Fix cache look-up failures while applying changes in logical replication.

While building a new attrmap which maps partition attribute numbers to
remoterel's, we incorrectly update the map for dropped column attributes.
Later, it caused cache look-up failure when we tried to use the map to
fetch the information about attributes.

This also fixes the partition map cache invalidation which was using the
wrong type cast to fetch the entry. We were using stale partition map
entry after invalidation which leads to the assertion or cache look-up
failure.

Reported-by: Shi Yu
Author: Hou Zhijie, Shi Yu
Reviewed-by: Amit Langote, Amit Kapila
Backpatch-through: 13, where it was introduced
Discussion: https://postgr.es/m/OSZPR01MB6310F46CD425A967E4AEF736FDA49@OSZPR01MB6310.jpnprd01.prod.outlook.com

1 files changed, 37 insertions, 25 deletions

diff --git a/src/backend/replication/logical/relation.c b/src/backend/replication/logical/relation.c
index 901bff99745..283afa5d9d7 100644
--- a/src/backend/replication/logical/relation.c
+++ b/src/backend/replication/logical/relation.c
@@ -418,7 +418,7 @@ logicalrep_rel_close(LogicalRepRelMapEntry *rel, LOCKMODE lockmode)
 static void
 logicalrep_partmap_invalidate_cb(Datum arg, Oid reloid)
 {
-	LogicalRepRelMapEntry *entry;
+	LogicalRepPartMapEntry *entry;
 
 	/* Just to be sure. */
 	if (LogicalRepPartMap == NULL)
@@ -431,11 +431,11 @@ logicalrep_partmap_invalidate_cb(Datum arg, Oid reloid)
 		hash_seq_init(&status, LogicalRepPartMap);
 
 		/* TODO, use inverse lookup hashtable? */
-		while ((entry = (LogicalRepRelMapEntry *) hash_seq_search(&status)) != NULL)
+		while ((entry = (LogicalRepPartMapEntry *) hash_seq_search(&status)) != NULL)
 		{
-			if (entry->localreloid == reloid)
+			if (entry->relmapentry.localreloid == reloid)
 			{
-				entry->localrelvalid = false;
+				entry->relmapentry.localrelvalid = false;
 				hash_seq_term(&status);
 				break;
 			}
@@ -448,8 +448,8 @@ logicalrep_partmap_invalidate_cb(Datum arg, Oid reloid)
 
 		hash_seq_init(&status, LogicalRepPartMap);
 
-		while ((entry = (LogicalRepRelMapEntry *) hash_seq_search(&status)) != NULL)
-			entry->localrelvalid = false;
+		while ((entry = (LogicalRepPartMapEntry *) hash_seq_search(&status)) != NULL)
+			entry->relmapentry.localrelvalid = false;
 	}
 }
 
@@ -502,7 +502,6 @@ logicalrep_partition_open(LogicalRepRelMapEntry *root,
 	Oid			partOid = RelationGetRelid(partrel);
 	AttrMap    *attrmap = root->attrmap;
 	bool		found;
-	int			i;
 	MemoryContext oldctx;
 
 	if (LogicalRepPartMap == NULL)
@@ -513,31 +512,40 @@ logicalrep_partition_open(LogicalRepRelMapEntry *root,
 														(void *) &partOid,
 														HASH_ENTER, &found);
 
-	if (found)
-		return &part_entry->relmapentry;
+	entry = &part_entry->relmapentry;
 
-	memset(part_entry, 0, sizeof(LogicalRepPartMapEntry));
+	if (found && entry->localrelvalid)
+		return entry;
 
 	/* Switch to longer-lived context. */
 	oldctx = MemoryContextSwitchTo(LogicalRepPartMapContext);
 
-	part_entry->partoid = partOid;
+	if (!found)
+	{
+		memset(part_entry, 0, sizeof(LogicalRepPartMapEntry));
+		part_entry->partoid = partOid;
+	}
 
-	/* Remote relation is copied as-is from the root entry. */
-	entry = &part_entry->relmapentry;
-	entry->remoterel.remoteid = remoterel->remoteid;
-	entry->remoterel.nspname = pstrdup(remoterel->nspname);
-	entry->remoterel.relname = pstrdup(remoterel->relname);
-	entry->remoterel.natts = remoterel->natts;
-	entry->remoterel.attnames = palloc(remoterel->natts * sizeof(char *));
-	entry->remoterel.atttyps = palloc(remoterel->natts * sizeof(Oid));
-	for (i = 0; i < remoterel->natts; i++)
+	if (!entry->remoterel.remoteid)
 	{
-		entry->remoterel.attnames[i] = pstrdup(remoterel->attnames[i]);
-		entry->remoterel.atttyps[i] = remoterel->atttyps[i];
+		int			i;
+
+		/* Remote relation is copied as-is from the root entry. */
+		entry = &part_entry->relmapentry;
+		entry->remoterel.remoteid = remoterel->remoteid;
+		entry->remoterel.nspname = pstrdup(remoterel->nspname);
+		entry->remoterel.relname = pstrdup(remoterel->relname);
+		entry->remoterel.natts = remoterel->natts;
+		entry->remoterel.attnames = palloc(remoterel->natts * sizeof(char *));
+		entry->remoterel.atttyps = palloc(remoterel->natts * sizeof(Oid));
+		for (i = 0; i < remoterel->natts; i++)
+		{
+			entry->remoterel.attnames[i] = pstrdup(remoterel->attnames[i]);
+			entry->remoterel.atttyps[i] = remoterel->atttyps[i];
+		}
+		entry->remoterel.replident = remoterel->replident;
+		entry->remoterel.attkeys = bms_copy(remoterel->attkeys);
 	}
-	entry->remoterel.replident = remoterel->replident;
-	entry->remoterel.attkeys = bms_copy(remoterel->attkeys);
 
 	entry->localrel = partrel;
 	entry->localreloid = partOid;
@@ -562,7 +570,11 @@ logicalrep_partition_open(LogicalRepRelMapEntry *root,
 		{
 			AttrNumber	root_attno = map->attnums[attno];
 
-			entry->attrmap->attnums[attno] = attrmap->attnums[root_attno - 1];
+			/* 0 means it's a dropped attribute.  See comments atop AttrMap. */
+			if (root_attno == 0)
+				entry->attrmap->attnums[attno] = -1;
+			else
+				entry->attrmap->attnums[attno] = attrmap->attnums[root_attno - 1];
 		}
 	}
 	else