Protect against overflow of ltree.numlevel and lquery.numlevel.

These uint16 fields could be overflowed by excessively long input,
producing strange results.  Complain for invalid input.

Likewise check for out-of-range values of the repeat counts in lquery.
(We don't try too hard on that one, notably not bothering to detect
if atoi's result has overflowed.)

Also detect length overflow in ltree_concat.

In passing, be more consistent about whether "syntax error" messages
include the type name.  Also, clarify the documentation about what
the size limit is.

This has been broken for a long time, so back-patch to all supported
branches.

Nikita Glukhov, reviewed by Benjie Gillam and Tomas Vondra

Discussion: https://postgr.es/m/CAP_rww=waX2Oo6q+MbMSiZ9ktdj6eaJj0cQzNu=Ry2cCDij5fw@mail.gmail.com

contrib/ltree/expected/ltree.out

@@ -457,6 +457,52 @@ SELECT nlevel('1.2.3.4');
       4
 (1 row)
 
+SELECT nlevel(('1' || repeat('.1', 65534))::ltree);
+ nlevel 
+--------
+  65535
+(1 row)
+
+SELECT nlevel(('1' || repeat('.1', 65535))::ltree);
+ERROR:  number of ltree levels (65536) exceeds the maximum allowed (65535)
+SELECT nlevel(('1' || repeat('.1', 65534))::ltree || '1');
+ERROR:  number of ltree levels (65536) exceeds the maximum allowed (65535)
+SELECT ('1' || repeat('.1', 65534))::lquery IS NULL;
+ ?column? 
+----------
+ f
+(1 row)
+
+SELECT ('1' || repeat('.1', 65535))::lquery IS NULL;
+ERROR:  number of lquery levels (65536) exceeds the maximum allowed (65535)
+SELECT '*{65535}'::lquery;
+  lquery  
+----------
+ *{65535}
+(1 row)
+
+SELECT '*{65536}'::lquery;
+ERROR:  lquery syntax error
+LINE 1: SELECT '*{65536}'::lquery;
+               ^
+DETAIL:  Low limit (65536) exceeds the maximum allowed (65535).
+SELECT '*{,65534}'::lquery;
+  lquery   
+-----------
+ *{,65534}
+(1 row)
+
+SELECT '*{,65535}'::lquery;
+ lquery 
+--------
+ *
+(1 row)
+
+SELECT '*{,65536}'::lquery;
+ERROR:  lquery syntax error
+LINE 1: SELECT '*{,65536}'::lquery;
+               ^
+DETAIL:  High limit (65536) exceeds the maximum allowed (65535).
 SELECT '1.2'::ltree  < '2.2'::ltree;
  ?column? 
 ----------

contrib/ltree/ltree.h

@@ -25,6 +25,7 @@ typedef struct
 
 #define LTREE_HDRSIZE	MAXALIGN( offsetof(ltree, data) )
 #define LTREE_FIRST(x)	( (ltree_level*)( ((char*)(x))+LTREE_HDRSIZE ) )
+#define LTREE_MAX_LEVELS	PG_UINT16_MAX	/* ltree.numlevel is uint16 */
 
 
 /* lquery */
@@ -77,6 +78,7 @@ typedef struct
 
 #define LQUERY_HDRSIZE	 MAXALIGN( offsetof(lquery, data) )
 #define LQUERY_FIRST(x)   ( (lquery_level*)( ((char*)(x))+LQUERY_HDRSIZE ) )
+#define LQUERY_MAX_LEVELS	PG_UINT16_MAX	/* lquery.numlevel is uint16 */
 
 #define LQUERY_HASNOT		0x01
 

contrib/ltree/ltree_io.c

@@ -58,11 +58,11 @@ ltree_in(PG_FUNCTION_ARGS)
 		ptr += charlen;
 	}
 
-	if (num + 1 > MaxAllocSize / sizeof(nodeitem))
+	if (num + 1 > LTREE_MAX_LEVELS)
 		ereport(ERROR,
 				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-				 errmsg("number of levels (%d) exceeds the maximum allowed (%d)",
-						num + 1, (int) (MaxAllocSize / sizeof(nodeitem)))));
+				 errmsg("number of ltree levels (%d) exceeds the maximum allowed (%d)",
+						num + 1, LTREE_MAX_LEVELS)));
 	list = lptr = (nodeitem *) palloc(sizeof(nodeitem) * (num + 1));
 	ptr = buf;
 	while (*ptr)
@@ -227,11 +227,11 @@ lquery_in(PG_FUNCTION_ARGS)
 	}
 
