Fix uninitialized access to InitialRunningXacts during decoding after ERROR.

Amit Kapila · Amit Kapila · commit feb4e218e5f9 · 2023-09-12T09:36:56.000+05:30
The transactions and subtransactions array that was allocated under snapshot builder memory context and recorded during decoding was not cleared in case of errors. This can result in an assertion failure if we attempt to retry logical decoding within the same session. To address this issue, we register a callback function under the snapshot builder memory context to clear the recorded transactions and subtransactions array along with the context. This problem doesn't exist in PG16 and HEAD as instead of using InitialRunningXacts, we added the list of transaction IDs and sub-transaction IDs, that have modified catalogs and are running during snapshot serialization, to the serialized snapshot (see commit 7f13ac8). Author: Hou Zhijie Reviewed-by: Amit Kapila Backpatch-through: 11 Discussion: http://postgr.es/m/18055-ab3beed9f4b7b7d6@postgresql.org
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
@@ -336,6 +336,17 @@ SnapBuildStartNextPhaseAt(SnapBuild *builder, TransactionId at)
 	builder->was_running.was_xmax = at;
 }
 
+/*
+ * Memory context reset callback for clearing the array of running transactions
+ * and subtransactions.
+ */
+static void
+SnapBuildResetRunningXactsCallback(void *arg)
+{
+	NInitialRunningXacts = 0;
+	InitialRunningXacts = NULL;
+}
+
 /*
  * Allocate a new snapshot builder.
  *
@@ -351,6 +362,7 @@ AllocateSnapshotBuilder(ReorderBuffer *reorder,
 	MemoryContext context;
 	MemoryContext oldcontext;
 	SnapBuild  *builder;
+	MemoryContextCallback *mcallback;
 
 	/* allocate memory in own context, to have better accountability */
 	context = AllocSetContextCreate(CurrentMemoryContext,
@@ -375,6 +387,10 @@ AllocateSnapshotBuilder(ReorderBuffer *reorder,
 	builder->start_decoding_at = start_lsn;
 	builder->building_full_snapshot = need_full_snapshot;
 
+	mcallback = palloc0(sizeof(MemoryContextCallback));
+	mcallback->func = SnapBuildResetRunningXactsCallback;
+	MemoryContextRegisterResetCallback(CurrentMemoryContext, mcallback);
+
 	MemoryContextSwitchTo(oldcontext);
 
 	/* The initial running transactions array must be empty. */
@@ -400,10 +416,6 @@ FreeSnapshotBuilder(SnapBuild *builder)
 
 	/* other resources are deallocated via memory context reset */
 	MemoryContextDelete(context);
-
-	/* InitialRunningXacts is freed along with the context */
-	NInitialRunningXacts = 0;
-	InitialRunningXacts = NULL;
 }
 
 /*
