Improve hash_create()'s API for some added robustness.

Invent a new flag bit HASH_STRINGS to specify C-string hashing, which
was formerly the default; and add assertions insisting that exactly
one of the bits HASH_STRINGS, HASH_BLOBS, and HASH_FUNCTION be set.
This is in hopes of preventing recurrences of the type of oversight
fixed in commit a1b8aa1e4 (i.e., mistakenly omitting HASH_BLOBS).

Also, when HASH_STRINGS is specified, insist that the keysize be
more than 8 bytes.  This is a heuristic, but it should catch
accidental use of HASH_STRINGS for integer or pointer keys.
(Nearly all existing use-cases set the keysize to NAMEDATALEN or
more, so there's little reason to think this restriction should
be problematic.)

Tweak hash_create() to insist that the HASH_ELEM flag be set, and
remove the defaults it had for keysize and entrysize.  Since those
defaults were undocumented and basically useless, no callers
omitted HASH_ELEM anyway.

Also, remove memset's zeroing the HASHCTL parameter struct from
those callers that had one.  This has never been really necessary,
and while it wasn't a bad coding convention it was confusing that
some callers did it and some did not.  We might as well save a few
cycles by standardizing on "not".

Also improve the documentation for hash_create().

In passing, improve reinit.c's usage of a hash table by storing
the key as a binary Oid rather than a string; and, since that's
a temporary hash table, allocate it in CurrentMemoryContext for
neatness.

Discussion: https://postgr.es/m/590625.1607878171@sss.pgh.pa.us

contrib/dblink/dblink.c

@@ -2607,7 +2607,8 @@ createConnHash(void)
 	ctl.keysize = NAMEDATALEN;
 	ctl.entrysize = sizeof(remoteConnHashEnt);
 
-	return hash_create("Remote Con hash", NUMCONN, &ctl, HASH_ELEM);
+	return hash_create("Remote Con hash", NUMCONN, &ctl,
+					   HASH_ELEM | HASH_STRINGS);
 }
 
 static void

contrib/pg_stat_statements/pg_stat_statements.c

@@ -567,7 +567,6 @@ pgss_shmem_startup(void)
 		pgss->stats.dealloc = 0;
 	}
 
-	memset(&info, 0, sizeof(info));
 	info.keysize = sizeof(pgssHashKey);
 	info.entrysize = sizeof(pgssEntry);
 	pgss_hash = ShmemInitHash("pg_stat_statements hash",

contrib/postgres_fdw/connection.c

@@ -119,14 +119,11 @@ GetConnection(UserMapping *user, bool will_prep_stmt)
 	{
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(ConnCacheKey);
 		ctl.entrysize = sizeof(ConnCacheEntry);
-		/* allocate ConnectionHash in the cache context */
-		ctl.hcxt = CacheMemoryContext;
 		ConnectionHash = hash_create("postgres_fdw connections", 8,
 									 &ctl,
-									 HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+									 HASH_ELEM | HASH_BLOBS);
 
 		/*
 		 * Register some callback functions that manage connection cleanup.

contrib/postgres_fdw/shippable.c

@@ -93,7 +93,6 @@ InitializeShippableCache(void)
 	HASHCTL		ctl;
 
 	/* Create the hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(ShippableCacheKey);
 	ctl.entrysize = sizeof(ShippableCacheEntry);
 	ShippableCacheHash =

contrib/tablefunc/tablefunc.c

@@ -714,7 +714,6 @@ load_categories_hash(char *cats_sql, MemoryContext per_query_ctx)
 	MemoryContext SPIcontext;
 
 	/* initialize the category hash table */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = MAX_CATNAME_LEN;
 	ctl.entrysize = sizeof(crosstab_HashEnt);
 	ctl.hcxt = per_query_ctx;
@@ -726,7 +725,7 @@ load_categories_hash(char *cats_sql, MemoryContext per_query_ctx)
 	crosstab_hash = hash_create("crosstab hash",
 								INIT_CATS,
 								&ctl,
-								HASH_ELEM | HASH_CONTEXT);
+								HASH_ELEM | HASH_STRINGS | HASH_CONTEXT);
 
 	/* Connect to SPI manager */
 	if ((ret = SPI_connect()) < 0)

src/backend/access/gist/gistbuildbuffers.c

@@ -76,7 +76,6 @@ gistInitBuildBuffers(int pagesPerBuffer, int levelStep, int maxLevel)
 	 * nodeBuffersTab hash is association between index blocks and it's
 	 * buffers.
 	 */
-	memset(&hashCtl, 0, sizeof(hashCtl));
 	hashCtl.keysize = sizeof(BlockNumber);
 	hashCtl.entrysize = sizeof(GISTNodeBuffer);
 	hashCtl.hcxt = CurrentMemoryContext;

src/backend/access/hash/hashpage.c

@@ -1363,7 +1363,6 @@ _hash_finish_split(Relation rel, Buffer metabuf, Buffer obuf, Bucket obucket,
 	bool		found;
 
 	/* Initialize hash tables used to track TIDs */
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(ItemPointerData);
 	hash_ctl.entrysize = sizeof(ItemPointerData);
 	hash_ctl.hcxt = CurrentMemoryContext;

src/backend/access/heap/rewriteheap.c

@@ -266,7 +266,6 @@ begin_heap_rewrite(Relation old_heap, Relation new_heap, TransactionId oldest_xm
 	state->rs_cxt = rw_cxt;
 
 	/* Initialize hash tables used to track update chains */
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(TidHashKey);
 	hash_ctl.entrysize = sizeof(UnresolvedTupData);
 	hash_ctl.hcxt = state->rs_cxt;
@@ -824,7 +823,6 @@ logical_begin_heap_rewrite(RewriteState state)
 	state->rs_begin_lsn = GetXLogInsertRecPtr();
 	state->rs_num_rewrite_mappings = 0;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(TransactionId);
 	hash_ctl.entrysize = sizeof(RewriteMappingFile);
 	hash_ctl.hcxt = state->rs_cxt;

src/backend/access/transam/xlogutils.c

@@ -113,7 +113,6 @@ log_invalid_page(RelFileNode node, ForkNumber forkno, BlockNumber blkno,
 		/* create hash table when first needed */
 		HASHCTL		ctl;
 