 	num++;
-	if (num > MaxAllocSize / ITEMSIZE)
+	if (num > LQUERY_MAX_LEVELS)
 		ereport(ERROR,
 				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
-				 errmsg("number of levels (%d) exceeds the maximum allowed (%d)",
-						num, (int) (MaxAllocSize / ITEMSIZE))));
+				 errmsg("number of lquery levels (%d) exceeds the maximum allowed (%d)",
+						num, LQUERY_MAX_LEVELS)));
 	curqlevel = tmpql = (lquery_level *) palloc0(ITEMSIZE * num);
 	ptr = buf;
 	while (*ptr)
@@ -344,7 +344,7 @@ lquery_in(PG_FUNCTION_ARGS)
 			else if (charlen == 1 && t_iseq(ptr, '.'))
 			{
 				curqlevel->low = 0;
-				curqlevel->high = 0xffff;
+				curqlevel->high = LTREE_MAX_LEVELS;
 				curqlevel = NEXTLEV(curqlevel);
 				state = LQPRS_WAITLEVEL;
 			}
@@ -357,7 +357,16 @@ lquery_in(PG_FUNCTION_ARGS)
 				state = LQPRS_WAITSNUM;
 			else if (t_isdigit(ptr))
 			{
-				curqlevel->low = atoi(ptr);
+				int			low = atoi(ptr);
+
+				if (low < 0 || low > LTREE_MAX_LEVELS)
+					ereport(ERROR,
+							(errcode(ERRCODE_SYNTAX_ERROR),
+							 errmsg("lquery syntax error"),
+							 errdetail("Low limit (%d) exceeds the maximum allowed (%d).",
+									   low, LTREE_MAX_LEVELS)));
+
+				curqlevel->low = (uint16) low;
 				state = LQPRS_WAITND;
 			}
 			else
@@ -367,12 +376,21 @@ lquery_in(PG_FUNCTION_ARGS)
 		{
 			if (t_isdigit(ptr))
 			{
-				curqlevel->high = atoi(ptr);
+				int			high = atoi(ptr);
+
+				if (high < 0 || high > LTREE_MAX_LEVELS)
+					ereport(ERROR,
+							(errcode(ERRCODE_SYNTAX_ERROR),
+							 errmsg("lquery syntax error"),
+							 errdetail("High limit (%d) exceeds the maximum allowed (%d).",
+									   high, LTREE_MAX_LEVELS)));
+
+				curqlevel->high = (uint16) high;
 				state = LQPRS_WAITCLOSE;
 			}
 			else if (charlen == 1 && t_iseq(ptr, '}'))
 			{
-				curqlevel->high = 0xffff;
+				curqlevel->high = LTREE_MAX_LEVELS;
 				state = LQPRS_WAITEND;
 			}
 			else
@@ -422,7 +440,7 @@ lquery_in(PG_FUNCTION_ARGS)
 		if (lptr->start == ptr)
 			ereport(ERROR,
 					(errcode(ERRCODE_SYNTAX_ERROR),
-					 errmsg("syntax error"),
+					 errmsg("lquery syntax error"),
 					 errdetail("Unexpected end of line.")));
 
 		lptr->len = ptr - lptr->start -
@@ -432,7 +450,7 @@ lquery_in(PG_FUNCTION_ARGS)
 		if (lptr->len == 0)
 			ereport(ERROR,
 					(errcode(ERRCODE_SYNTAX_ERROR),
-					 errmsg("syntax error"),
+					 errmsg("lquery syntax error"),
 					 errdetail("Unexpected end of line.")));
 
 		if (lptr->wlen > 255)
@@ -444,11 +462,11 @@ lquery_in(PG_FUNCTION_ARGS)
 							   lptr->wlen, pos)));
 	}
 	else if (state == LQPRS_WAITOPEN)
-		curqlevel->high = 0xffff;
+		curqlevel->high = LTREE_MAX_LEVELS;
 	else if (state != LQPRS_WAITEND)
 		ereport(ERROR,
 				(errcode(ERRCODE_SYNTAX_ERROR),
-				 errmsg("syntax error"),
+				 errmsg("lquery syntax error"),
 				 errdetail("Unexpected end of line.")));
 
