
+			free_attstatsslot(vardata->atttype, hist_values, nhist, NULL, 0);
 			return -1.0;
+		}
 
 		/* check that it's a histogram, not just a dummy entry */
 		if (length_nhist < 2)
+		{
+			free_attstatsslot(vardata->atttype,
+							  length_hist_values, length_nhist, NULL, 0);
+			free_attstatsslot(vardata->atttype, hist_values, nhist, NULL, 0);
 			return -1.0;
+		}
 	}
 
 	/* Extract the bounds of the constant value. */
@@ -560,6 +578,10 @@ calc_hist_selectivity(TypeCacheEntry *typcache, VariableStatData *vardata,
 			break;
 	}
 
+	free_attstatsslot(vardata->atttype,
+					  length_hist_values, length_nhist, NULL, 0);
+	free_attstatsslot(vardata->atttype, hist_values, nhist, NULL, 0);
+
 	return hist_selec;
 }
 

src/backend/utils/adt/selfuncs.c

@@ -115,6 +115,7 @@
 #include "catalog/pg_type.h"
 #include "executor/executor.h"
 #include "mb/pg_wchar.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "optimizer/clauses.h"
@@ -129,6 +130,7 @@
 #include "parser/parse_coerce.h"
 #include "parser/parsetree.h"
 #include "statistics/statistics.h"
+#include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/bytea.h"
 #include "utils/date.h"
@@ -273,6 +275,7 @@ var_eq_const(VariableStatData *vardata, Oid operator,
 {
 	double		selec;
 	bool		isdefault;
+	Oid			opfuncoid;
 
 	/*
 	 * If the constant is NULL, assume operator is strict and return zero, ie,
@@ -291,7 +294,9 @@ var_eq_const(VariableStatData *vardata, Oid operator,
 	if (vardata->isunique && vardata->rel && vardata->rel->tuples >= 1.0)
 		return 1.0 / vardata->rel->tuples;
 
-	if (HeapTupleIsValid(vardata->statsTuple))
+	if (HeapTupleIsValid(vardata->statsTuple) &&
+		statistic_proc_security_check(vardata,
+									  (opfuncoid = get_opcode(operator))))
 	{
 		Form_pg_statistic stats;
 		Datum	   *values;
@@ -319,7 +324,7 @@ var_eq_const(VariableStatData *vardata, Oid operator,
 		{
 			FmgrInfo	eqproc;
 
-			fmgr_info(get_opcode(operator), &eqproc);
+			fmgr_info(opfuncoid, &eqproc);
 
 			for (i = 0; i < nvalues; i++)
 			{
@@ -625,6 +630,7 @@ mcv_selectivity(VariableStatData *vardata, FmgrInfo *opproc,
 	sumcommon = 0.0;
 
 	if (HeapTupleIsValid(vardata->statsTuple) &&
+		statistic_proc_security_check(vardata, opproc->fn_oid) &&
 		get_attstatsslot(vardata->statsTuple,
 						 vardata->atttype, vardata->atttypmod,
 						 STATISTIC_KIND_MCV, InvalidOid,
@@ -701,6 +707,7 @@ histogram_selectivity(VariableStatData *vardata, FmgrInfo *opproc,
 	Assert(min_hist_size > 2 * n_skip);
 