-		memset(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(xl_invalid_page_key);
 		ctl.entrysize = sizeof(xl_invalid_page);
 

src/backend/catalog/pg_enum.c

@@ -188,7 +188,6 @@ init_enum_blacklist(void)
 {
 	HASHCTL		hash_ctl;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(Oid);
 	hash_ctl.hcxt = TopTransactionContext;

src/backend/catalog/pg_inherits.c

@@ -171,7 +171,6 @@ find_all_inheritors(Oid parentrelId, LOCKMODE lockmode, List **numparents)
 			   *rel_numparents;
 	ListCell   *l;
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(SeenRelsEntry);
 	ctl.hcxt = CurrentMemoryContext;

src/backend/commands/async.c

@@ -2375,7 +2375,6 @@ AddEventToPendingNotifies(Notification *n)
 		ListCell   *l;
 
 		/* Create the hash table */
-		MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = sizeof(Notification *);
 		hash_ctl.entrysize = sizeof(NotificationHash);
 		hash_ctl.hash = notification_hash;

src/backend/commands/prepare.c

@@ -406,15 +406,13 @@ InitQueryHashTable(void)
 {
 	HASHCTL		hash_ctl;
 
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
-
 	hash_ctl.keysize = NAMEDATALEN;
 	hash_ctl.entrysize = sizeof(PreparedStatement);
 
 	prepared_queries = hash_create("Prepared Queries",
 								   32,
 								   &hash_ctl,
-								   HASH_ELEM);
+								   HASH_ELEM | HASH_STRINGS);
 }
 
 /*

src/backend/commands/sequence.c

@@ -1087,7 +1087,6 @@ create_seq_hashtable(void)
 {
 	HASHCTL		ctl;
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(SeqTableData);
 

src/backend/executor/execPartition.c

@@ -521,7 +521,6 @@ ExecHashSubPlanResultRelsByOid(ModifyTableState *mtstate,
 	HTAB	   *htab;
 	int			i;
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(SubplanResultRelHashElem);
 	ctl.hcxt = CurrentMemoryContext;

src/backend/nodes/extensible.c

@@ -47,11 +47,11 @@ RegisterExtensibleNodeEntry(HTAB **p_htable, const char *htable_label,
 	{
 		HASHCTL		ctl;
 
-		memset(&ctl, 0, sizeof(HASHCTL));
 		ctl.keysize = EXTNODENAME_MAX_LEN;
 		ctl.entrysize = sizeof(ExtensibleNodeEntry);
 
-		*p_htable = hash_create(htable_label, 100, &ctl, HASH_ELEM);
+		*p_htable = hash_create(htable_label, 100, &ctl,
+								HASH_ELEM | HASH_STRINGS);
 	}
 
 	if (strlen(extnodename) >= EXTNODENAME_MAX_LEN)

src/backend/optimizer/util/predtest.c

@@ -1982,7 +1982,6 @@ lookup_proof_cache(Oid pred_op, Oid clause_op, bool refute_it)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(OprProofCacheKey);
 		ctl.entrysize = sizeof(OprProofCacheEntry);
 		OprProofCacheHash = hash_create("Btree proof lookup cache", 256,

src/backend/optimizer/util/relnode.c

@@ -400,7 +400,6 @@ build_join_rel_hash(PlannerInfo *root)
 	ListCell   *l;
 
 	/* Create the hash table */
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Relids);
 	hash_ctl.entrysize = sizeof(JoinHashEntry);
 	hash_ctl.hash = bitmap_hash;

src/backend/parser/parse_oper.c

@@ -999,7 +999,6 @@ find_oper_cache_entry(OprCacheKey *key)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(OprCacheKey);
 		ctl.entrysize = sizeof(OprCacheEntry);
 		OprCacheHash = hash_create("Operator lookup cache", 256,

src/backend/partitioning/partdesc.c

@@ -286,13 +286,13 @@ CreatePartitionDirectory(MemoryContext mcxt)
 	PartitionDirectory pdir;
 	HASHCTL		ctl;
 
-	MemSet(&ctl, 0, sizeof(HASHCTL));
+	pdir = palloc(sizeof(PartitionDirectoryData));
+	pdir->pdir_mcxt = mcxt;
+
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(PartitionDirectoryEntry);
 	ctl.hcxt = mcxt;
 
-	pdir = palloc(sizeof(PartitionDirectoryData));
-	pdir->pdir_mcxt = mcxt;
 	pdir->pdir_hash = hash_create("partition directory", 256, &ctl,
 								  HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 

src/backend/postmaster/autovacuum.c

@@ -2043,7 +2043,6 @@ do_autovacuum(void)
 	pg_class_desc = CreateTupleDescCopy(RelationGetDescr(classRel));
 
 	/* create hash table for toast <-> main relid mapping */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(av_relation);
 

src/backend/postmaster/checkpointer.c

@@ -1161,7 +1161,6 @@ CompactCheckpointerRequestQueue(void)
 	skip_slot = palloc0(sizeof(bool) * CheckpointerShmem->num_requests);
 
 	/* Initialize temporary hash table */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(CheckpointerRequest);
 	ctl.entrysize = sizeof(struct CheckpointerSlotMapping);
 	ctl.hcxt = CurrentMemoryContext;

src/backend/postmaster/pgstat.c

@@ -1265,7 +1265,6 @@ pgstat_collect_oids(Oid catalogid, AttrNumber anum_oid)
 	HeapTuple	tup;
 	Snapshot	snapshot;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(Oid);
 	hash_ctl.hcxt = CurrentMemoryContext;
@@ -1815,7 +1814,6 @@ pgstat_init_function_usage(FunctionCallInfo fcinfo,
 		/* First time through - initialize function stat table */
 		HASHCTL		hash_ctl;
 
-		memset(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = sizeof(Oid);
 		hash_ctl.entrysize = sizeof(PgStat_BackendFunctionEntry);
 		pgStatFunctions = hash_create("Function stat entries",
@@ -1975,7 +1973,6 @@ get_tabstat_entry(Oid rel_id, bool isshared)
 	{
 		HASHCTL		ctl;
 
-		memset(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(TabStatHashEntry);
 
