Be more wary of corrupt data in pageinspect's heap_page_items().

tglsfdc · tglsfdc · commit 3f9132ed2822 · 2025-04-19T16:37:43.000-04:00
The original intent in heap_page_items() was to return nulls, not throw an error or crash, if an item was sufficiently corrupt that we couldn't safely extract data from it. However, commit d6061f8 utterly missed that memo, and not only put in an un-length-checked copy of the tuple's data section, but also managed to break the check on sane nulls-bitmap length. Either mistake could possibly lead to a SIGSEGV crash if the tuple is corrupt. Bug: #18896 Reported-by: Dmitry Kovalenko <d.kovalenko@postgrespro.ru> Author: Dmitry Kovalenko <d.kovalenko@postgrespro.ru> Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/18896-add267b8e06663e3@postgresql.org Backpatch-through: 13
diff --git a/contrib/pageinspect/heapfuncs.c b/contrib/pageinspect/heapfuncs.c
@@ -210,11 +210,8 @@ heap_page_items(PG_FUNCTION_ARGS)
 			lp_offset + lp_len <= raw_page_size)
 		{
 			HeapTupleHeader tuphdr;
-			bytea	   *tuple_data_bytea;
-			int			tuple_data_len;
 
 			/* Extract information from the tuple header */
-
 			tuphdr = (HeapTupleHeader) PageGetItem(page, id);
 
 			values[4] = UInt32GetDatum(HeapTupleHeaderGetRawXmin(tuphdr));
@@ -226,31 +223,32 @@ heap_page_items(PG_FUNCTION_ARGS)
 			values[9] = UInt32GetDatum(tuphdr->t_infomask);
 			values[10] = UInt8GetDatum(tuphdr->t_hoff);
 
-			/* Copy raw tuple data into bytea attribute */
-			tuple_data_len = lp_len - tuphdr->t_hoff;
-			tuple_data_bytea = (bytea *) palloc(tuple_data_len + VARHDRSZ);
-			SET_VARSIZE(tuple_data_bytea, tuple_data_len + VARHDRSZ);
-			memcpy(VARDATA(tuple_data_bytea), (char *) tuphdr + tuphdr->t_hoff,
-				   tuple_data_len);
-			values[13] = PointerGetDatum(tuple_data_bytea);
-
 			/*
 			 * We already checked that the item is completely within the raw
 			 * page passed to us, with the length given in the line pointer.
-			 * Let's check that t_hoff doesn't point over lp_len, before using
-			 * it to access t_bits and oid.
+			 * But t_hoff could be out of range, so check it before relying on
+			 * it to fetch additional info.
 			 */
 			if (tuphdr->t_hoff >= SizeofHeapTupleHeader &&
 				tuphdr->t_hoff <= lp_len &&
 				tuphdr->t_hoff == MAXALIGN(tuphdr->t_hoff))
 			{
+				int			tuple_data_len;
+				bytea	   *tuple_data_bytea;
+
+				/* Copy null bitmask and OID, if present */
 				if (tuphdr->t_infomask & HEAP_HASNULL)
 				{
-					int			bits_len;
-
-					bits_len =
-						BITMAPLEN(HeapTupleHeaderGetNatts(tuphdr)) * BITS_PER_BYTE;
-					values[11] = CStringGetTextDatum(bits_to_text(tuphdr->t_bits, bits_len));
+					int			bitmaplen;
+
+					bitmaplen = BITMAPLEN(HeapTupleHeaderGetNatts(tuphdr));
+					/* better range-check the attribute count, too */
+					if (bitmaplen <= tuphdr->t_hoff - SizeofHeapTupleHeader)
+						values[11] =
+							CStringGetTextDatum(bits_to_text(tuphdr->t_bits,
+															 bitmaplen * BITS_PER_BYTE));
+					else
+						nulls[11] = true;
 				}
 				else
 					nulls[11] = true;
@@ -259,11 +257,22 @@ heap_page_items(PG_FUNCTION_ARGS)
 					values[12] = HeapTupleHeaderGetOidOld(tuphdr);
 				else
 					nulls[12] = true;
+
+				/* Copy raw tuple data into bytea attribute */
+				tuple_data_len = lp_len - tuphdr->t_hoff;
+				tuple_data_bytea = (bytea *) palloc(tuple_data_len + VARHDRSZ);
+				SET_VARSIZE(tuple_data_bytea, tuple_data_len + VARHDRSZ);
+				if (tuple_data_len > 0)
+					memcpy(VARDATA(tuple_data_bytea),
+						   (char *) tuphdr + tuphdr->t_hoff,
+						   tuple_data_len);
+				values[13] = PointerGetDatum(tuple_data_bytea);
 			}
 			else
 			{
 				nulls[11] = true;
 				nulls[12] = true;
+				nulls[13] = true;
 			}
 		}
 		else