 	if (HeapTupleIsValid(vardata->statsTuple) &&
+		statistic_proc_security_check(vardata, opproc->fn_oid) &&
 		get_attstatsslot(vardata->statsTuple,
 						 vardata->atttype, vardata->atttypmod,
 						 STATISTIC_KIND_HISTOGRAM, InvalidOid,
@@ -778,6 +785,7 @@ ineq_histogram_selectivity(PlannerInfo *root,
 	 * the reverse way if isgt is TRUE.
 	 */
 	if (HeapTupleIsValid(vardata->statsTuple) &&
+		statistic_proc_security_check(vardata, opproc->fn_oid) &&
 		get_attstatsslot(vardata->statsTuple,
 						 vardata->atttype, vardata->atttypmod,
 						 STATISTIC_KIND_HISTOGRAM, InvalidOid,
@@ -2262,6 +2270,7 @@ eqjoinsel_inner(Oid operator,
 	double		nd2;
 	bool		isdefault1;
 	bool		isdefault2;
+	Oid			opfuncoid;
 	Form_pg_statistic stats1 = NULL;
 	Form_pg_statistic stats2 = NULL;
 	bool		have_mcvs1 = false;
@@ -2278,30 +2287,36 @@ eqjoinsel_inner(Oid operator,
 	nd1 = get_variable_numdistinct(vardata1, &isdefault1);
 	nd2 = get_variable_numdistinct(vardata2, &isdefault2);
 
+	opfuncoid = get_opcode(operator);
+
 	if (HeapTupleIsValid(vardata1->statsTuple))
 	{
+		/* note we allow use of nullfrac regardless of security check */
 		stats1 = (Form_pg_statistic) GETSTRUCT(vardata1->statsTuple);
-		have_mcvs1 = get_attstatsslot(vardata1->statsTuple,
-									  vardata1->atttype,
-									  vardata1->atttypmod,
-									  STATISTIC_KIND_MCV,
-									  InvalidOid,
-									  NULL,
-									  &values1, &nvalues1,
-									  &numbers1, &nnumbers1);
+		if (statistic_proc_security_check(vardata1, opfuncoid))
+			have_mcvs1 = get_attstatsslot(vardata1->statsTuple,
+										  vardata1->atttype,
+										  vardata1->atttypmod,
+										  STATISTIC_KIND_MCV,
+										  InvalidOid,
+										  NULL,
+										  &values1, &nvalues1,
+										  &numbers1, &nnumbers1);
 	}
 
 	if (HeapTupleIsValid(vardata2->statsTuple))
 	{
+		/* note we allow use of nullfrac regardless of security check */
 		stats2 = (Form_pg_statistic) GETSTRUCT(vardata2->statsTuple);
-		have_mcvs2 = get_attstatsslot(vardata2->statsTuple,
-									  vardata2->atttype,
-									  vardata2->atttypmod,
-									  STATISTIC_KIND_MCV,
-									  InvalidOid,
-									  NULL,
-									  &values2, &nvalues2,
-									  &numbers2, &nnumbers2);
+		if (statistic_proc_security_check(vardata2, opfuncoid))
+			have_mcvs2 = get_attstatsslot(vardata2->statsTuple,
+										  vardata2->atttype,
+										  vardata2->atttypmod,
+										  STATISTIC_KIND_MCV,
+										  InvalidOid,
+										  NULL,
+										  &values2, &nvalues2,
+										  &numbers2, &nnumbers2);
 	}
 
 	if (have_mcvs1 && have_mcvs2)
@@ -2335,7 +2350,7 @@ eqjoinsel_inner(Oid operator,
 		int			i,
 					nmatches;
 
-		fmgr_info(get_opcode(operator), &eqproc);
+		fmgr_info(opfuncoid, &eqproc);
 		hasmatch1 = (bool *) palloc0(nvalues1 * sizeof(bool));
 		hasmatch2 = (bool *) palloc0(nvalues2 * sizeof(bool));
 
@@ -2478,6 +2493,7 @@ eqjoinsel_inner(Oid operator,
  *
  * (Also used for anti join, which we are supposed to estimate the same way.)
  * Caller has ensured that vardata1 is the LHS variable.
+ * Unlike eqjoinsel_inner, we have to cope with operator being InvalidOid.
  */
 static double
 eqjoinsel_semi(Oid operator,
@@ -2489,6 +2505,7 @@ eqjoinsel_semi(Oid operator,
 	double		nd2;
 	bool		isdefault1;
 	bool		isdefault2;
+	Oid			opfuncoid;
 	Form_pg_statistic stats1 = NULL;
 	bool		have_mcvs1 = false;
 	Datum	   *values1 = NULL;
@@ -2504,6 +2521,8 @@ eqjoinsel_semi(Oid operator,
 	nd1 = get_variable_numdistinct(vardata1, &isdefault1);
 	nd2 = get_variable_numdistinct(vardata2, &isdefault2);
 