@@ -4994,7 +4991,6 @@ reset_dbentry_counters(PgStat_StatDBEntry *dbentry)
 	dbentry->stat_reset_timestamp = GetCurrentTimestamp();
 	dbentry->stats_timestamp = 0;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
 	dbentry->tables = hash_create("Per-database table",
@@ -5423,7 +5419,6 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 	/*
 	 * Create the DB hashtable
 	 */
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(PgStat_StatDBEntry);
 	hash_ctl.hcxt = pgStatLocalContext;
@@ -5608,7 +5603,6 @@ pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
 						break;
 				}
 
-				memset(&hash_ctl, 0, sizeof(hash_ctl));
 				hash_ctl.keysize = sizeof(Oid);
 				hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
 				hash_ctl.hcxt = pgStatLocalContext;

src/backend/replication/logical/relation.c

@@ -111,7 +111,6 @@ logicalrep_relmap_init(void)
 								  ALLOCSET_DEFAULT_SIZES);
 
 	/* Initialize the relation hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(LogicalRepRelId);
 	ctl.entrysize = sizeof(LogicalRepRelMapEntry);
 	ctl.hcxt = LogicalRepRelMapContext;
@@ -120,7 +119,6 @@ logicalrep_relmap_init(void)
 								   HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 
 	/* Initialize the type hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(LogicalRepTyp);
 	ctl.hcxt = LogicalRepRelMapContext;
@@ -606,7 +604,6 @@ logicalrep_partmap_init(void)
 								  ALLOCSET_DEFAULT_SIZES);
 
 	/* Initialize the relation hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);	/* partition OID */
 	ctl.entrysize = sizeof(LogicalRepPartMapEntry);
 	ctl.hcxt = LogicalRepPartMapContext;

src/backend/replication/logical/reorderbuffer.c

@@ -1619,8 +1619,6 @@ ReorderBufferBuildTupleCidHash(ReorderBuffer *rb, ReorderBufferTXN *txn)
 	if (!rbtxn_has_catalog_changes(txn) || dlist_is_empty(&txn->tuplecids))
 		return;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
-
 	hash_ctl.keysize = sizeof(ReorderBufferTupleCidKey);
 	hash_ctl.entrysize = sizeof(ReorderBufferTupleCidEnt);
 	hash_ctl.hcxt = rb->context;
@@ -4116,7 +4114,6 @@ ReorderBufferToastInitHash(ReorderBuffer *rb, ReorderBufferTXN *txn)
 
 	Assert(txn->toast_hash == NULL);
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(ReorderBufferToastEnt);
 	hash_ctl.hcxt = rb->context;

src/backend/replication/logical/tablesync.c

@@ -372,7 +372,6 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn)
 	{
 		HASHCTL		ctl;
 
-		memset(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(struct tablesync_start_time_mapping);
 		last_start_times = hash_create("Logical replication table sync worker start times",

src/backend/replication/pgoutput/pgoutput.c

@@ -867,22 +867,18 @@ static void
 init_rel_sync_cache(MemoryContext cachectx)
 {
 	HASHCTL		ctl;
-	MemoryContext old_ctxt;
 
 	if (RelationSyncCache != NULL)
 		return;
 
 	/* Make a new hash table for the cache */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(RelationSyncEntry);
 	ctl.hcxt = cachectx;
 
-	old_ctxt = MemoryContextSwitchTo(cachectx);
 	RelationSyncCache = hash_create("logical replication output relation cache",
 									128, &ctl,
 									HASH_ELEM | HASH_CONTEXT | HASH_BLOBS);
-	(void) MemoryContextSwitchTo(old_ctxt);
 
 	Assert(RelationSyncCache != NULL);
 

src/backend/storage/buffer/bufmgr.c

@@ -2505,7 +2505,6 @@ InitBufferPoolAccess(void)
 
 	memset(&PrivateRefCountArray, 0, sizeof(PrivateRefCountArray));
 
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(int32);
 	hash_ctl.entrysize = sizeof(PrivateRefCountEntry);
 

src/backend/storage/buffer/localbuf.c

@@ -465,7 +465,6 @@ InitLocalBuffers(void)
 	}
 
 	/* Create the lookup hash table */
-	MemSet(&info, 0, sizeof(info));
 	info.keysize = sizeof(BufferTag);
 	info.entrysize = sizeof(LocalBufferLookupEnt);
 

src/backend/storage/file/reinit.c

@@ -30,7 +30,7 @@ static void ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname,
 
 typedef struct
 {
-	char		oid[OIDCHARS + 1];
+	Oid			reloid;			/* hash key */
 } unlogged_relation_entry;
 
 /*
@@ -172,10 +172,11 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
 		 * need to be reset.  Otherwise, this cleanup operation would be
 		 * O(n^2).
 		 */
-		memset(&ctl, 0, sizeof(ctl));
-		ctl.keysize = sizeof(unlogged_relation_entry);
+		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(unlogged_relation_entry);
-		hash = hash_create("unlogged hash", 32, &ctl, HASH_ELEM);
+		ctl.hcxt = CurrentMemoryContext;
+		hash = hash_create("unlogged relation OIDs", 32, &ctl,
+						   HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 
 		/* Scan the directory. */
 		dbspace_dir = AllocateDir(dbspacedirname);
@@ -198,9 +199,8 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
 			 * Put the OID portion of the name into the hash table, if it
 			 * isn't already.
 			 */
-			memset(ent.oid, 0, sizeof(ent.oid));
-			memcpy(ent.oid, de->d_name, oidchars);
-			hash_search(hash, &ent, HASH_ENTER, NULL);
+			ent.reloid = atooid(de->d_name);
+			(void) hash_search(hash, &ent, HASH_ENTER, NULL);
 		}
 
 		/* Done with the first pass. */
@@ -224,7 +224,6 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
 		{
 			ForkNumber	forkNum;
 			int			oidchars;
-			bool		found;
 			unlogged_relation_entry ent;
 
 			/* Skip anything that doesn't look like a relation data file. */
@@ -238,14 +237,10 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
 
 			/*
 			 * See whether the OID portion of the name shows up in the hash
-			 * table.
+			 * table.  If so, nuke it!
 			 */
-			memset(ent.oid, 0, sizeof(ent.oid));
-			memcpy(ent.oid, de->d_name, oidchars);
-			hash_search(hash, &ent, HASH_FIND, &found);
-
-			/* If so, nuke it! */
-			if (found)
+			ent.reloid = atooid(de->d_name);
+			if (hash_search(hash, &ent, HASH_FIND, NULL))
 			{
 				snprintf(rm_path, sizeof(rm_path), "%s/%s",
 						 dbspacedirname, de->d_name);

src/backend/storage/ipc/shmem.c

@@ -292,7 +292,6 @@ void
 InitShmemIndex(void)
 {
 	HASHCTL		info;
-	int			hash_flags;
 
