From af838f90d3752d6b1379f1c4d092d27fb6d58b89 Mon Sep 17 00:00:00 2001
From: Mark Dilger <mark.dilger@enterprisedb.com>
Date: Tue, 4 May 2021 08:46:56 -0700
Subject: [PATCH v2] Adding more toast pointer checks to amcheck

Expanding the checks of toasted attributes to complain if the
rawsize is overlarge.  For compressed attributes, complaining if
compression appears to have expanded the attribute or if the
compression method is invalid.
---
 contrib/amcheck/verify_heapam.c | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/contrib/amcheck/verify_heapam.c b/contrib/amcheck/verify_heapam.c
index 36c1b791a2..2b5dcfb7c1 100644
--- a/contrib/amcheck/verify_heapam.c
+++ b/contrib/amcheck/verify_heapam.c
@@ -30,6 +30,9 @@ PG_FUNCTION_INFO_V1(verify_heapam);
 /* The number of columns in tuples returned by verify_heapam */
 #define HEAPCHECK_RELATION_COLS 4
 
+/* The largest valid toast va_rawsize */
+#define VARLENA_SIZE_LIMIT 0x3FFFFFFF
+
 /*
  * Despite the name, we use this for reporting problems with both XIDs and
  * MXIDs.
@@ -1384,6 +1387,49 @@ check_tuple_attribute(HeapCheckContext *ctx)
 	 */
 	VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
 
+	/* Toasted attributes too large to be untoasted should never be stored */
+	if (toast_pointer.va_rawsize > VARLENA_SIZE_LIMIT)
+		report_corruption(ctx,
+						  psprintf("toast value %u rawsize %u exceeds limit %u",
+								   toast_pointer.va_valueid,
+								   toast_pointer.va_rawsize,
+								   VARLENA_SIZE_LIMIT));
+
+	if (VARATT_IS_COMPRESSED(&toast_pointer))
+	{
+		ToastCompressionId cmid;
+		bool		valid = false;
+
+		/* Compression should never expand the attribute */
+		if (VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) > toast_pointer.va_rawsize - VARHDRSZ)
+			report_corruption(ctx,
+							  psprintf("toast value %u external size %u exceeds maximum expected for rawsize %u",
+									   toast_pointer.va_valueid,
+									   VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer),
+									   toast_pointer.va_rawsize));
+
+		/* Compressed attributes should have a valid compression method */
+		cmid = TOAST_COMPRESS_METHOD(&toast_pointer);
+		switch (cmid)
+		{
+			/* List of all valid compression method IDs */
+			case TOAST_PGLZ_COMPRESSION_ID:
+			case TOAST_LZ4_COMPRESSION_ID:
+				valid = true;
+				break;
+
+			/* Recognized but invalid compression method ID */
+			case TOAST_INVALID_COMPRESSION_ID:
+				break;
+
+			/* Intentionally no default here */
+		}
+		if (!valid)
+			report_corruption(ctx,
+							  psprintf("toast value %u has invalid compression method id %d",
+									   toast_pointer.va_valueid, cmid));
+	}
+
 	/* The tuple header better claim to contain toasted values */
 	if (!(infomask & HEAP_HASEXTERNAL))
 	{
-- 
2.21.1 (Apple Git-122.3)