+	opfuncoid = OidIsValid(operator) ? get_opcode(operator) : InvalidOid;
+
 	/*
 	 * We clamp nd2 to be not more than what we estimate the inner relation's
 	 * size to be.  This is intuitively somewhat reasonable since obviously
@@ -2539,18 +2558,21 @@ eqjoinsel_semi(Oid operator,
 
 	if (HeapTupleIsValid(vardata1->statsTuple))
 	{
+		/* note we allow use of nullfrac regardless of security check */
 		stats1 = (Form_pg_statistic) GETSTRUCT(vardata1->statsTuple);
-		have_mcvs1 = get_attstatsslot(vardata1->statsTuple,
-									  vardata1->atttype,
-									  vardata1->atttypmod,
-									  STATISTIC_KIND_MCV,
-									  InvalidOid,
-									  NULL,
-									  &values1, &nvalues1,
-									  &numbers1, &nnumbers1);
+		if (statistic_proc_security_check(vardata1, opfuncoid))
+			have_mcvs1 = get_attstatsslot(vardata1->statsTuple,
+										  vardata1->atttype,
+										  vardata1->atttypmod,
+										  STATISTIC_KIND_MCV,
+										  InvalidOid,
+										  NULL,
+										  &values1, &nvalues1,
+										  &numbers1, &nnumbers1);
 	}
 
-	if (HeapTupleIsValid(vardata2->statsTuple))
+	if (HeapTupleIsValid(vardata2->statsTuple) &&
+		statistic_proc_security_check(vardata2, opfuncoid))
 	{
 		have_mcvs2 = get_attstatsslot(vardata2->statsTuple,
 									  vardata2->atttype,
@@ -2592,7 +2614,7 @@ eqjoinsel_semi(Oid operator,
 		 */
 		clamped_nvalues2 = Min(nvalues2, nd2);
 
-		fmgr_info(get_opcode(operator), &eqproc);
+		fmgr_info(opfuncoid, &eqproc);
 		hasmatch1 = (bool *) palloc0(nvalues1 * sizeof(bool));
 		hasmatch2 = (bool *) palloc0(clamped_nvalues2 * sizeof(bool));
 