 	/*
 	 * Create the shared memory shmem index.
@@ -304,11 +303,11 @@ InitShmemIndex(void)
 	 */
 	info.keysize = SHMEM_INDEX_KEYSIZE;
 	info.entrysize = sizeof(ShmemIndexEnt);
-	hash_flags = HASH_ELEM;
 
 	ShmemIndex = ShmemInitHash("ShmemIndex",
 							   SHMEM_INDEX_SIZE, SHMEM_INDEX_SIZE,
-							   &info, hash_flags);
+							   &info,
+							   HASH_ELEM | HASH_STRINGS);
 }
 
 /*
@@ -329,6 +328,11 @@ InitShmemIndex(void)
  * whose maximum size is certain, this should be equal to max_size; that
  * ensures that no run-time out-of-shared-memory failures can occur.
  *
+ * *infoP and hash_flags must specify at least the entry sizes and key
+ * comparison semantics (see hash_create()).  Flag bits and values specific
+ * to shared-memory hash tables are added here, except that callers may
+ * choose to specify HASH_PARTITION and/or HASH_FIXED_SIZE.
+ *
  * Note: before Postgres 9.0, this function returned NULL for some failure
  * cases.  Now, it always throws error instead, so callers need not check
  * for NULL.

src/backend/storage/ipc/standby.c

@@ -81,7 +81,6 @@ InitRecoveryTransactionEnvironment(void)
 	 * Initialize the hash table for tracking the list of locks held by each
 	 * transaction.
 	 */
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(TransactionId);
 	hash_ctl.entrysize = sizeof(RecoveryLockListsEntry);
 	RecoveryLockLists = hash_create("RecoveryLockLists",

src/backend/storage/lmgr/lock.c

@@ -419,7 +419,6 @@ InitLocks(void)
 	 * Allocate hash table for LOCK structs.  This stores per-locked-object
 	 * information.
 	 */
-	MemSet(&info, 0, sizeof(info));
 	info.keysize = sizeof(LOCKTAG);
 	info.entrysize = sizeof(LOCK);
 	info.num_partitions = NUM_LOCK_PARTITIONS;

src/backend/storage/lmgr/lwlock.c

@@ -342,7 +342,6 @@ init_lwlock_stats(void)
 											 ALLOCSET_DEFAULT_SIZES);
 	MemoryContextAllowInCriticalSection(lwlock_stats_cxt, true);
 
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(lwlock_stats_key);
 	ctl.entrysize = sizeof(lwlock_stats);
 	ctl.hcxt = lwlock_stats_cxt;

src/backend/storage/lmgr/predicate.c

@@ -1096,7 +1096,6 @@ InitPredicateLocks(void)
 	 * Allocate hash table for PREDICATELOCKTARGET structs.  This stores
 	 * per-predicate-lock-target information.
 	 */
-	MemSet(&info, 0, sizeof(info));
 	info.keysize = sizeof(PREDICATELOCKTARGETTAG);
 	info.entrysize = sizeof(PREDICATELOCKTARGET);
 	info.num_partitions = NUM_PREDICATELOCK_PARTITIONS;
@@ -1129,7 +1128,6 @@ InitPredicateLocks(void)
 	 * Allocate hash table for PREDICATELOCK structs.  This stores per
 	 * xact-lock-of-a-target information.
 	 */
-	MemSet(&info, 0, sizeof(info));
 	info.keysize = sizeof(PREDICATELOCKTAG);
 	info.entrysize = sizeof(PREDICATELOCK);
 	info.hash = predicatelock_hash;
@@ -1212,7 +1210,6 @@ InitPredicateLocks(void)
 	 * Allocate hash table for SERIALIZABLEXID structs.  This stores per-xid
 	 * information for serializable transactions which have accessed data.
 	 */
-	MemSet(&info, 0, sizeof(info));
 	info.keysize = sizeof(SERIALIZABLEXIDTAG);
 	info.entrysize = sizeof(SERIALIZABLEXID);
 
@@ -1853,7 +1850,6 @@ CreateLocalPredicateLockHash(void)
 
 	/* Initialize the backend-local hash table of parent locks */
 	Assert(LocalPredicateLockHash == NULL);
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(PREDICATELOCKTARGETTAG);
 	hash_ctl.entrysize = sizeof(LOCALPREDICATELOCK);
 	LocalPredicateLockHash = hash_create("Local predicate lock",

src/backend/storage/smgr/smgr.c

@@ -154,7 +154,6 @@ smgropen(RelFileNode rnode, BackendId backend)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(RelFileNodeBackend);
 		ctl.entrysize = sizeof(SMgrRelationData);
 		SMgrRelationHash = hash_create("smgr relation table", 400,

src/backend/storage/sync/sync.c

@@ -150,7 +150,6 @@ InitSync(void)
 											  ALLOCSET_DEFAULT_SIZES);
 		MemoryContextAllowInCriticalSection(pendingOpsCxt, true);
 
-		MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = sizeof(FileTag);
 		hash_ctl.entrysize = sizeof(PendingFsyncEntry);
 		hash_ctl.hcxt = pendingOpsCxt;

src/backend/tsearch/ts_typanalyze.c

@@ -180,7 +180,6 @@ compute_tsvector_stats(VacAttrStats *stats,
 	 * worry about overflowing the initial size. Also we don't need to pay any
 	 * attention to locking and memory management.
 	 */
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(LexemeHashKey);
 	hash_ctl.entrysize = sizeof(TrackItem);
 	hash_ctl.hash = lexeme_hash;

src/backend/utils/adt/array_typanalyze.c

@@ -277,7 +277,6 @@ compute_array_stats(VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc,
 	 * worry about overflowing the initial size. Also we don't need to pay any
 	 * attention to locking and memory management.
 	 */
-	MemSet(&elem_hash_ctl, 0, sizeof(elem_hash_ctl));
 	elem_hash_ctl.keysize = sizeof(Datum);
 	elem_hash_ctl.entrysize = sizeof(TrackItem);
 	elem_hash_ctl.hash = element_hash;
@@ -289,7 +288,6 @@ compute_array_stats(VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc,
 							   HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
 