 	curqlevel = tmpql;
@@ -468,8 +486,8 @@ lquery_in(PG_FUNCTION_ARGS)
 		else if (curqlevel->low > curqlevel->high)
 			ereport(ERROR,
 					(errcode(ERRCODE_SYNTAX_ERROR),
-					 errmsg("syntax error"),
-					 errdetail("Low limit(%d) is greater than upper(%d).",
+					 errmsg("lquery syntax error"),
+					 errdetail("Low limit (%d) is greater than upper (%d).",
 							   curqlevel->low, curqlevel->high)));
 
 		curqlevel = NEXTLEV(curqlevel);
@@ -593,7 +611,7 @@ lquery_out(PG_FUNCTION_ARGS)
 			}
 			else if (curqlevel->low == 0)
 			{
-				if (curqlevel->high == 0xffff)
+				if (curqlevel->high == LTREE_MAX_LEVELS)
 				{
 					*ptr = '*';
 					*(ptr + 1) = '\0';
@@ -601,7 +619,7 @@ lquery_out(PG_FUNCTION_ARGS)
 				else
 					sprintf(ptr, "*{,%d}", curqlevel->high);
 			}
-			else if (curqlevel->high == 0xffff)
+			else if (curqlevel->high == LTREE_MAX_LEVELS)
 			{
 				sprintf(ptr, "*{%d,}", curqlevel->low);
 			}

contrib/ltree/ltree_op.c

@@ -274,10 +274,17 @@ static ltree *
 ltree_concat(ltree *a, ltree *b)
 {
 	ltree	   *r;
+	int			numlevel = (int) a->numlevel + b->numlevel;
+
+	if (numlevel > LTREE_MAX_LEVELS)
+		ereport(ERROR,
+				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
+				 errmsg("number of ltree levels (%d) exceeds the maximum allowed (%d)",
+						numlevel, LTREE_MAX_LEVELS)));
 
 	r = (ltree *) palloc0(VARSIZE(a) + VARSIZE(b) - LTREE_HDRSIZE);
 	SET_VARSIZE(r, VARSIZE(a) + VARSIZE(b) - LTREE_HDRSIZE);
-	r->numlevel = a->numlevel + b->numlevel;
+	r->numlevel = (uint16) numlevel;
 
 	memcpy(LTREE_FIRST(r), LTREE_FIRST(a), VARSIZE(a) - LTREE_HDRSIZE);
 	memcpy(((char *) LTREE_FIRST(r)) + VARSIZE(a) - LTREE_HDRSIZE,

contrib/ltree/sql/ltree.sql

@@ -90,6 +90,17 @@ SELECT '1.*.4|3|2.*{1}'::lquery;
 SELECT 'qwerty%@*.tu'::lquery;
 
 SELECT nlevel('1.2.3.4');
+SELECT nlevel(('1' || repeat('.1', 65534))::ltree);
+SELECT nlevel(('1' || repeat('.1', 65535))::ltree);
+SELECT nlevel(('1' || repeat('.1', 65534))::ltree || '1');
+SELECT ('1' || repeat('.1', 65534))::lquery IS NULL;
+SELECT ('1' || repeat('.1', 65535))::lquery IS NULL;
+SELECT '*{65535}'::lquery;
+SELECT '*{65536}'::lquery;
+SELECT '*{,65534}'::lquery;
+SELECT '*{,65535}'::lquery;
+SELECT '*{,65536}'::lquery;
+
 SELECT '1.2'::ltree  < '2.2'::ltree;
 SELECT '1.2'::ltree  <= '2.2'::ltree;
 SELECT '2.2'::ltree  = '2.2'::ltree;

doc/src/sgml/ltree.sgml

@@ -37,8 +37,7 @@
    A <firstterm>label path</firstterm> is a sequence of zero or more
    labels separated by dots, for example <literal>L1.L2.L3</literal>, representing
    a path from the root of a hierarchical tree to a particular node.  The
-   length of a label path must be less than 65kB, but keeping it under 2kB is
-   preferable.
+   length of a label path cannot exceed 65535 labels.
   </para>
 
   <para>