@@ -4558,6 +4580,9 @@ get_join_variables(PlannerInfo *root, List *args, SpecialJoinInfo *sjinfo,
  *		this query.  (Caution: this should be trusted for statistical
  *		purposes only, since we do not check indimmediate nor verify that
  *		the exact same definition of equality applies.)
+ *	acl_ok: TRUE if current user has permission to read the column(s)
+ *		underlying the pg_statistic entry.  This is consulted by
+ *		statistic_proc_security_check().
  *
  * Caller is responsible for doing ReleaseVariableStats() before exiting.
  */
@@ -4726,6 +4751,30 @@ examine_variable(PlannerInfo *root, Node *node, int varRelid,
 												Int16GetDatum(pos + 1),
 												BoolGetDatum(false));
 							vardata->freefunc = ReleaseSysCache;
+
+							if (HeapTupleIsValid(vardata->statsTuple))
+							{
+								/* Get index's table for permission check */
+								RangeTblEntry *rte;
+
+								rte = planner_rt_fetch(index->rel->relid, root);
+								Assert(rte->rtekind == RTE_RELATION);
+
+								/*
+								 * For simplicity, we insist on the whole
+								 * table being selectable, rather than trying
+								 * to identify which column(s) the index
+								 * depends on.
+								 */
+								vardata->acl_ok =
+									(pg_class_aclcheck(rte->relid, GetUserId(),
+												 ACL_SELECT) == ACLCHECK_OK);
+							}
+							else
+							{
+								/* suppress leakproofness checks later */
+								vardata->acl_ok = true;
+							}
 						}
 						if (vardata->statsTuple)
 							break;
@@ -4778,6 +4827,21 @@ examine_simple_variable(PlannerInfo *root, Var *var,
 											  Int16GetDatum(var->varattno),
 											  BoolGetDatum(rte->inh));
 		vardata->freefunc = ReleaseSysCache;
+
+		if (HeapTupleIsValid(vardata->statsTuple))
+		{
+			/* check if user has permission to read this column */
+			vardata->acl_ok =
+				(pg_class_aclcheck(rte->relid, GetUserId(),
+								   ACL_SELECT) == ACLCHECK_OK) ||
+				(pg_attribute_aclcheck(rte->relid, var->varattno, GetUserId(),
+									   ACL_SELECT) == ACLCHECK_OK);
+		}
+		else
+		{
+			/* suppress any possible leakproofness checks later */
+			vardata->acl_ok = true;
+		}
 	}
 	else if (rte->rtekind == RTE_SUBQUERY && !rte->inh)
 	{
@@ -4894,6 +4958,30 @@ examine_simple_variable(PlannerInfo *root, Var *var,
 	}
 }
 
+/*
+ * Check whether it is permitted to call func_oid passing some of the
+ * pg_statistic data in vardata.  We allow this either if the user has SELECT
+ * privileges on the table or column underlying the pg_statistic data or if
+ * the function is marked leak-proof.
+ */
+bool
+statistic_proc_security_check(VariableStatData *vardata, Oid func_oid)
+{
+	if (vardata->acl_ok)
+		return true;
+
+	if (!OidIsValid(func_oid))
+		return false;
+
+	if (get_func_leakproof(func_oid))
+		return true;
+
+	ereport(DEBUG2,
+			(errmsg_internal("not using statistics because function \"%s\" is not leak-proof",
+							 get_func_name(func_oid))));
+	return false;
+}
+
 /*
  * get_variable_numdistinct
  *	  Estimate the number of distinct values of a variable.
@@ -5036,6 +5124,7 @@ get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop,
 	bool		have_data = false;
 	int16		typLen;
 	bool		typByVal;
+	Oid			opfuncoid;
 	Datum	   *values;
 	int			nvalues;
 	int			i;
@@ -5058,6 +5147,17 @@ get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop,
 		return false;
 	}
 
+	/*
+	 * If we can't apply the sortop to the stats data, just fail.  In
+	 * principle, if there's a histogram and no MCVs, we could return the
+	 * histogram endpoints without ever applying the sortop ... but it's
+	 * probably not worth trying, because whatever the caller wants to do with
+	 * the endpoints would likely fail the security check too.
+	 */
+	if (!statistic_proc_security_check(vardata,
+									   (opfuncoid = get_opcode(sortop))))
+		return false;
+
 	get_typlenbyval(vardata->atttype, &typLen, &typByVal);
 
 	/*
@@ -5110,7 +5210,7 @@ get_variable_range(PlannerInfo *root, VariableStatData *vardata, Oid sortop,
 		bool		tmax_is_mcv = false;
 		FmgrInfo	opproc;
 
-		fmgr_info(get_opcode(sortop), &opproc);
+		fmgr_info(opfuncoid, &opproc);
 
 		for (i = 0; i < nvalues; i++)
 		{

src/include/utils/selfuncs.h

@@ -75,6 +75,7 @@ typedef struct VariableStatData
 	Oid			atttype;		/* type to pass to get_attstatsslot */
 	int32		atttypmod;		/* typmod to pass to get_attstatsslot */
 	bool		isunique;		/* matches unique index or DISTINCT clause */
+	bool		acl_ok;			/* result of ACL check on table or column */
 } VariableStatData;
 