 	/* hashtable for array distinct elements counts */
-	MemSet(&count_hash_ctl, 0, sizeof(count_hash_ctl));
 	count_hash_ctl.keysize = sizeof(int);
 	count_hash_ctl.entrysize = sizeof(DECountItem);
 	count_hash_ctl.hcxt = CurrentMemoryContext;

src/backend/utils/adt/jsonfuncs.c

@@ -3439,14 +3439,13 @@ get_json_object_as_hash(char *json, int len, const char *funcname)
 	JsonLexContext *lex = makeJsonLexContextCstringLen(json, len, GetDatabaseEncoding(), true);
 	JsonSemAction *sem;
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = NAMEDATALEN;
 	ctl.entrysize = sizeof(JsonHashEntry);
 	ctl.hcxt = CurrentMemoryContext;
 	tab = hash_create("json object hashtable",
 					  100,
 					  &ctl,
-					  HASH_ELEM | HASH_CONTEXT);
+					  HASH_ELEM | HASH_STRINGS | HASH_CONTEXT);
 
 	state = palloc0(sizeof(JHashState));
 	sem = palloc0(sizeof(JsonSemAction));
@@ -3831,14 +3830,13 @@ populate_recordset_object_start(void *state)
 		return;
 
 	/* Object at level 1: set up a new hash table for this object */
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = NAMEDATALEN;
 	ctl.entrysize = sizeof(JsonHashEntry);
 	ctl.hcxt = CurrentMemoryContext;
 	_state->json_hash = hash_create("json object hashtable",
 									100,
 									&ctl,
-									HASH_ELEM | HASH_CONTEXT);
+									HASH_ELEM | HASH_STRINGS | HASH_CONTEXT);
 }
 
 static void

src/backend/utils/adt/pg_locale.c

@@ -1297,7 +1297,6 @@ lookup_collation_cache(Oid collation, bool set_flags)
 		/* First time through, initialize the hash table */
 		HASHCTL		ctl;
 
-		memset(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(collation_cache_entry);
 		collation_cache = hash_create("Collation cache", 100, &ctl,

src/backend/utils/adt/ri_triggers.c

@@ -2540,7 +2540,6 @@ ri_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(RI_ConstraintInfo);
 	ri_constraint_cache = hash_create("RI constraint cache",
@@ -2552,14 +2551,12 @@ ri_InitHashTables(void)
 								  InvalidateConstraintCacheCallBack,
 								  (Datum) 0);
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(RI_QueryKey);
 	ctl.entrysize = sizeof(RI_QueryHashEntry);
 	ri_query_cache = hash_create("RI query cache",
 								 RI_INIT_QUERYHASHSIZE,
 								 &ctl, HASH_ELEM | HASH_BLOBS);
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(RI_CompareKey);
 	ctl.entrysize = sizeof(RI_CompareHashEntry);
 	ri_compare_cache = hash_create("RI compare cache",

src/backend/utils/adt/ruleutils.c

@@ -3464,14 +3464,14 @@ set_rtable_names(deparse_namespace *dpns, List *parent_namespaces,
 	 * We use a hash table to hold known names, so that this process is O(N)
 	 * not O(N^2) for N names.
 	 */
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = NAMEDATALEN;
 	hash_ctl.entrysize = sizeof(NameHashEntry);
 	hash_ctl.hcxt = CurrentMemoryContext;
 	names_hash = hash_create("set_rtable_names names",
 							 list_length(dpns->rtable),
 							 &hash_ctl,
-							 HASH_ELEM | HASH_CONTEXT);
+							 HASH_ELEM | HASH_STRINGS | HASH_CONTEXT);
+
 	/* Preload the hash table with names appearing in parent_namespaces */
 	foreach(lc, parent_namespaces)
 	{

src/backend/utils/cache/attoptcache.c

@@ -79,7 +79,6 @@ InitializeAttoptCache(void)
 	HASHCTL		ctl;
 
 	/* Initialize the hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(AttoptCacheKey);
 	ctl.entrysize = sizeof(AttoptCacheEntry);
 	AttoptCacheHash =

src/backend/utils/cache/evtcache.c

@@ -118,7 +118,6 @@ BuildEventTriggerCache(void)
 	EventTriggerCacheState = ETCS_REBUILD_STARTED;
 
 	/* Create new hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(EventTriggerEvent);
 	ctl.entrysize = sizeof(EventTriggerCacheEntry);
 	ctl.hcxt = EventTriggerCacheContext;

src/backend/utils/cache/relcache.c

@@ -1607,7 +1607,6 @@ LookupOpclassInfo(Oid operatorClassOid,
 		/* First time through: initialize the opclass cache */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(OpClassCacheEnt);
 		OpClassCache = hash_create("Operator class cache", 64,
@@ -3775,7 +3774,6 @@ RelationCacheInitialize(void)
 	/*
 	 * create hashtable that indexes the relcache
 	 */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(RelIdCacheEnt);
 	RelationIdCache = hash_create("Relcache by OID", INITRELCACHESIZE,

src/backend/utils/cache/relfilenodemap.c

@@ -110,17 +110,15 @@ InitializeRelfilenodeMap(void)
 	relfilenode_skey[0].sk_attno = Anum_pg_class_reltablespace;
 	relfilenode_skey[1].sk_attno = Anum_pg_class_relfilenode;
 
-	/* Initialize the hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
-	ctl.keysize = sizeof(RelfilenodeMapKey);
-	ctl.entrysize = sizeof(RelfilenodeMapEntry);
-	ctl.hcxt = CacheMemoryContext;
-
 	/*
 	 * Only create the RelfilenodeMapHash now, so we don't end up partially
 	 * initialized when fmgr_info_cxt() above ERRORs out with an out of memory
 	 * error.
 	 */
+	ctl.keysize = sizeof(RelfilenodeMapKey);
+	ctl.entrysize = sizeof(RelfilenodeMapEntry);
+	ctl.hcxt = CacheMemoryContext;
+
 	RelfilenodeMapHash =
 		hash_create("RelfilenodeMap cache", 64, &ctl,
 					HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);

src/backend/utils/cache/spccache.c

@@ -79,7 +79,6 @@ InitializeTableSpaceCache(void)
 	HASHCTL		ctl;
 
