From c9f4618e5b0cee1b125e59b947c9f4b3fe1887d2 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Thu, 5 Jun 2014 11:31:22 -0400
Subject: [PATCH] Add defenses against running with a wrong selection of
 LOBLKSIZE.

It's critical that the backend's idea of LOBLKSIZE match the way data has
actually been divided up in pg_largeobject.  While we don't provide any
direct way to adjust that value, doing so is a one-line source code change
and various people have expressed interest recently in changing it.  So,
just as with TOAST_MAX_CHUNK_SIZE, it seems prudent to record the value in
pg_control and cross-check that the backend's compiled-in setting matches
the on-disk data.

Also tweak the code in inv_api.c so that fetches from pg_largeobject
explicitly verify that the length of the data field is not more than
LOBLKSIZE.  Formerly we just had Asserts() for that, which is no protection
at all in production builds.  In some of the call sites an overlength data
value would translate directly to a security-relevant stack clobber, so it
seems worth one extra runtime comparison to be sure.

In the back branches, we can't change the contents of pg_control; but we
can still make the extra checks in inv_api.c, which will offer some amount
of protection against running with the wrong value of LOBLKSIZE.
---
 src/backend/storage/large_object/inv_api.c | 84 ++++++++++------------
 1 file changed, 39 insertions(+), 45 deletions(-)

diff --git a/src/backend/storage/large_object/inv_api.c b/src/backend/storage/large_object/inv_api.c
index 50c654bd362..dc1d7ad944b 100644
--- a/src/backend/storage/large_object/inv_api.c
+++ b/src/backend/storage/large_object/inv_api.c
@@ -174,13 +174,38 @@ myLargeObjectExists(Oid loid, Snapshot snapshot)
 }
 
 
-static int32
-getbytealen(bytea *data)
+/*
+ * Extract data field from a pg_largeobject tuple, detoasting if needed
+ * and verifying that the length is sane.  Returns data pointer (a bytea *),
+ * data length, and an indication of whether to pfree the data pointer.
+ */
+static void
+getdatafield(Form_pg_largeobject tuple,
+			 bytea **pdatafield,
+			 int *plen,
+			 bool *pfreeit)
 {
-	Assert(!VARATT_IS_EXTENDED(data));
-	if (VARSIZE(data) < VARHDRSZ)
-		elog(ERROR, "invalid VARSIZE(data)");
-	return (VARSIZE(data) - VARHDRSZ);
+	bytea	   *datafield;
+	int			len;
+	bool		freeit;
+
+	datafield = &(tuple->data); /* see note at top of file */
+	freeit = false;
+	if (VARATT_IS_EXTENDED(datafield))
+	{
+		datafield = (bytea *)
+			heap_tuple_untoast_attr((struct varlena *) datafield);
+		freeit = true;
+	}
+	len = VARSIZE(datafield) - VARHDRSZ;
+	if (len < 0 || len > LOBLKSIZE)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("pg_largeobject entry for OID %u, page %d has invalid data field size %d",
+						tuple->loid, tuple->pageno, len)));
+	*pdatafield = datafield;
+	*plen = len;
+	*pfreeit = freeit;
 }
 
 
@@ -362,20 +387,14 @@ inv_getsize(LargeObjectDesc *obj_desc)
 	{
 		Form_pg_largeobject data;
 		bytea	   *datafield;
+		int			len;
 		bool		pfreeit;
 
 		if (HeapTupleHasNulls(tuple))	/* paranoia */
 			elog(ERROR, "null field found in pg_largeobject");
 		data = (Form_pg_largeobject) GETSTRUCT(tuple);
-		datafield = &(data->data);		/* see note at top of file */
-		pfreeit = false;
-		if (VARATT_IS_EXTENDED(datafield))
-		{
-			datafield = (bytea *)
-				heap_tuple_untoast_attr((struct varlena *) datafield);
-			pfreeit = true;
-		}
-		lastbyte = data->pageno * LOBLKSIZE + getbytealen(datafield);
+		getdatafield(data, &datafield, &len, &pfreeit);
+		lastbyte = data->pageno * LOBLKSIZE + len;
 		if (pfreeit)
 			pfree(datafield);
 	}
@@ -490,15 +509,7 @@ inv_read(LargeObjectDesc *obj_desc, char *buf, int nbytes)
 			off = (int) (obj_desc->offset - pageoff);
 			Assert(off >= 0 && off < LOBLKSIZE);
 
-			datafield = &(data->data);	/* see note at top of file */
-			pfreeit = false;
-			if (VARATT_IS_EXTENDED(datafield))
-			{
-				datafield = (bytea *)
-					heap_tuple_untoast_attr((struct varlena *) datafield);
-				pfreeit = true;
-			}
-			len = getbytealen(datafield);
+			getdatafield(data, &datafield, &len, &pfreeit);
 			if (len > off)
 			{
 				n = len - off;
@@ -617,16 +628,7 @@ inv_write(LargeObjectDesc *obj_desc, const char *buf, int nbytes)
 			 *
 			 * First, load old data into workbuf
 			 */
-			datafield = &(olddata->data);		/* see note at top of file */
-			pfreeit = false;
-			if (VARATT_IS_EXTENDED(datafield))
-			{
-				datafield = (bytea *)
-					heap_tuple_untoast_attr((struct varlena *) datafield);
-				pfreeit = true;
-			}
-			len = getbytealen(datafield);
-			Assert(len <= LOBLKSIZE);
+			getdatafield(olddata, &datafield, &len, &pfreeit);
 			memcpy(workb, VARDATA(datafield), len);
 			if (pfreeit)
 				pfree(datafield);
@@ -799,19 +801,11 @@ inv_truncate(LargeObjectDesc *obj_desc, int len)
 	if (olddata != NULL && olddata->pageno == pageno)
 	{
 		/* First, load old data into workbuf */
-		bytea	   *datafield = &(olddata->data);		/* see note at top of
-														 * file */
-		bool		pfreeit = false;
+		bytea	   *datafield;
 		int			pagelen;
+		bool		pfreeit;
 
-		if (VARATT_IS_EXTENDED(datafield))
-		{
-			datafield = (bytea *)
-				heap_tuple_untoast_attr((struct varlena *) datafield);
-			pfreeit = true;
-		}
-		pagelen = getbytealen(datafield);
-		Assert(pagelen <= LOBLKSIZE);
+		getdatafield(olddata, &datafield, &pagelen, &pfreeit);
 		memcpy(workb, VARDATA(datafield), pagelen);
 		if (pfreeit)
 			pfree(datafield);