 #define ReleaseVariableStats(vardata)  \
@@ -153,6 +154,7 @@ extern PGDLLIMPORT get_index_stats_hook_type get_index_stats_hook;
 
 extern void examine_variable(PlannerInfo *root, Node *node, int varRelid,
 				 VariableStatData *vardata);
+extern bool statistic_proc_security_check(VariableStatData *vardata, Oid func_oid);
 extern bool get_restriction_variable(PlannerInfo *root, List *args,
 						 int varRelid,
 						 VariableStatData *vardata, Node **other,

src/test/regress/expected/privileges.out

@@ -184,6 +184,103 @@ SELECT * FROM atest1; -- ok
  1 | two
 (2 rows)
 
+-- test leaky-function protections in selfuncs
+-- regress_user1 will own a table and provide a view for it.
+SET SESSION AUTHORIZATION regress_user1;
+CREATE TABLE atest12 as
+  SELECT x AS a, 10001 - x AS b FROM generate_series(1,10000) x;
+CREATE INDEX ON atest12 (a);
+CREATE INDEX ON atest12 (abs(a));
+VACUUM ANALYZE atest12;
+CREATE FUNCTION leak(integer,integer) RETURNS boolean
+  AS $$begin return $1 < $2; end$$
+  LANGUAGE plpgsql immutable;
+CREATE OPERATOR <<< (procedure = leak, leftarg = integer, rightarg = integer,
+                     restrict = scalarltsel);
+-- view with leaky operator
+CREATE VIEW atest12v AS
+  SELECT * FROM atest12 WHERE b <<< 5;
+GRANT SELECT ON atest12v TO PUBLIC;
+-- This plan should use nestloop, knowing that few rows will be selected.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+                   QUERY PLAN                    
+-------------------------------------------------
+ Nested Loop
+   ->  Seq Scan on atest12 atest12_1
+         Filter: (b <<< 5)
+   ->  Index Scan using atest12_a_idx on atest12
+         Index Cond: (a = atest12_1.b)
+         Filter: (b <<< 5)
+(6 rows)
+
+-- And this one.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 x, atest12 y
+  WHERE x.a = y.b and abs(y.a) <<< 5;
+                    QUERY PLAN                     
+---------------------------------------------------
+ Nested Loop
+   ->  Seq Scan on atest12 y
+         Filter: (abs(a) <<< 5)
+   ->  Index Scan using atest12_a_idx on atest12 x
+         Index Cond: (a = y.b)
+(5 rows)
+
+-- Check if regress_user2 can break security.
+SET SESSION AUTHORIZATION regress_user2;
+CREATE FUNCTION leak2(integer,integer) RETURNS boolean
+  AS $$begin raise notice 'leak % %', $1, $2; return $1 > $2; end$$
+  LANGUAGE plpgsql immutable;
+CREATE OPERATOR >>> (procedure = leak2, leftarg = integer, rightarg = integer,
+                     restrict = scalargtsel);
+-- This should not show any "leak" notices before failing.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 WHERE a >>> 0;
+ERROR:  permission denied for relation atest12
+-- This plan should use hashjoin, as it will expect many rows to be selected.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+                QUERY PLAN                 
+-------------------------------------------
+ Hash Join
+   Hash Cond: (atest12.a = atest12_1.b)
+   ->  Seq Scan on atest12
+         Filter: (b <<< 5)
+   ->  Hash
+         ->  Seq Scan on atest12 atest12_1
+               Filter: (b <<< 5)
+(7 rows)
+
+-- Now regress_user1 grants sufficient access to regress_user2.
+SET SESSION AUTHORIZATION regress_user1;
+GRANT SELECT (a, b) ON atest12 TO PUBLIC;
+SET SESSION AUTHORIZATION regress_user2;
+-- Now regress_user2 will also get a good row estimate.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+                   QUERY PLAN                    
+-------------------------------------------------
+ Nested Loop
+   ->  Seq Scan on atest12 atest12_1
+         Filter: (b <<< 5)
+   ->  Index Scan using atest12_a_idx on atest12
+         Index Cond: (a = atest12_1.b)
+         Filter: (b <<< 5)
+(6 rows)
+
+-- But not for this, due to lack of table-wide permissions needed
+-- to make use of the expression index's statistics.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 x, atest12 y
+  WHERE x.a = y.b and abs(y.a) <<< 5;
+              QUERY PLAN              
+--------------------------------------
+ Hash Join
+   Hash Cond: (x.a = y.b)
+   ->  Seq Scan on atest12 x
+   ->  Hash
+         ->  Seq Scan on atest12 y
+               Filter: (abs(a) <<< 5)
+(6 rows)
+
+-- clean up (regress_user1's objects are all dropped later)
+DROP FUNCTION leak2(integer, integer) CASCADE;
+NOTICE:  drop cascades to operator >>>(integer,integer)
 -- groups
 SET SESSION AUTHORIZATION regress_user3;
 CREATE TABLE atest3 (one int, two int, three int);