 	/* Initialize the hash table. */
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(TableSpaceCacheEntry);
 	TableSpaceCacheHash =

src/backend/utils/cache/ts_cache.c

@@ -117,7 +117,6 @@ lookup_ts_parser_cache(Oid prsId)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(TSParserCacheEntry);
 		TSParserCacheHash = hash_create("Tsearch parser cache", 4,
@@ -215,7 +214,6 @@ lookup_ts_dictionary_cache(Oid dictId)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(TSDictionaryCacheEntry);
 		TSDictionaryCacheHash = hash_create("Tsearch dictionary cache", 8,
@@ -365,7 +363,6 @@ init_ts_config_cache(void)
 {
 	HASHCTL		ctl;
 
-	MemSet(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(TSConfigCacheEntry);
 	TSConfigCacheHash = hash_create("Tsearch configuration cache", 16,

src/backend/utils/cache/typcache.c

@@ -341,7 +341,6 @@ lookup_type_cache(Oid type_id, int flags)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(Oid);
 		ctl.entrysize = sizeof(TypeCacheEntry);
 		TypeCacheHash = hash_create("Type information cache", 64,
@@ -1874,7 +1873,6 @@ assign_record_type_typmod(TupleDesc tupDesc)
 		/* First time through: initialize the hash table */
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(TupleDesc);	/* just the pointer */
 		ctl.entrysize = sizeof(RecordCacheEntry);
 		ctl.hash = record_type_typmod_hash;

src/backend/utils/fmgr/dfmgr.c

@@ -680,13 +680,12 @@ find_rendezvous_variable(const char *varName)
 	{
 		HASHCTL		ctl;
 
-		MemSet(&ctl, 0, sizeof(ctl));
 		ctl.keysize = NAMEDATALEN;
 		ctl.entrysize = sizeof(rendezvousHashEntry);
 		rendezvousHash = hash_create("Rendezvous variable hash",
 									 16,
 									 &ctl,
-									 HASH_ELEM);
+									 HASH_ELEM | HASH_STRINGS);
 	}
 
 	/* Find or create the hashtable entry for this varName */

src/backend/utils/fmgr/fmgr.c

@@ -565,7 +565,6 @@ record_C_func(HeapTuple procedureTuple,
 	{
 		HASHCTL		hash_ctl;
 
-		MemSet(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = sizeof(Oid);
 		hash_ctl.entrysize = sizeof(CFuncHashTabEntry);
 		CFuncHash = hash_create("CFuncHash",

src/backend/utils/hash/dynahash.c

@@ -30,11 +30,12 @@
  * dynahash.c provides support for these types of lookup keys:
  *
  * 1. Null-terminated C strings (truncated if necessary to fit in keysize),
- * compared as though by strcmp().  This is the default behavior.
+ * compared as though by strcmp().  This is selected by specifying the
+ * HASH_STRINGS flag to hash_create.
  *
  * 2. Arbitrary binary data of size keysize, compared as though by memcmp().
  * (Caller must ensure there are no undefined padding bits in the keys!)
- * This is selected by specifying HASH_BLOBS flag to hash_create.
+ * This is selected by specifying the HASH_BLOBS flag to hash_create.
  *
  * 3. More complex key behavior can be selected by specifying user-supplied
  * hashing, comparison, and/or key-copying functions.  At least a hashing
@@ -47,8 +48,8 @@
  *   locks.
  * - Shared memory hashes are allocated in a fixed size area at startup and
  *   are discoverable by name from other processes.
- * - Because entries don't need to be moved in the case of hash conflicts, has
- *   better performance for large entries
+ * - Because entries don't need to be moved in the case of hash conflicts,
+ *   dynahash has better performance for large entries.
  * - Guarantees stable pointers to entries.
  *
  * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
@@ -316,6 +317,28 @@ string_compare(const char *key1, const char *key2, Size keysize)
  *	*info: additional table parameters, as indicated by flags
  *	flags: bitmask indicating which parameters to take from *info
  *
+ * The flags value *must* include HASH_ELEM.  (Formerly, this was nominally
+ * optional, but the default keysize and entrysize values were useless.)
+ * The flags value must also include exactly one of HASH_STRINGS, HASH_BLOBS,
+ * or HASH_FUNCTION, to define the key hashing semantics (C strings,
+ * binary blobs, or custom, respectively).  Callers specifying a custom
+ * hash function will likely also want to use HASH_COMPARE, and perhaps
+ * also HASH_KEYCOPY, to control key comparison and copying.
+ * Another often-used flag is HASH_CONTEXT, to allocate the hash table
+ * under info->hcxt rather than under TopMemoryContext; the default
+ * behavior is only suitable for session-lifespan hash tables.
+ * Other flags bits are special-purpose and seldom used, except for those
+ * associated with shared-memory hash tables, for which see ShmemInitHash().
+ *
+ * Fields in *info are read only when the associated flags bit is set.
+ * It is not necessary to initialize other fields of *info.
+ * Neither tabname nor *info need persist after the hash_create() call.
+ *
+ * Note: It is deprecated for callers of hash_create() to explicitly specify
+ * string_hash, tag_hash, uint32_hash, or oid_hash.  Just set HASH_STRINGS or
+ * HASH_BLOBS.  Use HASH_FUNCTION only when you want something other than
+ * one of these.
+ *
  * Note: for a shared-memory hashtable, nelem needs to be a pretty good
  * estimate, since we can't expand the table on the fly.  But an unshared
  * hashtable can be expanded on-the-fly, so it's better for nelem to be
@@ -323,11 +346,19 @@ string_compare(const char *key1, const char *key2, Size keysize)
  * large nelem will penalize hash_seq_search speed without buying much.
  */
 HTAB *
-hash_create(const char *tabname, long nelem, HASHCTL *info, int flags)
+hash_create(const char *tabname, long nelem, const HASHCTL *info, int flags)
 {
 	HTAB	   *hashp;
 	HASHHDR    *hctl;
 