src/test/regress/sql/privileges.sql

@@ -127,6 +127,67 @@ bar	true
 SELECT * FROM atest1; -- ok
 
 
+-- test leaky-function protections in selfuncs
+
+-- regress_user1 will own a table and provide a view for it.
+SET SESSION AUTHORIZATION regress_user1;
+
+CREATE TABLE atest12 as
+  SELECT x AS a, 10001 - x AS b FROM generate_series(1,10000) x;
+CREATE INDEX ON atest12 (a);
+CREATE INDEX ON atest12 (abs(a));
+VACUUM ANALYZE atest12;
+
+CREATE FUNCTION leak(integer,integer) RETURNS boolean
+  AS $$begin return $1 < $2; end$$
+  LANGUAGE plpgsql immutable;
+CREATE OPERATOR <<< (procedure = leak, leftarg = integer, rightarg = integer,
+                     restrict = scalarltsel);
+
+-- view with leaky operator
+CREATE VIEW atest12v AS
+  SELECT * FROM atest12 WHERE b <<< 5;
+GRANT SELECT ON atest12v TO PUBLIC;
+
+-- This plan should use nestloop, knowing that few rows will be selected.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+
+-- And this one.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 x, atest12 y
+  WHERE x.a = y.b and abs(y.a) <<< 5;
+
+-- Check if regress_user2 can break security.
+SET SESSION AUTHORIZATION regress_user2;
+
+CREATE FUNCTION leak2(integer,integer) RETURNS boolean
+  AS $$begin raise notice 'leak % %', $1, $2; return $1 > $2; end$$
+  LANGUAGE plpgsql immutable;
+CREATE OPERATOR >>> (procedure = leak2, leftarg = integer, rightarg = integer,
+                     restrict = scalargtsel);
+
+-- This should not show any "leak" notices before failing.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 WHERE a >>> 0;
+
+-- This plan should use hashjoin, as it will expect many rows to be selected.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+
+-- Now regress_user1 grants sufficient access to regress_user2.
+SET SESSION AUTHORIZATION regress_user1;
+GRANT SELECT (a, b) ON atest12 TO PUBLIC;
+SET SESSION AUTHORIZATION regress_user2;
+
+-- Now regress_user2 will also get a good row estimate.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12v x, atest12v y WHERE x.a = y.b;
+
+-- But not for this, due to lack of table-wide permissions needed
+-- to make use of the expression index's statistics.
+EXPLAIN (COSTS OFF) SELECT * FROM atest12 x, atest12 y
+  WHERE x.a = y.b and abs(y.a) <<< 5;
+
+-- clean up (regress_user1's objects are all dropped later)
+DROP FUNCTION leak2(integer, integer) CASCADE;
+
+
 -- groups
 
 SET SESSION AUTHORIZATION regress_user3;