+	/*
+	 * Hash tables now allocate space for key and data, but you have to say
+	 * how much space to allocate.
+	 */
+	Assert(flags & HASH_ELEM);
+	Assert(info->keysize > 0);
+	Assert(info->entrysize >= info->keysize);
+
 	/*
 	 * For shared hash tables, we have a local hash header (HTAB struct) that
 	 * we allocate in TopMemoryContext; all else is in shared memory.
@@ -370,28 +401,43 @@ hash_create(const char *tabname, long nelem, HASHCTL *info, int flags)
 	 * Select the appropriate hash function (see comments at head of file).
 	 */
 	if (flags & HASH_FUNCTION)
+	{
+		Assert(!(flags & (HASH_BLOBS | HASH_STRINGS)));
 		hashp->hash = info->hash;
+	}
 	else if (flags & HASH_BLOBS)
 	{
+		Assert(!(flags & HASH_STRINGS));
 		/* We can optimize hashing for common key sizes */
-		Assert(flags & HASH_ELEM);
 		if (info->keysize == sizeof(uint32))
 			hashp->hash = uint32_hash;
 		else
 			hashp->hash = tag_hash;
 	}
 	else
-		hashp->hash = string_hash;	/* default hash function */
+	{
+		/*
+		 * string_hash used to be considered the default hash method, and in a
+		 * non-assert build it effectively still is.  But we now consider it
+		 * an assertion error to not say HASH_STRINGS explicitly.  To help
+		 * catch mistaken usage of HASH_STRINGS, we also insist on a
+		 * reasonably long string length: if the keysize is only 4 or 8 bytes,
+		 * it's almost certainly an integer or pointer not a string.
+		 */
+		Assert(flags & HASH_STRINGS);
+		Assert(info->keysize > 8);
+
+		hashp->hash = string_hash;
+	}
 
 	/*
 	 * If you don't specify a match function, it defaults to string_compare if
-	 * you used string_hash (either explicitly or by default) and to memcmp
-	 * otherwise.
+	 * you used string_hash, and to memcmp otherwise.
 	 *
 	 * Note: explicitly specifying string_hash is deprecated, because this
 	 * might not work for callers in loadable modules on some platforms due to
 	 * referencing a trampoline instead of the string_hash function proper.
-	 * Just let it default, eh?
+	 * Specify HASH_STRINGS instead.
 	 */
 	if (flags & HASH_COMPARE)
 		hashp->match = info->match;
@@ -505,16 +551,9 @@ hash_create(const char *tabname, long nelem, HASHCTL *info, int flags)
 		hctl->dsize = info->dsize;
 	}
 
-	/*
-	 * hash table now allocates space for key and data but you have to say how
-	 * much space to allocate
-	 */
-	if (flags & HASH_ELEM)
-	{
-		Assert(info->entrysize >= info->keysize);
-		hctl->keysize = info->keysize;
-		hctl->entrysize = info->entrysize;
-	}
+	/* remember the entry sizes, too */
+	hctl->keysize = info->keysize;
+	hctl->entrysize = info->entrysize;
 
 	/* make local copies of heavily-used constant fields */
 	hashp->keysize = hctl->keysize;
@@ -593,10 +632,6 @@ hdefault(HTAB *hashp)
 	hctl->dsize = DEF_DIRSIZE;
 	hctl->nsegs = 0;
 
-	/* rather pointless defaults for key & entry size */
-	hctl->keysize = sizeof(char *);
-	hctl->entrysize = 2 * sizeof(char *);
-
 	hctl->num_partitions = 0;	/* not partitioned */
 
 	/* table has no fixed maximum size */

src/backend/utils/mmgr/portalmem.c

@@ -119,7 +119,7 @@ EnablePortalManager(void)
 	 * create, initially
 	 */
 	PortalHashTable = hash_create("Portal hash", PORTALS_PER_USER,
-								  &ctl, HASH_ELEM);
+								  &ctl, HASH_ELEM | HASH_STRINGS);
 }
 
 /*

src/backend/utils/time/combocid.c

@@ -223,7 +223,6 @@ GetComboCommandId(CommandId cmin, CommandId cmax)
 		sizeComboCids = CCID_ARRAY_SIZE;
 		usedComboCids = 0;
 
-		memset(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = sizeof(ComboCidKeyData);
 		hash_ctl.entrysize = sizeof(ComboCidEntryData);
 		hash_ctl.hcxt = TopTransactionContext;

src/include/utils/hsearch.h

@@ -64,25 +64,36 @@ typedef struct HTAB HTAB;
 /* Only those fields indicated by hash_flags need be set */
 typedef struct HASHCTL
 {
+	/* Used if HASH_PARTITION flag is set: */
 	long		num_partitions; /* # partitions (must be power of 2) */
+	/* Used if HASH_SEGMENT flag is set: */
 	long		ssize;			/* segment size */
+	/* Used if HASH_DIRSIZE flag is set: */
 	long		dsize;			/* (initial) directory size */
 	long		max_dsize;		/* limit to dsize if dir size is limited */
+	/* Used if HASH_ELEM flag is set (which is now required): */
 	Size		keysize;		/* hash key length in bytes */
 	Size		entrysize;		/* total user element size in bytes */
+	/* Used if HASH_FUNCTION flag is set: */
 	HashValueFunc hash;			/* hash function */
+	/* Used if HASH_COMPARE flag is set: */
 	HashCompareFunc match;		/* key comparison function */
+	/* Used if HASH_KEYCOPY flag is set: */
 	HashCopyFunc keycopy;		/* key copying function */
+	/* Used if HASH_ALLOC flag is set: */
 	HashAllocFunc alloc;		/* memory allocator */
+	/* Used if HASH_CONTEXT flag is set: */
 	MemoryContext hcxt;			/* memory context to use for allocations */
+	/* Used if HASH_SHARED_MEM flag is set: */
 	HASHHDR    *hctl;			/* location of header in shared mem */
 } HASHCTL;
 
-/* Flags to indicate which parameters are supplied */
+/* Flag bits for hash_create; most indicate which parameters are supplied */
 #define HASH_PARTITION	0x0001	/* Hashtable is used w/partitioned locking */
 #define HASH_SEGMENT	0x0002	/* Set segment size */
 #define HASH_DIRSIZE	0x0004	/* Set directory size (initial and max) */
-#define HASH_ELEM		0x0010	/* Set keysize and entrysize */
+#define HASH_ELEM		0x0008	/* Set keysize and entrysize (now required!) */
+#define HASH_STRINGS	0x0010	/* Select support functions for string keys */
 #define HASH_BLOBS		0x0020	/* Select support functions for binary keys */
 #define HASH_FUNCTION	0x0040	/* Set user defined hash function */
 #define HASH_COMPARE	0x0080	/* Set user defined comparison function */
@@ -93,7 +104,6 @@ typedef struct HASHCTL
 #define HASH_ATTACH		0x1000	/* Do not initialize hctl */
 #define HASH_FIXED_SIZE 0x2000	/* Initial size is a hard limit */
 
-
 /* max_dsize value to indicate expansible directory */
 #define NO_MAX_DSIZE			(-1)
 
@@ -116,13 +126,9 @@ typedef struct
 
 /*
  * prototypes for functions in dynahash.c
- *
- * Note: It is deprecated for callers of hash_create to explicitly specify
- * string_hash, tag_hash, uint32_hash, or oid_hash.  Just set HASH_BLOBS or
- * not.  Use HASH_FUNCTION only when you want something other than those.
  */
 extern HTAB *hash_create(const char *tabname, long nelem,
-						 HASHCTL *info, int flags);
+						 const HASHCTL *info, int flags);
 extern void hash_destroy(HTAB *hashp);
 extern void hash_stats(const char *where, HTAB *hashp);
 extern void *hash_search(HTAB *hashp, const void *keyPtr, HASHACTION action,

src/pl/plperl/plperl.c

@@ -458,7 +458,6 @@ _PG_init(void)
 	/*
 	 * Create hash tables.
 	 */
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(plperl_interp_desc);
 	plperl_interp_hash = hash_create("PL/Perl interpreters",
@@ -466,7 +465,6 @@ _PG_init(void)
 									 &hash_ctl,
 									 HASH_ELEM | HASH_BLOBS);
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(plperl_proc_key);
 	hash_ctl.entrysize = sizeof(plperl_proc_ptr);
 	plperl_proc_hash = hash_create("PL/Perl procedures",
@@ -580,13 +578,12 @@ select_perl_context(bool trusted)
 	{
 		HASHCTL		hash_ctl;
 
-		memset(&hash_ctl, 0, sizeof(hash_ctl));
 		hash_ctl.keysize = NAMEDATALEN;
 		hash_ctl.entrysize = sizeof(plperl_query_entry);
 		interp_desc->query_hash = hash_create("PL/Perl queries",
 											  32,
 											  &hash_ctl,
-											  HASH_ELEM);
+											  HASH_ELEM | HASH_STRINGS);
 	}
 
 	/*

src/pl/plpgsql/src/pl_comp.c

@@ -2567,7 +2567,6 @@ plpgsql_HashTableInit(void)
 	/* don't allow double-initialization */
 	Assert(plpgsql_HashTable == NULL);
 
-	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(PLpgSQL_func_hashkey);
 	ctl.entrysize = sizeof(plpgsql_HashEnt);
 	plpgsql_HashTable = hash_create("PLpgSQL function hash",

src/pl/plpgsql/src/pl_exec.c

@@ -4058,7 +4058,6 @@ plpgsql_estate_setup(PLpgSQL_execstate *estate,
 	{
 		estate->simple_eval_estate = simple_eval_estate;
 		/* Private cast hash just lives in function's main context */
-		memset(&ctl, 0, sizeof(ctl));
 		ctl.keysize = sizeof(plpgsql_CastHashKey);
 		ctl.entrysize = sizeof(plpgsql_CastHashEntry);
 		ctl.hcxt = CurrentMemoryContext;
@@ -4077,7 +4076,6 @@ plpgsql_estate_setup(PLpgSQL_execstate *estate,
 			shared_cast_context = AllocSetContextCreate(TopMemoryContext,
 														"PLpgSQL cast info",
 														ALLOCSET_DEFAULT_SIZES);
-			memset(&ctl, 0, sizeof(ctl));
 			ctl.keysize = sizeof(plpgsql_CastHashKey);
 			ctl.entrysize = sizeof(plpgsql_CastHashEntry);
 			ctl.hcxt = shared_cast_context;

src/pl/plpython/plpy_plpymodule.c

@@ -214,7 +214,6 @@ PLy_add_exceptions(PyObject *plpy)
 	PLy_exc_spi_error = PLy_create_exception("plpy.SPIError", NULL, NULL,
 											 "SPIError", plpy);
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(int);
 	hash_ctl.entrysize = sizeof(PLyExceptionEntry);
 	PLy_spi_exceptions = hash_create("PL/Python SPI exceptions", 256,

src/pl/plpython/plpy_procedure.c

@@ -34,7 +34,6 @@ init_procedure_caches(void)
 {
 	HASHCTL		hash_ctl;
 
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(PLyProcedureKey);
 	hash_ctl.entrysize = sizeof(PLyProcedureEntry);
 	PLy_procedure_cache = hash_create("PL/Python procedures", 32, &hash_ctl,

src/pl/tcl/pltcl.c

@@ -439,7 +439,6 @@ _PG_init(void)
 	/************************************************************
 	 * Create the hash table for working interpreters
 	 ************************************************************/
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(Oid);
 	hash_ctl.entrysize = sizeof(pltcl_interp_desc);
 	pltcl_interp_htab = hash_create("PL/Tcl interpreters",
@@ -450,7 +449,6 @@ _PG_init(void)
 	/************************************************************
 	 * Create the hash table for function lookup
 	 ************************************************************/
-	memset(&hash_ctl, 0, sizeof(hash_ctl));
 	hash_ctl.keysize = sizeof(pltcl_proc_key);
 	hash_ctl.entrysize = sizeof(pltcl_proc_ptr);
 	pltcl_proc_htab = hash_create("PL/Tcl functions",

src/timezone/pgtz.c

@@ -203,15 +203,13 @@ init_timezone_hashtable(void)
 {
 	HASHCTL		hash_ctl;
 
-	MemSet(&hash_ctl, 0, sizeof(hash_ctl));
-
 	hash_ctl.keysize = TZ_STRLEN_MAX + 1;
 	hash_ctl.entrysize = sizeof(pg_tz_cache);
 
 	timezone_cache = hash_create("Timezones",
 								 4,
 								 &hash_ctl,
-								 HASH_ELEM);
+								 HASH_ELEM | HASH_STRINGS);
 	if (!timezone_cache)
 		return false;